Search

Simple Summary: The aim of this study was to assess the impact of various factors—such as age, age at menarche, age at first childbirth, number of births, body mass index (BMI), living environment (rural vs. urban), and other factors later discussed—on the likelihood of developing breast cancer. This article's original research was based on data gathered from 687 breast biopsies, which were analyzed through comparative analysis and regression analysis to identify possible predictors for malignancy and tumor size. The comparative analysis and regression models in this study provide deeper insights into the roles of various variables, particularly positive hormonal receptor status, in malignancy. Introduction: Breast cancer has become one of the most serious and widespread public health concerns globally, affecting an increasing number of women—and, in rare cases, men—across the world. It is the most common cancer among women across all countries. In this study, we aimed to evaluate the influence of demographic factors, medical and reproductive history, diagnostic techniques, and hormone receptor status on the development and progression of breast cancer. Materials and Methods: A total of 687 female patients from Romania underwent standard breast examination techniques, including clinical breast examination, mammography, ultrasonography, and, ultimately, breast biopsy. Statistical analysis was performed using the R programming language and RStudio software. The study included a comparative analysis and a prediction analysis for malignancy and tumor size (cumulative histological dimension) through logistic and linear regression models. Results: The comparative analysis identified several variables associated with malignancy: older age (p < 0.001), non-vulnerability (p = 0.04), no daily physical activity (p = 0.002), no re-biopsy (p < 0.001), immunohistochemistry use (p < 0.001), use of larger gauge needles (p < 0.001), ultrasound-guided biopsy (p < 0.001), and vacuum biopsy (p < 0.001). The hormone receptor statuses—estrogen receptor (ER), progesterone receptor (PR), and androgen receptor (AR)—showed statistically significant differences in distribution across breast cancer B classifications. Logistic regression analysis identified ER, PR, and age as significant predictors of malignancy. Linear regression analysis revealed histopathological results, living environment, geographical region, vulnerability, prior breast examination, and the number of histological fragments as significant predictors of cumulative histological dimension. Conclusions: Our predictive models demonstrate the impact of demographic factors, medical history, diagnostic techniques, and hormone receptor status on breast cancer development and progression, accounting for a significant portion of the variance in malignancy and cumulative histological dimension. [ABSTRACT FROM AUTHOR]

Breast cancer is the most prevalent cancer among women worldwide. B-mode ultrasound (US) is essential for early detection, offering high sensitivity and specificity without radiation exposure. This study introduces a semi-automatic method to streamline breast US report generation, aiming to reduce the burden on radiologists. Our method synthesizes comprehensive breast US reports by combining the extracted information from radiologists' annotations during routine screenings with the analysis results from deep learning algorithms on multimodal US images. Key modules in our method include image classification using visual features (ICVF), type classification via deep learning (TCDL), and automatic report structuring and compilation (ARSC). Experiments showed that the proposed method reduced the average report generation time to 3.8 min compared to manual processes, even when using relatively low-spec hardware. Generated reports perfectly matched ground truth reports for suspicious masses without a single failure on our evaluation datasets. Additionally, the deep-learning-based algorithm, utilizing DenseNet-121 as its core model, achieved an overall accuracy of 0.865, precision of 0.868, recall of 0.847, F1-score of 0.856, and area under the receiver operating characteristics of 0.92 in classifying tissue stiffness in breast US shear-wave elastography (SWE-mode) images. These improvements not only streamline the report generation process but also allow radiologists to dedicate more time and focus on patient care, ultimately enhancing clinical outcomes and patient satisfaction. [ABSTRACT FROM AUTHOR]

Background: Neoadjuvant chemotherapy (NAC) is currently used for treating breast cancer in selected cases. Our study aims to evaluate the role of automated breast ultrasound (ABUS) in the assessment of response to NAC and compare the ABUS results with MRI. Methods: A total of 52 consecutive patients were included in this study. ABUS and MRI sensitivity (SE), specificity (SP), diagnostic accuracy (DA), positive predictive value (PPV), and negative predictive value (NPV) were calculated and represented using Area Under ROC Curve (ROC) analysis, searching for any significant difference (p < 0.05). The McNemar test was used searching for any significant difference in terms of sensitivity by comparing the ABUS and MRI results. The inter-observer agreement between the readers in evaluating the response to NAC for both MRI and ABUS was calculated using Cohen's kappa k coefficient. Results: A total of 35 cases of complete response and 17 cases of persistent disease were found. MRI showed SE, SP, DA, PPV, and NPV values of 100%, 88%, 92%, 81%, and 100%, respectively, with an AUC value of 0.943 (p < 0.0001). ABUS showed SE, SP, DA, PPV, and NPV values of 88%, 94%, 92%, 89%, and 94%, respectively, with an AUC of 0.913 (p < 0.0001). The McNemar test revealed no significant difference (p = 0.1250). The inter-observer agreement between the two readers in evaluating the response to NAC for MRI and ABUS was, respectively, 0.88 and 0.89. Conclusions: Automatic breast ultrasound represents a new accurate, tri-dimensional and operator-independent tool for evaluating patients referred to NAC. [ABSTRACT FROM AUTHOR]

Multi-task learning (MTL) methods are widely applied in breast imaging for lesion area perception and classification to assist in breast cancer diagnosis and personalized treatment. A typical paradigm of MTL is the shared-backbone network architecture, which can lead to information sharing conflicts and result in the decline or even failure of the main task's performance. Therefore, extracting richer lesion features and alleviating information-sharing conflicts has become a significant challenge for breast cancer classification. This study proposes a novel Multi-Feature Fusion Multi-Task (MFFMT) model to effectively address this issue. Firstly, in order to better capture the local and global feature relationships of lesion areas, a Contextual Lesion Enhancement Perception (CLEP) module is designed, which integrates channel attention mechanisms with detailed spatial positional information to extract more comprehensive lesion feature information. Secondly, a novel Multi-Feature Fusion (MFF) module is presented. The MFF module effectively extracts differential features that distinguish between lesion-specific characteristics and the semantic features used for tumor classification, and enhances the common feature information of them as well. Experimental results on two public breast ultrasound imaging datasets validate the effectiveness of our proposed method. Additionally, a comprehensive study on the impact of various factors on the model's performance is conducted to gain a deeper understanding of the working mechanism of the proposed framework. [ABSTRACT FROM AUTHOR]

Our study develops a computer-aided diagnosis (CAD) system for breast ultrasound by presenting an innovative frequency domain technique for extracting mass irregularity features, thereby significantly boosting tumor classification accuracy. The experimental data consists of 5252 ultrasound breast tumor images, including 2745 benign tumors and 2507 malignant tumors. A Support Vector Machine was employed to classify the tumor as either benign or malignant, and the effectiveness of the proposed features set in distinguishing malignant masses from benign ones was validated. For the constructed CAD system, the performance indices' accuracy, sensitivity, specificity, PPV, and NPV were 92.91%, 89.94%, 91.38%, 90.29%, and 91.45%, respectively, and the area index in the ROC analysis (AUC) was 0.924, demonstrating our method's superiority over traditional spatial gray level dependence (SGLD), the ratio of depth to width, the count of depressions, and orientation features. Therefore, the constructed CAD system with the proposed features will be able to provide a precise and quick distinction between benign and malignant breast tumors with minimal training time in clinical settings. [ABSTRACT FROM AUTHOR]

Interoperator variability in the reproducibility of breast lesions found by handheld ultrasound (HHUS) can significantly interfere with clinical care. This study analyzed the features associated with breast mass position differences during HHUS. The ability of operators to reproduce the position of small masses and the time required to generate annotations with and without a computer-assisted scanning device (DEVICE) were also evaluated. This prospective study included 28 patients with 34 benign or probably benign small breast masses. Two operators generated manual and automated position annotations for each mass. The probe and body positions were systematically varied during scanning with the DEVICE, and the features describing mass movement were used in three logistic regression models trained to discriminate small from large breast mass displacements (cutoff: 10 mm). All models successfully discriminated small from large breast mass displacements (areas under the curve: 0.78 to 0.82). The interoperator localization precision was 6.6 ± 2.8 mm with DEVICE guidance and 19.9 ± 16.1 mm with manual annotations. Computer-assisted scanning reduced the time to annotate and reidentify a mass by 33 and 46 s on average, respectively. The results demonstrated that breast mass location reproducibility and exam efficiency improved by controlling operator actionable features with computer-assisted HHUS. [ABSTRACT FROM AUTHOR]

Despite the widely reported potential of deep neural networks for automated breast tumor classification and detection, these models are vulnerable to adversarial attacks, which leads to significant performance degradation on different datasets. In this paper, we introduce a novel adversarial attack approach under the decision-based black-box setting, where the attack does not have access to the model parameters, and the returned information from querying the target model consists of only the final class label prediction (i.e., hard-label attack). The proposed attack approach has two major components: adaptive binary search and semantic-aware search. The adaptive binary search utilizes a coarse-to-fine strategy that applies adaptive tolerance values in different searching stages to reduce unnecessary queries. The proposed semantic mask-aware search crops the search space by using breast anatomy, which significantly avoids invalid searches. We validate the proposed approach using a dataset of 3378 breast ultrasound images and compare it with another state-of-the-art method by attacking five deep learning models. The results demonstrate that the proposed approach generates imperceptible adversarial samples at a high success rate (between 99.52% and 100%), and dramatically reduces the average and median queries by 23.96% and 31.79%, respectively, compared with the state-of-the-art approach. [ABSTRACT FROM AUTHOR]

Simple Summary: Tumor marking before neoadjuvant systemic therapy (NAST) is an essential part of early breast cancer treatment, aiming to enable adequate surgical excision of the tumor bed in cases with complete clinical regression. Standard surgical techniques for targeted excision generally rely on the invasive insertion of various markers (radiopaque clips, radioactive seeds, silver wire, etc.) into or around the tumor. These techniques are burdened by technical complexity, the risk of complications (hematoma, infection, marker migration, etc.), and limited precision in the insertion and later identification of markers. Herein, we present our original technique of non-invasive three-dimensional tumor localization before and repeatedly during NAST and the preliminary results of its application. Multiple repetitions (monitoring the occasionally eccentric pattern of tumor regression) without the risk of complications suggest a possible advantage over invasive marking techniques. Application in surgical centers lacking trained staff and equipment for invasive tumor marking may impact the quality improvement of post-NAST breast cancer surgery in those centers. Background: We present a detailed description and the preliminary results of our original technique for non-invasive three-dimensional tumor localization in the breast, which was created as an alternative to standard invasive tumor marking before neoadjuvant systemic therapy (NAST), aiming to enable adequate surgery after complete tumor regression. Methods: A detailed description of the technique is provided in the main text. The technique's feasibility and precision were assessed in a single-arm, prospective study based on the histological parameters of the adequacy and rationality of the excision of completely regressed tumor beds. Results: Out of 94 recruited patients, 15 (16%) were deemed unsuitable, mainly due to the tumors' inadequate ultrasound visibility. Among the 79 processed patients, 31 (39%) had complete clinical regression after NAST and were operated on using our technique. The histological parameters of surgical precision (signs of tumor regression: 24/31; microscopic cancer residues: 7/31) were verified in all excised specimens (100% precision). There were no positive margins in seven cases with microscopic residues, indicating our technique's capacity to enable oncologically safe post-NAST surgery. Conclusions: The proposed technique is feasible and satisfactorily accurate in determining the location of regressed tumors, thus representing an alternative to invasive tumor marking, especially in surgical centers lacking trained staff and equipment for invasive marking. The technique's limitations are mainly related to the inadequate ultrasound visibility of the tumor. [ABSTRACT FROM AUTHOR]

Breast cancer is a global health concern, emphasizing the need for early detection. However, current mammography struggles to effectively image dense breasts. Breast ultrasound can be an adjunctive method, but it is highly dependent on operator skill. Ultrasound computed tomography (USCT) reflection imaging provides high-quality 3D images, but often uses delay-and-sum (DAS) beamforming, which limits its image quality. This article proposes the integration of coherence-factor (CF) beamforming into ultrasound computed tomography (USCT) reflection imaging to enhance image quality. CF assesses the focus quality of beamforming by analyzing the signal coherence across different channels, assigning higher weights to high-quality focus points and thereby improving overall image quality. Numerical simulations and phantom experiments using our built USCT prototype were conducted to optimize the imaging parameters and assess and compare the image quality of CF and DAS beamforming. Numerical simulations demonstrated that CF beamforming can significantly enhance image quality. Phantom experiments with our prototype revealed that CF beamforming significantly improves image resolution (from 0.35 mm to 0.14 mm) and increases contrast ratio (from 24.54 dB to 63.28 dB). The integration of CF beamforming into USCT reflection imaging represents a substantial improvement in image quality, offering promise for enhanced breast cancer detection and imaging capabilities. [ABSTRACT FROM AUTHOR]

This review provides unique insights to the scientific scope and clinical visions of the inventors and pioneers of the SoftVue breast tomographic ultrasound (BTUS). Their >20-year collaboration produced extensive basic research and technology developments, culminating in SoftVue, which recently received the Food and Drug Administration's approval as an adjunct to breast cancer screening in women with dense breasts. SoftVue's multi-center trial confirmed the diagnostic goals of the tissue characterization and localization of quantitative acoustic tissue differences in 2D and 3D coronal image sequences. SoftVue mass characterizations are also reviewed within the standard cancer risk categories of the Breast Imaging Reporting and Data System. As a quantitative diagnostic modality, SoftVue can also function as a cost-effective platform for artificial intelligence-assisted breast cancer identification. Finally, SoftVue's quantitative acoustic maps facilitate noninvasive temperature monitoring and a unique form of time-reversed, focused US in a single theranostic device that actually focuses acoustic energy better within the highly scattering breast tissues, allowing for localized hyperthermia, drug delivery, and/or ablation. Women also prefer the comfort of SoftVue over mammograms and will continue to seek out less-invasive breast care, from diagnosis to treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: This review analyzes the possibility of breast ultrasound as a primary screening modality for breast cancer, particularly in resource-limited areas. It examines 52 recent papers and underlines ultrasound's advantages, including radiation-free imaging and suitability for younger populations. Reduced specificity and operator reliance are two major challenges. Despite advances such as automatic breast ultrasound (ABUS), this review emphasizes the importance of a comprehensive screening approach, with a focus on international collaboration to enhance global outcomes. Breast cancer, affecting both genders, but mostly females, exhibits shifting demographic patterns, with an increasing incidence in younger age groups. Early identification through mammography, clinical examinations, and breast self-exams enhances treatment efficacy, but challenges persist in low- and medium-income countries due to limited imaging resources. This review assesses the feasibility of employing breast ultrasound as the primary breast cancer screening method, particularly in resource-constrained regions. Following the PRISMA guidelines, this study examines 52 publications from the last five years. Breast ultrasound, distinct from mammography, offers advantages like radiation-free imaging, suitability for repeated screenings, and preference for younger populations. Real-time imaging and dense breast tissue evaluation enhance sensitivity, accessibility, and cost-effectiveness. However, limitations include reduced specificity, operator dependence, and challenges in detecting microcalcifications. Automatic breast ultrasound (ABUS) addresses some issues but faces constraints like potential inaccuracies and limited microcalcification detection. The analysis underscores the need for a comprehensive approach to breast cancer screening, emphasizing international collaboration and addressing limitations, especially in resource-constrained settings. Despite advancements, notably with ABUS, the primary goal is to contribute insights for optimizing breast cancer screening globally, improving outcomes, and mitigating the impact of this debilitating disease. [ABSTRACT FROM AUTHOR]

Traditional B-mode ultrasound has difficulties distinguishing benign from malignant breast lesions. It appears that Quantitative Ultrasound (QUS) may offer advantages. We examined the QUS imaging system's potential, utilizing parameters like Attenuation Coefficient (AC), Speed of Sound (SoS), Effective Scatterer Diameter (ESD), and Effective Scatterer Concentration (ESC) to enhance diagnostic accuracy. B-mode images and radiofrequency signals were gathered from breast lesions. These parameters were processed and analyzed by a QUS system trained on a simulated acoustic dataset and equipped with an encoder-decoder structure. Fifty-seven patients were enrolled over six months. Biopsies served as the diagnostic ground truth. AC, SoS, and ESD showed significant differences between benign and malignant lesions (p < 0.05), but ESC did not. A logistic regression model was developed, demonstrating an area under the receiver operating characteristic curve of 0.90 (95% CI: 0.78, 0.96) for distinguishing between benign and malignant lesions. In conclusion, the QUS system shows promise in enhancing diagnostic accuracy by leveraging AC, SoS, and ESD. Further studies are needed to validate these findings and optimize the system for clinical use. [ABSTRACT FROM AUTHOR]

Simple Summary: Non-calcified mammographic findings, which are suspicious for breast cancer, often undergo ultrasound for further evaluation and to facilitate percutaneous tissue sampling. Most of these findings have a correlation with ultrasound examinations, but some do not. The significance of those without an ultrasound correlation has not been evaluated with modern mammographic techniques. Specifically, mammographic architectural distortion is of particular interest given that it is more commonly identified with digital breast tomosynthesis, a modern quasi-three-dimensional mammographic technique. This article serves to provide management guidance for those situations by retrospectively evaluating a very large cohort of these findings. Suspicious non-calcified mammographic findings have not been evaluated with modern mammographic technique, and the purpose of this work is to compare the likelihood of malignancy for those findings. To do this, 5018 consecutive mammographically guided biopsies performed during 2016–2019 at a large metropolitan, community-based hospital system were retrospectively reviewed. In total, 4396 were excluded for targeting calcifications, insufficient follow-up, or missing data. Thirty-seven of 126 masses (29.4%) were malignant, 44 of 194 asymmetries (22.7%) were malignant, and 77 of 302 architectural distortions (AD, 25.5%) were malignant. The combined likelihood of malignancy was 25.4%. Older age was associated with a higher likelihood of malignancy for each imaging finding type (all p ≤ 0.006), and a possible ultrasound correlation was associated with a higher likelihood of malignancy when all findings were considered together (p = 0.012). Two-view asymmetries were more frequently malignant than one-view asymmetries (p = 0.03). There were two false-negative biopsies (98.7% sensitivity and 100% specificity). In conclusion, the 25.4% likelihood of malignancy confirms the recommendation for biopsy of suspicious, ultrasound-occult, mammographic findings. Mammographically guided biopsies were highly sensitive and specific in this study. Older patient age and a possible ultrasound correlation should raise concern given the increased likelihood of malignancy in those scenarios. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common cancers in the world, especially among women. Breast tumor segmentation is a key step in the identification and localization of the breast tumor region, which has important clinical significance. Inspired by the swin-transformer model with powerful global modeling ability, we propose a semantic segmentation framework named Swin-Net for breast ultrasound images, which combines Transformer and Convolutional Neural Networks (CNNs) to effectively improve the accuracy of breast ultrasound segmentation. Firstly, our model utilizes a swin-transformer encoder with stronger learning ability, which can extract features of images more precisely. In addition, two new modules are introduced in our method, including the feature refinement and enhancement module (RLM) and the hierarchical multi-scale feature fusion module (HFM), given that the influence of ultrasonic image acquisition methods and the characteristics of tumor lesions is difficult to capture. Among them, the RLM module is used to further refine and enhance the feature map learned by the transformer encoder. The HFM module is used to process multi-scale high-level semantic features and low-level details, so as to achieve effective cross-layer feature fusion, suppress noise, and improve model segmentation performance. Experimental results show that Swin-Net performs significantly better than the most advanced methods on the two public benchmark datasets. In particular, it achieves an absolute improvement of 1.4–1.8% on Dice. Additionally, we provide a new dataset of breast ultrasound images on which we test the effect of our model, further demonstrating the validity of our method. In summary, the proposed Swin-Net framework makes significant advancements in breast ultrasound image segmentation, providing valuable exploration for research and applications in this domain. [ABSTRACT FROM AUTHOR]

Background and Objectives: The surge in breast-related surgeries in Korea underscores the critical need for an accurate early diagnosis of silicone breast implant-related issues. Complications such as BIA-ALCL and BIA-SCC add complexity to breast health concerns, necessitating vigilant monitoring. Despite advancements, discrepancies persist between ultrasonographic and pathologic classifications of silicone implant ruptures, highlighting a need for enhanced diagnostic tools. This study explores the reliability of ultrasonography in diagnosing silicone breast implant ruptures and determining the extent of silicone migration, specifically with a focus on guiding potential capsulectomy based on pathology. Materials and Methods: A comprehensive review of medical records encompassing 5557 breast implants across 2790 patients who underwent ultrasound-assisted examinations was conducted. Among the screened implants, 8.9% (249 cases) were diagnosed with silicone breast implant rupture through ultrasonography. Subsequently, 89 women underwent revisional surgery, involving capsulectomy. The pathological analysis of 111 periprosthetic capsules from these cases aimed to assess the extent of silicone migration, and the findings were juxtaposed with the existing ultrasonographic rupture classification. Results: The diagnostic agreement between preoperative sonography and postoperative findings reached 100% for silicone breast implant ruptures. All eighty prosthetic capsules exhibiting a snowstorm sign in ultrasonography demonstrated silicone migration to capsules upon pathologic findings. Conclusions: High-resolution ultrasonography emerged as a valuable and reliable imaging modality for diagnosing silicone breast implant ruptures, with a notable ability to ascertain the extent of free silicone migration to capsules. This diagnostic precision is pivotal in informing decisions about potential capsulectomy during revisional surgery. The study advocates for an update to the current binary ultrasonographic classification, suggesting a more nuanced categorization into three types (subcapsular, intracapsular, and extracapsular) based on pathology. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study on metaplastic breast cancer (BC-Mp), we assessed the accuracy of predicting tumor size measurements in pathology examinations (pT) using (1) preoperative breast ultrasound and (2) full-field digital mammography (cT). The retrospective multi-center cohort study included 45 females with BC-Mp who underwent upfront surgery. Results showed that tumor sizes were statistically assessed as significantly smaller compared to the pathological examination in both imaging methods. Neither of the techniques showed clear statistical superiority, but both were more accurate for smaller tumors. The risk of underestimating tumor size with these methods, especially in larger tumors, needs consideration in surgical planning for BC-Mp. Neither ultrasound nor full-field digital mammography can be recommended as superior in this diagnostic setting. Tumor size was found to be the sole predictive factor for BC-Mp, emphasizing the crucial role of its assessment. Metaplastic breast cancer (BC-Mp) presents diagnostic and therapeutic complexities, with scant literature available. Correct assessment of tumor size by ultrasound (US) and full-field digital mammography (FFDM) is crucial for treatment planning. Methods: A retrospective cohort study was conducted on databases encompassing records of BC patients (2012–2022) at the National Research Institutes of Oncology (Warsaw, Gliwice and Krakow Branches). Inclusion criteria comprised confirmed diagnosis in postsurgical pathology reports with tumor size details (pT) and availability of tumor size from preoperative US and/or FFDM. Patients subjected to neoadjuvant systemic treatment were excluded. Demographics and clinicopathological data were gathered. Results: Forty-five females were included. A total of 86.7% were triple-negative. The median age was 66 years (range: 33–89). The median pT was 41.63 mm (6–130), and eight patients were N-positive. Median tumor size assessed by US and FFDM was 31.81 mm (9–100) and 34.14 mm (0–120), respectively. Neither technique demonstrated superiority (p > 0.05), but they both underestimated the tumor size (p = 0.002 for US and p = 0.018 for FFDM). Smaller tumors (pT1-2) were statistically more accurately assessed by any technique (p < 0.001). Only pT correlated with overall survival. Conclusion: The risk of underestimation in tumor size assessment with US and FFDM has to be taken into consideration while planning surgical procedures for BC-Mp. [ABSTRACT FROM AUTHOR]

The primary aim of our study was to assess the main mammographic and ultrasonographic features of invasive male breast malignancies. The secondary aim was to evaluate whether a specific radiological presentation would be associated with a worse receptor profile. Radiological images (mammography and/or ultrasound) of all patients who underwent surgery for male invasive breast cancer in our institution between 2008 and 2023 were retrospectively analyzed by two breast radiologists in consensus. All significant features of radiological presentation known in the literature were re-evaluated. Fifty-six patients were selected. The mean age at surgery of patients was 69 years (range: 35–81); in 82% of cases (46 patients), the histologic outcome was invasive ductal carcinoma. A total of 28 out of 56 (50%) patients had preoperative mammography; in 9/28 cases (32%), we found a mass with microcalcifications on mammography. The mass presented high density in 25 out of 28 patients (89%); the mass showed irregular margins in 15/28 (54%) cases. A total of 46 out of 56 patients had preoperative ultrasounds. The lesion showed a solid mass in 41/46 (89%) cases. In 5/46 patients (11%), the lesion was a mass with a mixed (partly liquid–partly solid) structure. We did not find any statistically significant correlation between major types of radiological presentation and tumor receptor arrangement. Knowledge of the main radiologic presentation patterns of malignant male breast neoplasm can help better manage this type of disease, which is rare but whose incidence is increasing. [ABSTRACT FROM AUTHOR]

Background and Objectives: This study compares the clinical properties of original breast ultrasound images and those synthesized by a generative adversarial network (GAN) to assess the clinical usefulness of GAN-synthesized images. Materials and Methods: We retrospectively collected approximately 200 breast ultrasound images for each of five representative histological tissue types (cyst, fibroadenoma, scirrhous, solid, and tubule-forming invasive ductal carcinomas) as training images. A deep convolutional GAN (DCGAN) image-generation model synthesized images of the five histological types. Two diagnostic radiologists (reader 1 with 13 years of experience and reader 2 with 7 years of experience) were given a reading test consisting of 50 synthesized and 50 original images (≥1-month interval between sets) to assign the perceived histological tissue type. The percentages of correct diagnoses were calculated, and the reader agreement was assessed using the kappa coefficient. Results: The synthetic and original images were indistinguishable. The correct diagnostic rates from the synthetic images for readers 1 and 2 were 86.0% and 78.0% and from the original images were 88.0% and 78.0%, respectively. The kappa values were 0.625 and 0.650 for the synthetic and original images, respectively. The diagnoses made from the DCGAN synthetic images and original images were similar. Conclusion: The DCGAN-synthesized images closely resemble the original ultrasound images in clinical characteristics, suggesting their potential utility in clinical education and training, particularly for enhancing diagnostic skills in breast ultrasound imaging. [ABSTRACT FROM AUTHOR]

A segmentation model of the ultrasound (US) images of breast tumors based on virtual agents trained using reinforcement learning (RL) is proposed. The agents, living in the edge map, are able to avoid false boundaries, connect broken parts, and finally, accurately delineate the contour of the tumor. The agents move similarly to robots navigating in the unknown environment with the goal of maximizing the rewards. The individual agent does not know the goal of the entire population. However, since the robots communicate, the model is able to understand the global information and fit the irregular boundaries of complicated objects. Combining the RL with a neural network makes it possible to automatically learn and select the local features. In particular, the agents handle the edge leaks and artifacts typical for the US images. The proposed model outperforms 13 state-of-the-art algorithms, including selected deep learning models and their modifications. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this meta-analysis is to investigate the effectiveness of supplementing screening mammography with three-dimensional automated breast ultrasonography (3D ABUS) in improving breast cancer detection rates in asymptomatic women with dense breasts. Materials and Methods: We conducted a thorough review of scientific publications comparing 3D ABUS and mammography. Articles for inclusion were sourced from peer-reviewed journal databases, namely MEDLINE (PubMed) and Scopus, based on an initial screening of their titles and abstracts. To ensure a sufficient sample size for meaningful analysis, only studies evaluating a minimum of 20 patients were retained. Eligibility for evaluation was further limited to articles written in English. Additionally, selected studies were required to have participants aged 18 or above at the time of the study. We analyzed 25 studies published between 2000 and 2021, which included a total of 31,549 women with dense breasts. Among these women, 229 underwent mammography alone, while 347 underwent mammography in combination with 3D ABUS. The average age of the women was 50.86 years (±10 years standard deviation), with a range of 40–56 years. In our efforts to address and reduce bias, we applied a range of statistical analyses. These included assessing study variation through heterogeneity assessment, accounting for potential study variability using a random-effects model, exploring sources of bias via meta-regression analysis, and checking for publication bias through funnel plots and the Egger test. These methods ensured the reliability of our study findings. Results: According to the 25 studies included in this metanalysis, out of the total number of women, 27,495 were diagnosed with breast cancer. Of these, 211 were diagnosed through mammography alone, while an additional 329 women were diagnosed through the combination of full-field digital mammography (FFDSM) and 3D ABUS. This represents an increase of 51.5%. The rate of cancers detected per 1000 women screened was 23.25‰ (95% confidence interval [CI]: 21.20, 25.60; p < 0.001) with mammography alone. In contrast, the addition of 3D ABUS to mammography increased the number of tumors detected to 20.95‰ (95% confidence interval [CI]: 18.50, 23; p < 0.001) per 1000 women screened. Discussion: Even though variability in study results, lack of long-term outcomes, and selection bias may be present, this systematic review and meta-analysis confirms that supplementing mammography with 3D ABUS increases the accuracy of breast cancer detection in women with ACR3 to ACR4 breasts. Our findings suggest that the combination of mammography and 3D ABUS should be considered for screening women with dense breasts. Conclusions: Our research confirms that adding 3D automated breast ultrasound to mammography-only screening in patients with dense breasts (ACR3 and ACR4) significantly (p < 0.05) increases the cancer detection rate. [ABSTRACT FROM AUTHOR]

Background: Breast cancer is arguably one of the leading causes of death among women around the world. The automation of the early detection process and classification of breast masses has been a prominent focus for researchers in the past decade. The utilization of ultrasound imaging is prevalent in the diagnostic evaluation of breast cancer, with its predictive accuracy being dependent on the expertise of the specialist. Therefore, there is an urgent need to create fast and reliable ultrasound image detection algorithms to address this issue. Methods: This paper aims to compare the efficiency of six state-of-the-art, fine-tuned deep learning models that can classify breast tissue from ultrasound images into three classes: benign, malignant, and normal, using transfer learning. Additionally, the architecture of a custom model is introduced and trained from the ground up on a public dataset containing 780 images, which was further augmented to 3900 and 7800 images, respectively. What is more, the custom model is further validated on another private dataset containing 163 ultrasound images divided into two classes: benign and malignant. The pre-trained architectures used in this work are ResNet-50, Inception-V3, Inception-ResNet-V2, MobileNet-V2, VGG-16, and DenseNet-121. The performance evaluation metrics that are used in this study are as follows: Precision, Recall, F1-Score and Specificity. Results: The experimental results show that the models trained on the augmented dataset with 7800 images obtained the best performance on the test set, having 94.95 ± 0.64%, 97.69 ± 0.52%, 97.69 ± 0.13%, 97.77 ± 0.29%, 95.07 ± 0.41%, 98.11 ± 0.10%, and 96.75 ± 0.26% accuracy for the ResNet-50, MobileNet-V2, InceptionResNet-V2, VGG-16, Inception-V3, DenseNet-121, and our model, respectively. Conclusion: Our proposed model obtains competitive results, outperforming some state-of-the-art models in terms of accuracy and training time. [ABSTRACT FROM AUTHOR]

Tumor boundary identification during colorectal cancer surgery can be challenging, and incomplete tumor removal occurs in approximately 10% of the patients operated for advanced rectal cancer. In this paper, a deep learning framework for automatic tumor segmentation in colorectal ultrasound images was developed, to provide real-time guidance on resection margins using intra-operative ultrasound. A colorectal ultrasound dataset was acquired consisting of 179 images from 74 patients, with ground truth tumor annotations based on histopathology results. To address data scarcity, transfer learning techniques were used to optimize models pre-trained on breast ultrasound data for colorectal ultrasound data. A new custom gradient-based loss function (GWDice) was developed, which emphasizes the clinically relevant top margin of the tumor while training the networks. Lastly, ensemble learning methods were applied to combine tumor segmentation predictions of multiple individual models and further improve the overall tumor segmentation performance. Transfer learning outperformed training from scratch, with an average Dice coefficient over all individual networks of 0.78 compared to 0.68. The new GWDice loss function clearly decreased the average tumor margin prediction error from 1.08 mm to 0.92 mm, without compromising the segmentation of the overall tumor contour. Ensemble learning further improved the Dice coefficient to 0.84 and the tumor margin prediction error to 0.67 mm. Using transfer and ensemble learning strategies, good tumor segmentation performance was achieved despite the relatively small dataset. The developed US segmentation model may contribute to more accurate colorectal tumor resections by providing real-time intra-operative feedback on tumor margins. [ABSTRACT FROM AUTHOR]

This single center study includes a comparative analysis of the diagnostic performance of full-field digital mammography (FFDM), contrast-enhanced mammography (CEM) and automatic breast ultrasound (ABUS) in the group of patients with breast American College of Radiology (ACR) categories C and D as well as A and B with FFDM. The study involved 297 patients who underwent ABUS and FFDM. Breast types C and D were determined in 40% of patients with FFDM and low- energy CEM. CEM was performed on 76 patients. Focal lesions were found in 131 patients, of which 115 were histopathologically verified. The number of lesions detected in patients with multiple lesions were 40 from 48 with ABUS, 13 with FFDM and 21 with CEM. Compliance in determining the number of foci was 82% for FFDM and 91% for both CEM and ABUS. In breast types C and D, 72% of all lesions were found with ABUS, 56% with CEM and 29% with FFDM (p = 0.008, p = 0.000); all invasive cancers were diagnosed with ABUS, 83% with CEM and 59% with FFDM (p = 0.000, p = 0.023); 100% DCIS were diagnosed with ABUS, 93% with CEM and 59% with FFDM. The size of lesions from histopathology in breast ACR categories A and B was 14–26 mm, while in breast categories C and D was 11–37 mm. In breast categories C and D, sensitivity of ABUS, FFDM and CEM was, respectively, 78.05, 85.37, 92.68; specificity: 40, 13.33, 8.33; PPV (positive predictive value): 78.05, 72.92, 77.55; NPV (negative predictive value): 40, 25, 25, accuracy: 67.86, 66.07, 73.58. In breast categories A and B, sensitivity of ABUS, FFDM and CEM was, respectively, 81.25, 93.75, 93.48; specificity: 18.18, 18.18, 16.67; PPV: 81.25, 83.33, 89.58; NPV: 18.18, 40, 25; accuracy: 69.49, 79.66, 84.62. The sensitivity of the combination of FFDM and ABUS was 100 for all types of breast categories; the accuracy was 75 in breast types C and D and 81.36 in breast types A and B. The study confirms the predominance of C and D breast anatomy types and the low diagnostic performance of FFDM within that group and indicates ABUS and CEM as potential additive methods in breast cancer diagnostics. [ABSTRACT FROM AUTHOR]

Breast cancer is the most common and deadly cancer in women, where early detection is of the utmost importance as survival rates decrease with the advancement of the disease. Most available methods of breast cancer screening and evaluation lack the ability to effectively differentiate between benign and malignant lesions without a biopsy. Ultrasound elastography (USE) is a cost-effective method that can potentially provide an initial malignancy assessment at the bedside. One of the challenges, however, is the uncertainty of tissue displacement data when performing USE due to out-of-plane movement of the tissue during mechanical stimulation, in addition to the computational efficiency necessary for real-time image reconstruction. This work presents a comparison of four different theoretically sound displacement estimators for their ability in tissue Young's modulus reconstruction level with an emphasis on quality-to-runtime ratio to determine which estimators are most suitable for real-time USE systems. The methods are known in literature as AM2D, GLUE, OVERWIND, and SOUL methods. The effectiveness of each method was assessed as a stand-alone method or in combination with a strain field enhancement technique known as STREAL, which was recently developed using tissue mechanics-based regularization. The study was performed using radiofrequency US data pertaining to in silico and tissue mimicking phantoms in addition to clinical data. This data was used to generate tissue displacement fields employed to generate axial and lateral strain images before Young's modulus images were reconstructed. The study indicates that the AM2D displacement estimator, which is an older and computationally less involved method, along with a tissue-mechanics-based image processing algorithm, performs very well, with high CNR, SNR, and preservation of tumor heterogeneity obtained at both strain and stiffness image levels, while its computation run-time is much lower compared to other estimation methods. As such, it can be recommended for incorporation in real-time USE systems. [ABSTRACT FROM AUTHOR]

Deep learning (DL) models in breast ultrasound (BUS) image analysis face challenges with data imbalance and limited atypical tumor samples. Generative Adversarial Networks (GAN) address these challenges by providing efficient data augmentation for small datasets. However, current GAN approaches fail to capture the structural features of BUS and generated images lack structural legitimacy and are unrealistic. Furthermore, generated images require manual annotation for different downstream tasks before they can be used. Therefore, we propose a two-stage GAN framework, 2s-BUSGAN, for generating annotated BUS images. It consists of the Mask Generation Stage (MGS) and the Image Generation Stage (IGS), generating benign and malignant BUS images using corresponding tumor contours. Moreover, we employ a Feature-Matching Loss (FML) to enhance the quality of generated images and utilize a Differential Augmentation Module (DAM) to improve GAN performance on small datasets. We conduct experiments on two datasets, BUSI and Collected. Moreover, results indicate that the quality of generated images is improved compared with traditional GAN methods. Additionally, our generated images underwent evaluation by ultrasound experts, demonstrating the possibility of deceiving doctors. A comparative evaluation showed that our method also outperforms traditional GAN methods when applied to training segmentation and classification models. Our method achieved a classification accuracy of 69% and 85.7% on two datasets, respectively, which is about 3% and 2% higher than that of the traditional augmentation model. The segmentation model trained using the 2s-BUSGAN augmented datasets achieved DICE scores of 75% and 73% on the two datasets, respectively, which were higher than the traditional augmentation methods. Our research tackles imbalanced and limited BUS image data challenges. Our 2s-BUSGAN augmentation method holds potential for enhancing deep learning model performance in the field. [ABSTRACT FROM AUTHOR]

One of the most prevalent diseases affecting women in recent years is breast cancer. Early breast cancer detection can help in the treatment, lower the infection risk, and worsen the results. This paper presents a hybrid approach for augmentation and segmenting breast cancer. The framework contains two main stages: augmentation and segmentation of ultrasound images. The augmentation of the ultrasounds is applied using generative adversarial networks (GAN) with nonlinear identity block, label smoothing, and a new loss function. The segmentation of the ultrasounds applied a modified U-Net 3+. The hybrid approach achieves efficient results in the segmentation and augmentation steps compared with the other available methods for the same task. The modified version of the GAN with the nonlinear identity block overcomes different types of modified GAN in the ultrasound augmentation process, such as speckle GAN, UltraGAN, and deep convolutional GAN. The modified U-Net 3+ also overcomes the different architectures of U-Nets in the segmentation process. The GAN with nonlinear identity blocks achieved an inception score of 14.32 and a Fréchet inception distance of 41.86 in the augmenting process. The GAN with identity achieves a smaller value in Fréchet inception distance (FID) and a bigger value in inception score; these results prove the model's efficiency compared with other versions of GAN in the augmentation process. The modified U-Net 3+ architecture achieved a Dice Score of 95.49% and an Accuracy of 95.67%. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common female diseases, posing a great threat to women's health, and breast ultrasound imaging is a common method for breast cancer diagnosis. In recent years, U-Net and its variants have dominated the medical image segmentation field with their excellent performance. However, the existing U-type segmentation networks have the following problems: (1) the design of the feature extractor is complicated, and the calculation difficulty is increased; (2) the skip connection operation simply combines the features of the encoder and the decoder, without considering both spatial and channel dimensions; (3) during the downsampling phase, the pooling operation results in the loss of feature information. To address the above deficiencies, this paper proposes a breast tumor segmentation network, RMAU-Net, that combines residual depthwise separable convolution and a multi-scale channel attention gate. Specifically, we designed the RDw block, which has a simple structure and a larger sensory field, to overcome the localization problem of convolutional operations. Meanwhile, the MCAG module is designed to correct the low-level features in both spatial and channel dimensions and assist the high-level features to recover the up-sampling and pinpoint non-regular breast tumor features. In addition, this paper used the Patch Merging operation instead of the pooling method to prevent the loss of breast ultrasound image information. Experiments were conducted on two breast ultrasound datasets, Dataset B and BUSI, and the results show that the method in this paper has superior segmentation performance and better generalization. [ABSTRACT FROM AUTHOR]

Background: Breast cancer is one of the most common malignant tumors in women. A noninvasive ultrasound examination can identify mammary-gland-related diseases and is well tolerated by dense breast, making it a preferred method for breast cancer screening and of significant clinical value. However, the diagnosis of breast nodules or masses via ultrasound is performed by a doctor in real time, which is time-consuming and subjective. Junior doctors are prone to missed diagnoses, especially in remote areas or grass-roots hospitals, due to limited medical resources and other factors, which bring great risks to a patient's health. Therefore, there is an urgent need to develop fast and accurate ultrasound image analysis algorithms to assist diagnoses. Methods: We propose a breast ultrasound image-based assisted-diagnosis method based on convolutional neural networks, which can effectively improve the diagnostic speed and the early screening rate of breast cancer. Our method consists of two stages: tumor recognition and tumor classification. (1) Attention-based semantic segmentation is used to identify the location and size of the tumor; (2) the identified nodules are cropped to construct a training dataset. Then, a convolutional neural network for the diagnosis of benign and malignant breast nodules is trained on this dataset. We collected 2057 images from 1131 patients as the training and validation dataset, and 100 images of the patients with accurate pathological criteria were used as the test dataset. Results: The experimental results based on this dataset show that the MIoU of tumor location recognition is 0.89 and the average accuracy of benign and malignant diagnoses is 97%. The diagnosis performance of the developed diagnostic system is basically consistent with that of senior doctors and is superior to that of junior doctors. In addition, we can provide the doctor with a preliminary diagnosis so that it can be diagnosed quickly. Conclusion: Our proposed method can effectively improve diagnostic speed and the early screening rate of breast cancer. The system provides a valuable aid for the ultrasonic diagnosis of breast cancer. [ABSTRACT FROM AUTHOR]

Ultrasound (US) imaging is used in the diagnosis and monitoring of COVID-19 and breast cancer. The presence of Speckle Noise (SN) is a downside to its usage since it decreases lesion conspicuity. Filters can be used to remove SN, but they involve time-consuming computation and parameter tuning. Several researchers have been developing complex Deep Learning (DL) models (150,000–500,000 parameters) for the removal of simulated added SN, without focusing on the real-world application of removing naturally occurring SN from original US images. Here, a simpler (<30,000 parameters) Convolutional Neural Network Autoencoder (CNN-AE) to remove SN from US images of the breast and lung is proposed. In order to do so, simulated SN was added to such US images, considering four different noise levels (σ = 0.05, 0.1, 0.2, 0.5). The original US images (N = 1227, breast + lung) were given as targets, while the noised US images served as the input. The Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) were used to compare the output of the CNN-AE and of the Median and Lee filters with the original US images. The CNN-AE outperformed the use of these classic filters for every noise level. To see how well the model removed naturally occurring SN from the original US images and to test its real-world applicability, a CNN model that differentiates malignant from benign breast lesions was developed. Several inputs were used to train the model (original, CNN-AE denoised, filter denoised, and noised US images). The use of the original US images resulted in the highest Matthews Correlation Coefficient (MCC) and accuracy values, while for sensitivity and negative predicted values, the CNN-AE-denoised US images (for higher σ values) achieved the best results. Our results demonstrate that the application of a simpler DL model for SN removal results in fewer misclassifications of malignant breast lesions in comparison to the use of original US images and the application of the Median filter. This shows that the use of a less-complex model and the focus on clinical practice applicability are relevant and should be considered in future studies. [ABSTRACT FROM AUTHOR]

Breast cancer is the leading type of cancer in women, causing nearly 600,000 deaths every year, globally. Although the tumors can be localized within the breast, they can spread to other body parts, causing more harm. Therefore, early diagnosis can help reduce the risks of this cancer. However, a breast cancer diagnosis is complicated, requiring biopsy by various methods, such as MRI, ultrasound, BI-RADS, or even needle aspiration and cytology with the suggestions of specialists. On certain occasions, such as body examinations of a large number of people, it is also a large workload to check the images. Therefore, in this work, we present an efficient and automatic diagnosis system based on the hierarchical extreme learning machine (H-ELM) for breast cancer ultrasound results with high efficiency and make a primary diagnosis of the images. To make it compatible to use, this system consists of PNG images and general medical software within the H-ELM framework, which is easily trained and applied. Furthermore, this system only requires ultrasound images on a small scale, of 28 × 28 pixels, reducing the resources and fulfilling the application with low-resolution images. The experimental results show that the system can achieve 86.13% in the classification of breast cancer based on ultrasound images from the public breast ultrasound images (BUSI) dataset, without other relative information and supervision, which is higher than the conventional deep learning methods on the same dataset. Moreover, the training time is highly reduced, to only 5.31 s, and consumes few resources. The experimental results indicate that this system could be helpful for precise and efficient early diagnosis of breast cancers with primary examination results. [ABSTRACT FROM AUTHOR]

Introduction: Nowadays chemotherapy in breast cancer patients is optionally applied neoadjuvant, which allows for testing of tumor response to the chemotherapeutical treatment in vivo, as well as allowing a greater number of patients to benefit from a subsequent breast-conserving surgery. Material and methods: We compared breast ultrasonography, mammography, and clinical examination (palpation) results with postoperative histopathological findings after neoadjuvant chemotherapy, aiming to determine the most accurate prediction of complete remission and tumor-free resection margins. To this end, clinical and imaging data of 184 patients (193 tumors) with confirmed diagnosis of breast cancer and neoadjuvant therapy were analyzed. Results: After chemotherapy, tumors could be assessed by palpation in 91.7%, by sonography in 99.5%, and by mammography in 84.5% (chi-square p < 0.0001) of cases. Although mammography proved more accurate in estimating the exact neoadjuvant tumor size than breast sonography in total numbers (136/163 (83.44%) vs. 142/192 (73.96%), n.s.), 29 tumors could be assessed solely by means of breast sonography. A sonographic measurement was feasible in 192 cases (99.48%) post-chemotherapy and in all cases prior to chemotherapy. Conclusions: We determined a superiority of mammography and breast sonography over clinical palpation in predicting neoadjuvant tumor size. However, neither examination method can predict either pCR or tumor margins with high confidence. [ABSTRACT FROM AUTHOR]

The quality of breast ultrasound images has a significant impact on the accuracy of disease diagnosis. Existing image quality assessment (IQA) methods usually use pixel-level feature statistical methods or end-to-end deep learning methods, which focus on the global image quality but ignore the image quality of the lesion region. However, in clinical practice, doctors' evaluation of ultrasound image quality relies more on the local area of the lesion, which determines the diagnostic value of ultrasound images. In this study, a global–local integrated IQA framework for breast ultrasound images was proposed to learn doctors' clinical evaluation standards. In this study, 1285 breast ultrasound images were collected and scored by experienced doctors. After being classified as either images with lesions or images without lesions, they were evaluated using soft-reference IQA or bilinear CNN IQA, respectively. Experiments showed that for ultrasound images with lesions, our proposed soft-reference IQA achieved PLCC 0.8418 with doctors' annotation, while the existing end-to-end deep learning method that did not consider the local lesion features only achieved PLCC 0.6606. Due to the accuracy improvement for the images with lesions, our proposed global–local integrated IQA framework had better performance in the IQA task than the existing end-to-end deep learning method, with PLCC improving from 0.8306 to 0.8851. [ABSTRACT FROM AUTHOR]

The aim of this prospective study was to compare the diagnostic performance of contrast-enhanced mammography (CEM) versus digital mammography (DM) combined with breast ultrasound (BUS) in women with dense breasts. Between March 2021 and February 2022, patients eligible for CEM with the breast composition category ACR BI-RADS c–d at DM and an abnormal finding (BI-RADS 3-4-5) at DM and/or BUS were considered. During CEM, a nonionic iodinated contrast agent (Iohexol 350 mg I/mL, 1.5 mL/kg) was power-injected intravenously. Images were evaluated independently by two breast radiologists. Findings classified as BI-RADS 1–3 were considered benign, while BI-RADS 4–5 were considered malignant. In case of discrepancies, the higher category was considered for DM+BUS. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated, using histology/≥12-month follow-up as gold standards. In total, 51 patients with 65 breast lesions were included. 59 (90.7%) abnormal findings were detected at DM+BUS, and 65 (100%) at CEM. The inter-reader agreement was excellent (Cohen's k = 0.87 for DM+BUS and 0.97 for CEM). CEM showed a 93.5% sensitivity (vs. 90.3% for DM+BUS), a 79.4–82.4% specificity (vs. 32.4–35.5% for DM+BUS) (McNemar p = 0.006), a 80.6–82.9% PPV (vs. 54.9–56.0% for DM+BUS), a 93.1–93.3% NPV (vs. 78.6–80.0% for DM+BUS), and a 86.1–87.7% accuracy (vs. 60.0–61.5% for DM+BUS). The AUC was higher for CEM than for DM+BUS (0.865 vs. 0.613 for Reader 1, and 0.880 vs. 0.628, for Reader 2) (p < 0.001). In conclusion, CEM had a better diagnostic performance than DM and BUS alone and combined together in patients with dense breasts. [ABSTRACT FROM AUTHOR]

In the past few years, deep learning has gained increasingly widespread attention and has been applied to diagnosing benign and malignant thyroid nodules. It is difficult to acquire sufficient medical images, resulting in insufficient data, which hinders the development of an efficient deep-learning model. In this paper, we developed a deep-learning-based characterization framework to differentiate malignant and benign nodules from the thyroid ultrasound images. This approach improves the recognition accuracy of the inception network by combining squeeze and excitation networks with the inception modules. We have also integrated the concept of multi-level transfer learning using breast ultrasound images as a bridge dataset. This transfer learning approach addresses the issues regarding domain differences between natural images and ultrasound images during transfer learning. This paper aimed to investigate how the entire framework could help radiologists improve diagnostic performance and avoid unnecessary fine-needle aspiration. The proposed approach based on multi-level transfer learning and improved inception blocks achieved higher precision (0.9057 for the benign class and 0.9667 for the malignant class), recall (0.9796 for the benign class and 0.8529 for malignant), and F1-score (0.9412 for benign class and 0.9062 for malignant class). It also obtained an AUC value of 0.9537, which is higher than that of the single-level transfer learning method. The experimental results show that this model can achieve satisfactory classification accuracy comparable to experienced radiologists. Using this model, we can save time and effort as well as deliver potential clinical application value. [ABSTRACT FROM AUTHOR]

Introduction: Ultrasound is a non-invasive, low-cost technique that does not use ionising radiation and provides a "real-time" image, and for these reasons, this method is ideal in several situations. Purpose: To demonstrate breast ultrasound evaluation as a first-line diagnostic method and to evaluate the variation of breast characteristics with age. Material and Methods: A total of 105 women with a mean age of 30 years participated and were divided into three age groups: 18–39, 40–59, and 60–79 years, excluding participants subject to mastectomy. After completing the informed consent, all participants answered personal and sociodemographic questions, such as personal and family history, menstrual cycle, pregnancy, ultrasound, and mammography, among others. They were then submitted to a bilateral breast ultrasound examination. Subsequently, all the images and their data were analysed, and a technical report of the examination was given to all the participants. Results: A total of 105 women with a mean age of 30 years participated, 58 of whom underwent the examination for the first time. In 31, changes (of which only 7 were known) were diagnosed. It was verified that, according to age group, the density of the breast stroma varied; older women have less breast density. Conclusions: Ultrasound is a good method for breast evaluation and can be considered important for the early evaluation of breast pathology and follow-up of the pathology. [ABSTRACT FROM AUTHOR]

Early detection of breast lesions and distinguishing between malignant and benign lesions are critical for breast cancer (BC) prognosis. Breast ultrasonography (BU) is an important radiological imaging modality for the diagnosis of BC. This study proposes a BU image-based framework for the diagnosis of BC in women. Various pre-trained networks are used to extract the deep features of the BU images. Ten wrapper-based optimization algorithms, including the marine predator algorithm, generalized normal distribution optimization, slime mold algorithm, equilibrium optimizer (EO), manta-ray foraging optimization, atom search optimization, Harris hawks optimization, Henry gas solubility optimization, path finder algorithm, and poor and rich optimization, were employed to compute the optimal subset of deep features using a support vector machine classifier. Furthermore, a network selection algorithm was employed to determine the best pre-trained network. An online BU dataset was used to test the proposed framework. After comprehensive testing and analysis, it was found that the EO algorithm produced the highest classification rate for each pre-trained model. It produced the highest classification accuracy of 96.79%, and it was trained using only a deep feature vector with a size of 562 in the ResNet-50 model. Similarly, the Inception-ResNet-v2 had the second highest classification accuracy of 96.15% using the EO algorithm. Moreover, the results of the proposed framework are compared with those in the literature. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) applications in mammography have gained significant popular attention; however, AI has the potential to revolutionize other aspects of breast imaging beyond simple lesion detection. AI has the potential to enhance risk assessment by combining conventional factors with imaging and improve lesion detection through a comparison with prior studies and considerations of symmetry. It also holds promise in ultrasound analysis and automated whole breast ultrasound, areas marked by unique challenges. AI's potential utility also extends to administrative tasks such as MQSA compliance, scheduling, and protocoling, which can reduce the radiologists' workload. However, adoption in breast imaging faces limitations in terms of data quality and standardization, generalizability, benchmarking performance, and integration into clinical workflows. Developing methods for radiologists to interpret AI decisions, and understanding patient perspectives to build trust in AI results, will be key future endeavors, with the ultimate aim of fostering more efficient radiology practices and better patient care. [ABSTRACT FROM AUTHOR]

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer-aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA-approved AI applications for breast imaging, but adoption and utilization are widely variable and low overall. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer, and many of the most exciting research projects and available AI applications focus on cancer detection for mammography. There are, however, multiple additional potential applications for AI in breast imaging, including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization. [ABSTRACT FROM AUTHOR]

The preoperative differentiation of breast phyllodes tumors (PTs) from fibroadenomas (FAs) plays a critical role in identifying an appropriate surgical treatment. Although several imaging modalities are available, reliable differentiation between PT and FA remains a great challenge for radiologists in clinical work. Artificial intelligence (AI)-assisted diagnosis has shown promise in distinguishing PT from FA. However, a very small sample size was adopted in previous studies. In this work, we retrospectively enrolled 656 breast tumors (372 FAs and 284 PTs) with 1945 ultrasound images in total. Two experienced ultrasound physicians independently evaluated the ultrasound images. Meanwhile, three deep-learning models (i.e., ResNet, VGG, and GoogLeNet) were applied to classify FAs and PTs. The robustness of the models was evaluated by fivefold cross validation. The performance of each model was assessed by using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were also calculated. Among the three models, the ResNet model yielded the highest AUC value, of 0.91, with an accuracy value of 95.3%, a sensitivity value of 96.2%, and a specificity value of 94.7% in the testing data set. In contrast, the two physicians yielded an average AUC value of 0.69, an accuracy value of 70.7%, a sensitivity value of 54.4%, and a specificity value of 53.2%. Our findings indicate that the diagnostic performance of deep learning is better than that of physicians in the distinction of PTs from FAs. This further suggests that AI is a valuable tool for aiding clinical diagnosis, thereby advancing precision therapy. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate contrast-enhanced mammography (CEM) and to compare breast lesions on CEM and breast magnetic resonance imaging (MRI) using 5 features. We propose a flowchart for BI-RADS classification of breast lesions on CEM based on the Kaiser score (KS) flowchart for breast MRI. Sixty-eight subjects (women and men; median age 61.4 ± 11.6 years) who were suspected of having a malignant process in the breast based on digital mammography (MG) findings were included in the study. The patients underwent breast ultrasound (US), CEM, MRI and biopsy of the suspicious lesion. There were 47 patients with malignant lesions confirmed by biopsy and 21 patients with benign lesions, for each of which a KS was calculated. In the patients with malignant lesions, the MRI-derived KS was 9 (IQR 8–9); its CEM equivalent was 9 (IQR 8–9); and BI-RADS was 5 (IQR 4–5). In patients with benign lesions, MRI-derived KS was 3 (IQR 2–3); its CEM equivalent was 3 (IQR 1.7–5); and BI-RADS was 3 (IQR 0–4). There was no significant difference between the ROC-AUC of CEM and MRI (p = 0.749). In conclusion, there were no significant differences in KS results between CEM and breast MRI. The KS flowchart is useful for evaluating breast lesions on CEM. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common malignancies that threaten women's health. Ultrasound testing is a widespread technique employed for the early detection of tumors. However, after receiving the paper ultrasound report, most patients often have to wait for several days to receive the diagnosis results, which can increase their psychological burden and may cause treatment delay. Based on deep learning, this study designed a computer-aided diagnostic system that directly classifies benign and malignant tumors in breast ultrasound images on paper reports taken by patients, helping them obtain auxiliary diagnostic results as soon as possible. In order to segment and denoise ultrasound report images of patients, this paper proposes a breast ultrasound report generation method, which mainly includes a segmentation model, a rotating classification model and a generative model. With this method, multiple high-quality individual breast ultrasound images can be obtained from a single ultrasound report photo, improving the performance of the breast ultrasound image classification model. In order to utilize high-quality breast ultrasound images and improve classification performance, this paper proposed a breast ultrasound report classification model that includes a feature extraction module, a channel attention module and a classification module. The accuracy of the model reached 89.31%, recall rate reached 88.65%, specificity reached 89.57%, F1 score reached 89.42% and AUC reached 94.53% when input images contained noise. The method proposed in this article is more suitable for practical application scenarios and it can quickly and accurately assist patients in obtaining the benign and malignant classification results of ultrasound reports. [ABSTRACT FROM AUTHOR]

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide a more accurate and objective diagnosis of breast cancer, leading to improved patient outcomes. [ABSTRACT FROM AUTHOR]

Background. To evaluate the radiological features of B3 lesions in patients with genetic mutations to establish an anatomo-radiological correlation. Methods. A total of 227 women with a histological diagnosis of B3 breast lesion were enrolled. Breast images of 21 patients with genetic test positivity for mutations in genes associated with breast cancer were analyzed. Results. BRCA1 was the most frequent mutation (n = 12) followed by ATM (n = 6) and BRCA2 (n = 3). The histological findings showed nine atypical ductal hyperplasia (ADH), six lobular neoplasia (LN) including lobular carcinoma in situ (LCIS), three flat epithelial atypia (FEA) and three radial scar (RS) lesions. The results showed a significance difference between B3 lesion distribution in the three subgroups of mutations. LN and FEA showed the highest malignancy correlation. Patient age and risk anamnesis were factors that significantly influenced the malignancy rate. By mammography, 90.5% of lesions appeared as microcalcifications. By ultrasound, 13 lesions were observed as hypoechoic lesions. On breast MRI, 16 lesions were detected as a mass enhancement in all groups. DWI and kinetic curves significantly correlated with the risk of cancer. Conclusions. The radiological features of B3 lesions may help in the diagnosis of breast cancer malignancy. The high malignancy rate of cancer in our sample suggests they should always be surgically excised. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer (BC) screening is significantly important for reducing disease mortality. Mammography (MAM) is the gold standard for BC screening in high-income countries, while it is usually unavailable and infeasible in low- and middle-income countries (LMICs). Ultrasound (US) has been widely employed as an adjunct to MAM, particularly showing advantages over MAM for women of younger ages and with dense breasts. Nevertheless, it remains controversial whether US could be utilized as a primary tool for BC screening in underserved settings. This review focuses on randomized controlled trials and observational studies that demonstrated the role of US in BC screening. Furthermore, advanced techniques that might be useful to improve BC screening in LMICs are discussed. The results suggest that US, showing high sensitivity and an early detection rate, holds promise to achieve cost-effective screening initiatives where MAM is not available. The resource-appropriate recommendations on implementing BC screening in LMICs are also presented. Breast cancer (BC) is the most prevalent cancer among women globally. Cancer screening can reduce mortality and improve women's health. In developed countries, mammography (MAM) has been primarily utilized for population-based BC screening for several decades. However, it is usually unavailable in low-resource settings due to the lack of equipment, personnel, and time necessary to conduct and interpret the examinations. Ultrasound (US) with high detection sensitivity for women of younger ages and with dense breasts has become a supplement to MAM for breast examination. Some guidelines suggest using US as the primary screening tool in certain settings where MAM is unavailable and infeasible, but global recommendations have not yet reached a unanimous consensus. With the development of smart devices and artificial intelligence (AI) in medical imaging, clinical applications and preclinical studies have shown the potential of US combined with AI in BC screening. Nevertheless, there are few comprehensive reviews focused on the role of US in screening BC in underserved conditions, especially in technological, economical, and global perspectives. This work presents the benefits, limitations, advances, and future directions of BC screening with technology-assisted and resource-appropriate strategies, which may be helpful to implement screening initiatives in resource-limited countries. [ABSTRACT FROM AUTHOR]

(1) Objective: To evaluate the diagnostic performance of prototype handheld ultrasound compared to automated breast ultrasound, according to the fifth edition of BI-RADS categorization, among females with positive lumps. (2) Methods: A total of 1004 lesions in 162 participants who underwent both prototype handheld ultrasound and automated breast ultrasound were included. Two radiologists and a sonographer independently evaluated the sonographic features of each lesion according to the fifth BI-RADS edition. The kappa coefficient (κ) was calculated for each BI-RADS descriptor and final assessment category. The cross-tabulation was performed to see whether there were differences between the ABUS and prototype HHUS results. Specificity and sensitivity were evaluated and compared using the McNamar test. (3) Results: ABUS and prototype HHUS observers found the same number of breast lesions in the 324 breasts of the 162 respondents. There was no significant difference in the mean lesion size, with a maximum mean length dimension of 0.48 ± 0.33 cm. The assessment of the lesion's shape, orientation, margin, echo pattern, posterior acoustic features, and calcification was obtained with good to excellent agreements between ABUS and prototype HHUS observers (κ = 0.70–1.0). There was absolutely no significant difference between ABUS and prototype HHUS in assessment of lesion except for lesion orientation p = 0.00. Diagnostic accuracy (99.8% and 97.7–98.9%), sensitivity (99.5% and 98.0–99.0%), specificity (99.8% and 99.6–99.8%), positive predictive value (98.1% and 90.3–96.2%), negative predictive value (90.0% and 84.4–88.7%), and areas under the curve (0.98 and 0.83–0.92; p < 0.05) were not significantly different between ABUS and prototype HHUS observers. (4) Conclusion: According to the fifth BI-RADS edition, automated breast ultrasound is not statistically significantly different from prototype handheld ultrasound with regard to interobserver variability and diagnostic performance. [ABSTRACT FROM AUTHOR]

Recently, the Vision Transformer (ViT) model has been used for various computer vision tasks, due to its advantages to extracting long-range features. To better integrate the long-range features useful for classification, the standard ViT adds a class token, in addition to patch tokens. Despite state-of-the-art results on some traditional vision tasks, the ViT model typically requires large datasets for supervised training, and thus, it still face challenges in areas where it is difficult to build large datasets, such as medical image analysis. In the ViT model, only the output corresponding to the class token is fed to a Multi-Layer Perceptron (MLP) head for classification, and the outputs corresponding to the patch tokens are exposed. In this paper, we propose an improved ViT architecture (called ViT-Patch), which adds a shared MLP head to the output of each patch token to balance the feature learning on the class and patch tokens. In addition to the primary task, which uses the output of the class token to discriminate whether the image is malignant, a secondary task is introduced, which uses the output of each patch token to determine whether the patch overlaps with the tumor area. More interestingly, due to the correlation between the primary and secondary tasks, the supervisory information added to the patch tokens help with improving the performance of the primary task on the class token. The introduction of secondary supervision information also improves the attention interaction among the class and patch tokens. And by this way, ViT reduces the demand on dataset size. The proposed ViT-Patch is validated on a publicly available dataset, and the experimental results show its effectiveness for both malignant identification and tumor localization. [ABSTRACT FROM AUTHOR]

In the medical field, it is delicate to anticipate good performance in using deep learning due to the lack of large-scale training data and class imbalance. In particular, ultrasound, which is a key breast cancer diagnosis method, is delicate to diagnose accurately as the quality and interpretation of images can vary depending on the operator's experience and proficiency. Therefore, computer-aided diagnosis technology can facilitate diagnosis by visualizing abnormal information such as tumors and masses in ultrasound images. In this study, we implemented deep learning-based anomaly detection methods for breast ultrasound images and validated their effectiveness in detecting abnormal regions. Herein, we specifically compared the sliced-Wasserstein autoencoder with two representative unsupervised learning models autoencoder and variational autoencoder. The anomalous region detection performance is estimated with the normal region labels. Our experimental results showed that the sliced-Wasserstein autoencoder model outperformed the anomaly detection performance of others. However, anomaly detection using the reconstruction-based approach may not be effective because of the occurrence of numerous false-positive values. In the following studies, reducing these false positives becomes an important challenge. [ABSTRACT FROM AUTHOR]

The appropriate management strategies for BI-RADS category 4a lesions among handheld ultrasound (HHUS) remain a matter of debate. We aimed to explore the role of automated breast ultrasound (ABUS) or the second-look mammography (MAM) adjunct to ultrasound (US) of 4a masses to reduce unnecessary biopsies. Women aged 30 to 69 underwent HHUS and ABUS from 2016 to 2017 at five high-level hospitals in China, with those aged 40 or older also accepting MAM. Logistic regression analysis assessed image variables correlated with false-positive lesions in US category 4a. Unnecessary biopsies, invasive cancer (IC) yields, and diagnostic performance among different biopsy thresholds were compared. A total of 1946 women (44.9 ± 9.8 years) were eligible for analysis. The false-positive rate of category 4a in ABUS was almost 65.81% (77/117), which was similar to HHUS (67.55%; 127/188). Orientation, architectural distortion, and duct change were independent factors associated with the false-positive lesions in 4a of HHUS, whereas postmenopausal, calcification, and architectural distortion were significant features of ABUS (all p < 0.05). For HHUS, both unnecessary biopsy rate and IC yields were significantly reduced when changing biopsy thresholds by adding MAM for US 4a in the total population (scenario #1:BI-RADS 3, 4, and 5; scenario #2: BI-RADS 4 and 5) compared with the current scenario (all p < 0.05). Notably, scenario #1 reduced false-positive biopsies without affecting IC yields when compared to the current scenario for ABUS (p < 0.001; p = 0.125). The higher unnecessary biopsy rate of category 4a by ABUS was similar to HHUS. However, the second-look MAM adjunct to ABUS has the potential to safely reduce false-positive biopsies compared with HHUS. [ABSTRACT FROM AUTHOR]

Ultrasound imaging is cost effective, radiation-free, portable, and implemented routinely in clinical procedures. Nonetheless, image quality is characterized by a granulated appearance, a poor SNR, and speckle noise. Specific for breast tumors, the margins are commonly blurred and indistinct. Thus, there is a need for improving ultrasound image quality. We hypothesize that this can be achieved by translation into a more realistic display which mimics a pseudo anatomical cut through the tissue, using a cycle generative adversarial network (CycleGAN). In order to train CycleGAN for this translation, two datasets were used, "Breast Ultrasound Images" (BUSI) and a set of optical images of poultry breast tissues. The generated pseudo anatomical images provide improved visual discrimination of the lesions through clearer border definition and pronounced contrast. In order to evaluate the preservation of the anatomical features, the lesions in both datasets were segmented and compared. This comparison yielded median dice scores of 0.91 and 0.70; median center errors of 0.58% and 3.27%; and median area errors of 0.40% and 4.34% for the benign and malignancies, respectively. In conclusion, generated pseudo anatomical images provide a more intuitive display, enhance tissue anatomy, and preserve tumor geometry; and can potentially improve diagnoses and clinical outcomes. [ABSTRACT FROM AUTHOR]

Breast ultrasound (US) has undergone dramatic technological improvement through recent decades, moving from a low spatial resolution, grayscale-limited technique to a highly performing, multiparametric modality. In this review, we first focus on the spectrum of technical tools that have become commercially available, including new microvasculature imaging modalities, high-frequency transducers, extended field-of-view scanning, elastography, contrast-enhanced US, MicroPure, 3D US, automated US, S-Detect, nomograms, images fusion, and virtual navigation. In the subsequent section, we discuss the broadened current application of US in breast clinical scenarios, distinguishing among primary US, complementary US, and second-look US. Finally, we mention the still ongoing limitations and the challenging aspects of breast US. [ABSTRACT FROM AUTHOR]