Search

Copyright of Der Hautarzt is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Convolutional neural networks (CNNs) have shown a dermatologist-level performance in the classification of skin lesions. We aimed to deliver a head-to-head comparison of a conventional image analyser (CIA), which depends on segmentation and weighting of handcrafted features, to a CNN trained by deep learning. Cross-sectional study using a real-world, prospectively acquired, dermoscopic dataset of 1981 skin lesions to compare the diagnostic performance of a market-approved CNN (Moleanalyzer-Pro™, developed in 2018) to a CIA (Moleanalyzer-3™/Dynamole™; developed in 2004, all FotoFinder Systems Inc, Germany). As a reference standard, we used histopathological diagnoses (n = 785) or, in non-excised benign lesions (n = 1196), expert consensus plus an uneventful follow-up by sequential digital dermoscopy for at least 2 years. A total of 281 malignant lesions and 1700 benign lesions from 435 patients (62.2% male, mean age: 52 years) were prospectively imaged. The CNN showed a sensitivity of 77.6% (95% confidence interval [CI]: [72.4%–82.1%]), specificity of 95.3% (95% CI: [94.2%–96.2%]), and receiver operating characteristic (ROC)-area under the curve (AUC) of 0.945 (95% CI: [0.930–0.961]). In contrast, the CIA achieved a sensitivity of 53.4% (95% CI: [47.5%–59.1%]), specificity of 86.6% (95% CI: [84.9%–88.1%]) and ROC-AUC of 0.738 (95% CI: [0.701–0.774]). The data set included melanomas originally diagnosed by dynamic changes during sequential digital dermoscopy (52 of 201, 20.6%), which reduced the sensitivities of both classifiers. Pairwise comparisons of sensitivities, specificities, and ROC-AUCs indicated a clear outperformance by the CNN (all p < 0.001). The superior diagnostic performance of the CNN argues against a continued application of former CIAs as an aide to physicians' clinical management decisions. • We compared two market-approved computer-algorithms for skin cancer detection. • A conventional image analyser (CIA) was compared with a deep learning convolutional neural network (CNN). • The CNN significantly outperformed the CIA in sensitivity, specificity, and area under the receiver operating characteristic curve. [ABSTRACT FROM AUTHOR]

Chronic thromboembolic pulmonary hypertension (CTEPH) is confirmed by visual analysis of single-photon emission computer tomography (SPECT) ventilation and perfusion (V/Q) images. Defects in the perfusion image discordant with the ventilation image indicate obstructed segments and the positive diagnosis of CTEPH. A quantitative metric and classification algorithm are proposed based on volumetric data from SPECT V/Q images. The difference in ventilation and perfusion volumes (VV-P) is defined as a quantitative metric to identify discordant defects in the SPECT images. The algorithm was validated with 22 patients grouped according to their diagnosis: (1) CTEPH and (2) respiratory pathology. Volumetric data from SPECT perfusion images was also compared before and after treatment for CTEPH. CTEPH was detected with a sensitivity of 0.67 and specificity of 0.80. The performance of volumetric data from SPECT perfusion images for the evaluation of treatment response was studied for two cases and improvement of pulmonary perfusion was observed in one case. This study uses volumetric data from SPECT V/Q images for the diagnosis of CTEPH and its differentiation from respiratory pathologies. The results indicate that the defined metric is a viable option for a quantitative analysis of SPECT V/Q images. [ABSTRACT FROM AUTHOR]

Purpose: Computer-aided diagnosis (CAD) may improve interobserver agreement in the risk stratification of thyroid nodules. This study aims to evaluate the performance of the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) classification as estimated by an expert radiologist, a senior resident, a medical student, and a CAD system, as well as the interobserver agreement among them. Methods: Between July 2016 and 2018, 107 nodules (size 5–40 mm, 27 malignant) were classified according to the K-TIRADS by an expert radiologist and CAD software. A third-year resident and a medical student with basic imaging training, both blinded to previous findings, retrospectively estimated the K-TIRADS classification. The diagnostic performance was calculated, including sensitivity, specificity, positive and negative predictive values, and the area under the receiver operating characteristic curve. Results: The CAD system and the expert achieved a sensitivity of 70.37% (95% CI 49.82–86.25%) and 81.48% (61.92–93.7%) and a specificity of 87.50% (78.21–93.84%) and 88.75% (79.72–94.72%), respectively. The specificity of the student was significantly lower (76.25% [65.42–85.05%], p = 0.02). Conclusion: In our opinion, the CAD evaluation of thyroid nodules stratification risk has a potential role in a didactic field and does not play a real and effective role in the clinical field, where not only images but also specialistic medical practice is fundamental to achieve a diagnosis based on family history, genetics, lab tests, and so on. The CAD system may be useful for less experienced operators as its specificity was significantly higher. [ABSTRACT FROM AUTHOR]

High-resolution ultrasonography (US) is a valuable tool in breast imaging. Nevertheless, US is an operator-dependent technique: to overcome this issue, the American College of Radiology (ACR) has developed the breast imaging-reporting and data system (BI-RADS) US lexicon. Despite this effort, the variability in the assessment of focal breast lesions (FBLs) with the use of BI-RADS US lexicon is still an issue. Within this framework, evidence shows that computer-aided image analysis may be effective in improving the radiologist's assessment of FBLs. In particular, S-Detect is a newly developed image-analytic computer program that provides assistance in morphologic analysis of FBLs seen on US according to the BI-RADS US lexicon. This pictorial essay describes state-of-the-art of sonographic characterization of FBLs by using S-Detect. [ABSTRACT FROM AUTHOR]

The latest state of the art technological innovations have led to a palpable progression in endoscopic imaging and may facilitate standardisation of practice. One of the most rapidly evolving modalities is artificial intelligence with recent studies providing real‐time diagnoses and encouraging results in the first randomised trials to conventional endoscopic imaging. Advances in functional hypoxia imaging offer novel opportunities to be used to detect neoplasia and the assessment of colitis. Three‐dimensional volumetric imaging provides spatial information and has shown promise in the increased detection of small polyps. Studies to date of self‐propelling colonoscopes demonstrate an increased caecal intubation rate and possibly offer patients a more comfortable procedure. Further development in robotic technology has introduced ex vivo automated locomotor upper gastrointestinal and small bowel capsule devices. Eye‐tracking has the potential to revolutionise endoscopic training through the identification of differences in experts and non‐expert endoscopist as trainable parameters. In this review, we discuss the latest innovations of all these technologies and provide perspective into the exciting future of diagnostic luminal endoscopy. [ABSTRACT FROM AUTHOR]

Objective: A new computer tool is proposed to distinguish between focal nodular hyperplasia (FNH) and an inflammatory hepatocellular adenoma (I-HCA) using contrast-enhanced ultrasound (CEUS). The new method was compared with the usual qualitative analysis.Methods: The proposed tool embeds an "optical flow" algorithm, designed to mimic the human visual perception of object transport in image series, to quantitatively analyse apparent microbubble transport parameters visible on CEUS. Qualitative (visual) and quantitative (computer-assisted) CEUS data were compared in a cohort of adult patients with either FNH or I-HCA based on pathological and radiological results. For quantitative analysis, several computer-assisted classification models were tested and subjected to cross-validation. The accuracies, area under the receiver-operating characteristic curve (AUROC), sensitivity and specificity, positive predictive values (PPVs), negative predictive values (NPVs), false predictive rate (FPRs) and false negative rate (FNRs) were recorded.Results: Forty-six patients with FNH (n = 29) or I-HCA (n = 17) with 47 tumours (one patient with 2 I-HCA) were analysed. The qualitative diagnostic parameters were accuracy = 93.6%, AUROC = 0.94, sensitivity = 94.4%, specificity = 93.1%, PPV = 89.5%, NPV = 96.4%, FPR = 6.9% and FNR = 5.6%. The quantitative diagnostic parameters were accuracy = 95.9%, AUROC = 0.97, sensitivity = 93.4%, specificity = 97.6%, PPV = 95.3%, NPV = 96.7%, FPR = 2.4% and FNR = 6.6%.Conclusions: Microbubble transport patterns evident on CEUS are valuable diagnostic indicators. Machine-learning algorithms analysing such data facilitate the diagnosis of FNH and I-HCA tumours.Key Points: • Distinguishing between focal nodular hyperplasia and an inflammatory hepatocellular adenoma using dynamic contrast-enhanced ultrasound is sometimes difficult. • Microbubble transport patterns evident on contrast-enhanced sonography are valuable diagnostic indicators. • Machine-learning algorithms analysing microbubble transport patterns facilitate the diagnosis of FNH and I-HCA. [ABSTRACT FROM AUTHOR]

Background: Rosacea is one of the most common cutaneous disorder characterized primarily by facial flushing, erythema, papules, pustules, telangiectases, and nasal swelling. Diagnosis of rosacea is principally done by a physical examination and a consistent patient history. However, qualitative human assessment is often subjective and suffers from a relatively high intra‐ and inter‐observer variability in evaluating patient outcomes. Materials and Methods: To overcome these problems, we propose a quantitative and reproducible computer‐aided diagnosis system, Ros‐NET, which integrates information from different image scales and resolutions in order to identify rosacea lesions. This involves adaption of Inception‐ResNet‐v2 and ResNet‐101 to extract rosacea features from facial images. Additionally, we propose to refine the detection results by means of facial‐landmarks–based zones (ie, anthropometric landmarks) as regions of interest (ROI), which focus on typical areas of rosacea occurrence on a face. Results: Using a leave‐one‐patient‐out cross‐validation scheme, the weighted average Dice coefficients, in percentages, across all patients (N = 41) with 256 × 256 image patches are 89.8 ± 2.6% and 87.8 ± 2.4% with Inception‐ResNet‐v2 and ResNet‐101, respectively. Conclusion: The findings from this study support that pre‐trained networks trained via transfer learning can be beneficial in identifying rosacea lesions. Our future work will involve expanding the work to a larger database of cases with varying degrees of disease characteristics. [ABSTRACT FROM AUTHOR]

Congenital heart disease (CHD) is the major cause of morbidity/mortality in infancy and childhood. Using a mouse model to uncover the mechanism of CHD is essential to understand its pathogenesis. However, conventional 2D phenotyping methods cannot comprehensively exhibit and accurately distinguish various 3D cardiac malformations for the complicated structure of heart cavity. Here, a new automated tool based on microcomputed tomography (micro‐CT) image data sets known as computer‐assisted cardiac cavity tracking (CACCT) is presented, which can detect the connections between cardiac cavities and identify complicated cardiac malformations in mouse hearts automatically. With CACCT, researchers, even those without expert training or diagnostic experience of CHD, can identify complicated cardiac malformations in mice conveniently and precisely, including transposition of the great arteries, double‐outlet right ventricle and atypical ventricular septal defect, whose accuracy is equivalent to senior fetal cardiologists. CACCT provides an effective approach to accurately identify heterogeneous cardiac malformations, which will facilitate the mechanistic studies into CHD and heart development. [ABSTRACT FROM AUTHOR]

Featured Application: This paper focuses on improvement in patient care and it also helps practitioners optimize their dermatology services by means of computer-assisted diagnostic software using data from reflectance confocal microscopy devices. Reflectance confocal microscopy is an appropriate tool for the diagnosis of lentigo maligna. Compared with dermoscopy, this device can provide abundant information as a mosaic and/or a stack of images. In this particular context, the number of images per patient varied between 2 and 833 images and the objective, ultimately, is to be able to discern between benign and malignant classes. First, this paper evaluated classification at the image level, with the help of handcrafted methods derived from the literature and transfer learning methods. The transfer learning feature extraction methods outperformed the handcrafted feature extraction methods from literature, with a F 1 score value of 0.82. Secondly, this work proposed patient-level supervised methods based on image decisions and a comparison of these with multi-instance learning methods. This study achieved comparable results to those of the dermatologists, with an auc score of 0.87 for supervised patient diagnosis and an auc score of 0.88 for multi-instance learning patient diagnosis. According to these results, computer-aided diagnosis methods presented in this paper could be easily used in a clinical context to save time or confirm a diagnosis and can be oriented to detect images of interest. Also, this methodology can be used to serve future works based on multimodality. [ABSTRACT FROM AUTHOR]

Clinical evaluation of rheumatic and musculoskeletal diseases through images is a challenge for the beginner rheumatologist since image diagnosis is an expert task with a long learning curve. The aim of this work was to present a narrative review on the main ultrasound computer-aided diagnosis systems that may help clinicians thanks to the progress made in the application of artificial intelligence techniques. We performed a literature review searching for original articles in seven repositories, from 1970 to 2019, and identified 11 main methods currently used in ultrasound computer-aided diagnosis systems. Also, we found that rheumatoid arthritis, osteoarthritis, systemic lupus erythematosus, and idiopathic inflammatory myopathies are the four musculoskeletal and rheumatic diseases most studied that use these innovative systems, with an overall accuracy of > 75%. [ABSTRACT FROM AUTHOR]

Ultrasound bone segmentation is an important yet challenging task for many clinical applications. Several works have emerged attempting to improve and automate bone segmentation, which has led to a variety of computational techniques, validation practices and applied clinical scenarios. We characterize this exciting and growing body of research by reviewing published ultrasound bone segmentation techniques. We review 56 articles in detail and categorize and discuss the image analysis techniques that have been used for bone segmentation. We highlight the general trends of this field in terms of clinical motivation, image analysis techniques, ultrasound modalities and the types of validation practices used to quantify segmentation performance. Finally, we present an outlook on promising areas of research based on the unaddressed needs for solving ultrasound bone segmentation. [ABSTRACT FROM AUTHOR]

To evaluate the feasibility of integrating computer-aided diagnosis (CAD) with structured reports of prostate multiparametric MRI (mpMRI). This retrospective study enrolled 153 patients who underwent prostate mpMRI for the purpose of targeted biopsy; patients were divided into a group with clinically significant prostate cancer (csPCa, Gleason score ≥ 3 + 4, n = 89) and a group with non-csPCa (n = 64). Ten inexperienced radiologists retrospectively evaluated these cases (single reader per case) twice using structured reports, and they were blinded to the pathologic results. Initially, the readers interpreted mpMRI without CAD. Six weeks later, they evaluated the same cases again with CAD assistance. At each time of image interpretation, lesions detected by the readers were marked on the prostate vector map in structured reports, and a PI-RADS score was given to each lesion. Diagnostic efficacy and reading time were evaluated for the two reading sessions. With the assistance of CAD, the overall diagnostic efficacy was improved, i.e., the AUC increased from 0.83 to 0.89 (p = 0.018). Specifically, per-patient sensitivity (84.3% vs. 93.3%) and per-lesion sensitivity (76.7% vs. 88.8%) were significantly improved (all p < 0.05). Per-patient specificity with CAD (65.6%) was higher than that without CAD (56.3%), but statistical significance was not reached (p = 0.238). The reading time for each case decreased from 10.9 min to 7.8 min (p < 0.001). It is feasible to integrate CAD with structured reports of prostate mpMRI. This reading paradigm can improve the diagnostic sensitivity of csPCa detection and reduce reading time among inexperienced radiologists. • Concurrent CAD reading improves sensitivity of prostate tumors <1.5 cm. • CAD improves sensitivity of peripheral zone tumors, instead of transition zone. • Concurrent CAD reading can reduce reporting time of multiparametric MRI. [ABSTRACT FROM AUTHOR]

Objective: Content-based image retrieval (CBIR) is the most suitable and alternative method for older text searches that use keywords. This article aims to improve feature extraction as well as matching techniques designed for more accurate and precise CBIR systems, especially for brain scan images associated with various brain diseases and abnormalities. Tests should be described at an appropriate success rate. Methods: Various methods of producing medical images are discussed, and examples of biological applications are given. The discussion emphasizes as an introduction to CBIR the new method of echo-planar imaging, which is fully described. We have done here many methods related to digital image processing and we had developed a code for retrieving everything automatically. This application has been developed in Matlab software. Results: Testing the correctness and effectiveness of the system evolved becomes more important when the system is going to be used in real-time and more when it is for humankind, i.e., medical diagnosis. Nowadays, our science and technology areas as develop as we can say that we have such advanced medical equipment so that our thought and program can be capable that it is giving us useful results. Determining if whether the two images are identical or not, it depends on the point of view of the person. Conclusions: In this paper, the outcome of feature extraction and matching by setting cutoff limit and threshold is pretty promising. Further studies can be done apart from computed tomography scans for a more generalized CBIR system. [ABSTRACT FROM AUTHOR]

Study Question: Is it possible to develop an automated annotation tool for human embryo development in time-lapse devices based on image analysis?Summary Answer: We developed and validated an automated software for the annotation of human embryo morphokinetic parameters, having a good concordance with expert manual annotation on 701 time-lapse videos.What Is Known Already: Morphokinetic parameters obtained with time-lapse devices are increasingly used for the assessment of human embryo quality. However, their annotation is time-consuming and can be slightly operator-dependent, highlighting the need to develop fully automated approaches.Study Design, Size, Duration: This monocentric study was conducted on 701 videos originating from 584 couples undergoing IVF with embryo culture in a time-lapse device. The only selection criterion was that the duration of the video must be over 60 h.Participants/materials, Setting, Methods: An automated morphokinetic annotation tool was developed based on gray level coefficient of variation and detection of the thickness of the zona pellucida. The detection of cellular events obtained with the automated tool was compared with those obtained manually by trained experts in clinical settings.Main Results and the Role Of Chance: Although some differences were found when embryos were considered individually, we found an overall concordance between automated and manual annotation of human embryo morphokinetics from fertilization to expanded blastocyst stage (r2 = 0.92).Limitations, Reasons For Caution: These results should undergo multicentric external evaluation in order to test the overall performance of the annotation tool. Getting access to the export of 3D videos would enhance the quality of the correlation with the same algorithm and its extension to the 3D regions of interest. A technical limitation of our work lies within the duration of the video. The more embryo stages the video contains, the more information the script has to identify them correctly.Wider Implications Of the Findings: Our system paves the way for high-throughput analysis of multicentric morphokinetic databases, providing new insights into the clinical value of morphokinetics as a predictor of embryo quality and implantation.Study Funding/competing Interest(s): This study was partly funded by Finox-Gedeon Richter Forward Grant 2016 and NeXT (ANR-16-IDEX-0007). We have no conflict of interests to declare.Trial Registration Number: N/A. [ABSTRACT FROM AUTHOR]

Purpose: Pancreas segmentation from computed tomography (CT) images is an important step in surgical procedures such as cancer detection and radiation treatment. While manual segmentation is time-consuming and operator-dependent, current computer-assisted segmentation methods are facing challenges posed by varying shapes and sizes. To address these challenges, this paper presents a multi-scale feature fusion (MsFF) model for accurate pancreas segmentation from CT images. Methods: The proposed MsFF is built upon the well-recognized encoder–decoder framework. Firstly, in the encoder stage, the squeeze-and-excitation module is incorporated to enhance the learning of features by exploiting channel-wise independence. Secondly, a hierarchical fusion module is introduced to better utilize both low-level and high-level features to retain boundary information and make final predictions. Results: The proposed MsFF is evaluated on the NIH pancreas dataset and outperforms the current state-of-the-art methods, by achieving a mean of 87.26% and 22.67% under the Dice Sorensen Coefficient and Volumetric Overlap Error, respectively. Conclusion: The experimental results confirm that the incorporation of squeeze-and-excitation and hierarchical fusion modules contributes to a net gain in the performance of our proposed MsFF. [ABSTRACT FROM AUTHOR]

Objectives: To develop a radiomics model for predicting hematoma expansion in patients with intracerebral hemorrhage (ICH) and to compare its predictive performance with a conventional radiological feature-based model.Methods: We retrospectively analyzed 251 consecutive patients with acute ICH. Two radiologists independently assessed baseline noncontrast computed tomography (NCCT) images. For each radiologist, a radiological model was constructed from radiological variables; a radiomics score model was constructed from high-dimensional quantitative features extracted from NCCT images; and a combined model was constructed using both radiological variables and radiomics score. Development of models was constructed in a primary cohort (n = 177). We then validated the results in an independent validation cohort (n = 74). The primary outcome was hematoma expansion. We compared the three models for predicting hematoma expansion. Predictive performance was assessed with the receiver operating characteristic (ROC) curve analysis.Results: In the primary cohort, combined model and radiomics model showed greater AUCs than radiological model for both readers (all p < .05). In the validation cohort, combined model and radiomics model showed greater AUCs, sensitivities, and accuracies than radiological model for reader 2 (all p < .05). Combined model showed greater AUC than radiomics model for reader 1 only in the primary cohort (p = .03). Performance of three models was comparable between reader 1 and reader 2 in both cohorts (all p > .05).Conclusions: NCCT-based radiomics model showed high predictive performance and outperformed radiological model in the prediction of early hematoma expansion in ICH patients.Key Points: • Radiomics model showed better performance for prediction of hematoma expansion in patients with intracerebral hemorrhage than radiological feature-based model. • Hematomas which expanded in follow-up NCCT tended to be larger in baseline volume, more irregular in shape, more heterogeneous in composition, and coarser in texture. • A radiomics model provides a convenient and objective tool for prediction of hematoma expansion that helps to define subsets of patients who would benefit from anti-expansion therapy. [ABSTRACT FROM AUTHOR]

• A feature selection strategy which selects the optimal subset of features, by employing GSOA, from the original set is developed, in which the elimination of extraneous features takes place which enhances the classification performance and reduces the computational cost. This improves glaucoma detection while lowering model training computational costs and execution time. The performance is evaluated on the customized dataset of public and private images. • Further in this research, we discuss the application of machine learning in anticipating diseases,thus expanding the field of medical services and bringing in the most recent technology. It is demonstrated how to use the suggested technique, and a comprehensive analysis of different parameters is given. To determine the most effective presentation, various efficiency assessment criteria for many machine learning classifiers were implemented. The parameters included are accuracy, sensitivity,specificity, ROC curves and many more. • Through this study, we offer the best features(selected through soft-computing approach) to researchers, a reliable and effective system of support for medical professionals, and a software-based tool for the human race to slow down this infection spreading through early, quick, and accurate identification of this infection. It might be used in locations with a shortage of qualified medical workers like doctors and nurses. It can also be altered to work with wearable and portable medical devices. • For the detection of this infection from retinal fundus images, our proposed method outperforms existing techniques. This testing procedure will be advantageous for doctors and the state because it is significantly less expensive than other diagnostic instruments used by medical professionals to detect the disease. In addition, owing to its high performance, the proposed medical prediction system can be used to develop mobile applications that aid physicians in the early diagnosis of glaucoma. The process of feature selection (FS) is vital aspect of machine learning (ML) model's performance enhancement where the objective is the selection of the most influential subset of features. This paper suggests the Gravitational search optimization algorithm (GSOA) technique for metaheuristic-based FS. Glaucoma disease is selected as the subject of investigation as this disease is spreading worldwide at a very fast pace; 111 million instances of glaucoma are expected by 2040, up from 64 million in 2015. It causes widespread vision impairment. Optic nerve fibres can be degraded and cannot be replaced later in this disease. As a starting point, the retinal fundus images of glaucoma infected persons and healthy persons are used, and 36 features were retrieved from these images of public benchmark datasets and private dataset. Six ML models are trained for classification on the basis of the GSOA's returned subset of features. The suggested FS technique enhances classification performance with selection of most influential features. The eight statistical performance evaluating parameters along with execution time are calculated. The training and testing have been performed using a split approach (70:30), 5-fold cross validation (CV), as well as 10-fold CV. The suggested approach achieved 95.36 % accuracy. Due to its auspicious performance, doctors might use the suggested method to receive a second opinion, which would also help overburdened skilled medical practitioners and save patients from vision loss. [ABSTRACT FROM AUTHOR]

There are approximately 1.8 million diagnoses of colorectal cancer, 1 million diagnoses of stomach cancer, and 0.6 million diagnoses of esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect colorectal and esophagogastric cancer tissue in optical images would be hugely valuable to a surgeon during an intervention. Based on a colon dataset with 12 patients and an esophagogastric dataset of 10 patients, several state-of-the-art machine learning methods have been trained to detect cancer tissue using hyperspectral imaging (HSI), including Support Vector Machines (SVM) with radial basis function kernels, Multi-Layer Perceptrons (MLP) and 3D Convolutional Neural Networks (3DCNN). A leave-one-patient-out cross-validation (LOPOCV) with and without combining these sets was performed. The ROC-AUC score of the 3DCNN was slightly higher than the MLP and SVM with a difference of 0.04 AUC. The best performance was achieved with the 3DCNN for colon cancer and esophagogastric cancer detection with a high ROC-AUC of 0.93. The 3DCNN also achieved the best DICE scores of 0.49 and 0.41 on the colon and esophagogastric datasets, respectively. These scores were significantly improved using a patient-specific decision threshold to 0.58 and 0.51, respectively. This indicates that, in practical use, an HSI-based CAD system using an interactive decision threshold is likely to be valuable. Experiments were also performed to measure the benefits of combining the colorectal and esophagogastric datasets (22 patients), and this yielded significantly better results with the MLP and SVM models.

Digital pathology systems (DPSs) have been globally implemented, and computer-assisted diagnosis (CAD) software has been actively developed in recent years. This study aimed to investigate perceptions of digital pathology and the demand for CAD. An online survey involving members of the Korean Society of Pathologists was conducted, and a demonstration clip of the diagnostic assistant software for a prostate needle biopsy was shown to them to provide a simple experience with CAD. One hundred sixty-four Korean pathologists (13.6% of 1210 Korean pathologists) participated. The majority (77.4%) answered affirmatively regarding the necessity of implementing a DPS, and 26.8% had plans to implement or increase the use of DPSs in the following 2–3 years at their medical institutions. Pathologists felt that multidisciplinary care or conference accessibility (56.7%), remote consultation (49.4%), and big data building (32.9%) were useful parts of DPSs. Most pathologists (81.7%) responded that CAD software would assist with the diagnostic process. In a prostate needle biopsy, pathologists used the software to improve the measurement of tumor volume and/or length and core length but not to suggest a diagnostic name or Gleason grade. Korean pathologists who participated in the survey had highly positive perceptions of digital pathology and maintained a positive attitude toward the use of CAD software.

A clinical decision support system based on different methods of artificial intelligence (AI) can support the diagnosis of patients with unclear diseases by providing tentative diagnoses as well as proposals for further steps. In a user-centred-design process, we aim to find out how general practitioners envision the user interface of an AI-based clinical decision support system for primary care. A first user-interface prototype was developed using the task model based on user requirements from preliminary work. Five general practitioners evaluated the prototype in two workshops. The discussion of the prototype resulted in categorized suggestions with key messages for further development of the AI-based clinical decision support system, such as the integration of intelligent parameter requests. The early inclusion of different user feedback facilitated the implementation of a user interface for a user-friendly decision support system.

Purpose: To construct a deep learning knowledge distillation framework exploring the utilization of MRI alone or combing with distilled Arthroscopy information for meniscus tear detection. Methods: A database of 199 paired knee Arthroscopy-MRI exams was used to develop a multimodal teacher network and an MRI-based student network, which used residual neural networks architectures. A knowledge distillation framework comprising the multimodal teacher network T and the monomodal student network S was proposed. We optimized the loss functions of mean squared error (MSE) and cross-entropy (CE) to enable the student network S to learn arthroscopic information from the teacher network T through our deep learning knowledge distillation framework, ultimately resulting in a distilled student network S T . A coronal proton density (PD)-weighted fat-suppressed MRI sequence was used in this study. Fivefold cross-validation was employed, and the accuracy, sensitivity, specificity, F1-score, receiver operating characteristic (ROC) curves and area under the receiver operating characteristic curve (AUC) were used to evaluate the medial and lateral meniscal tears detection performance of the models, including the undistilled student model S , the distilled student model S T and the teacher model T . Results: The AUCs of the undistilled student model S , the distilled student model S T , the teacher model T for medial meniscus (MM) tear detection and lateral meniscus (LM) tear detection are 0.773/0.672, 0.792/0.751 and 0.834/0.746, respectively. The distilled student model S T had higher AUCs than the undistilled model S . After undergoing knowledge distillation processing, the distilled student model demonstrated promising results, with accuracy (0.764/0.734), sensitivity (0.838/0.661), and F1-score (0.680/0.754) for both medial and lateral tear detection better than the undistilled one with accuracy (0.734/0.648), sensitivity (0.733/0.607), and F1-score (0.620/0.673). Conclusion: Through the knowledge distillation framework, the student model S based on MRI benefited from the multimodal teacher model T and achieved an improved meniscus tear detection performance., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Ying, Wang, Yang, Wang and Liu.)

Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, the diagnostic performance of ultrasonography depends on the examiner's expertise. To support the ultrasonographic diagnosis, we developed YOLOv7-based deep learning models for metastatic LN detection on ultrasonography and compared their detection performance with that of highly experienced radiologists and less experienced residents. We enrolled 462 B- and D-mode ultrasound images of 261 metastatic and 279 non-metastatic histopathologically confirmed LNs from 126 patients with head and neck squamous cell carcinoma. The YOLOv7-based B- and D-mode models were optimized using B- and D-mode training and validation images and their detection performance for metastatic LNs was evaluated using B- and D-mode testing images, respectively. The D-mode model's performance was comparable to that of radiologists and superior to that of residents' reading of D-mode images, whereas the B-mode model's performance was higher than that of residents but lower than that of radiologists on B-mode images. Thus, YOLOv7-based B- and D-mode models can assist less experienced residents in ultrasonographic diagnoses. The D-mode model could raise the diagnostic performance of residents to the same level as experienced radiologists.

Computer-assisted polyp characterization (computer-aided diagnosis, CADx) facilitates optical diagnosis during colonoscopy. Several studies have demonstrated high sensitivity and specificity of CADx tools in identifying neoplastic changes in colorectal polyps. To implement CADx tools in colonoscopy, there is a need to confirm whether these tools satisfy the threshold levels that are required to introduce optical diagnosis strategies such as "diagnose-and-leave," "resect-and-discard" or "DISCARD-lite." In this article, we review the available data from prospective trials regarding the effect of multiple CADx tools and discuss whether they meet these thresholds.

Objective: To utilize hip MRI 3D models for demonstration of location and frequency of impingement during simulated range-of-motion in ischiofemoral impingement (IFI) compared to non-IFI hips., Materials and Methods: Sixteen hips (N = 7 IFI, 9 non-IFI) from 8 females were examined with high-resolution MRI. We performed image segmentation and generated 3D bone models and simulated hip range-of-motion and impingement. We examined the frequency and location of bone contact in early external rotation and early extension (0-20°), isolated maximum external rotation, and isolated maximum extension. Frequency and location of impingement at varied combinations of external rotation and extension and areas of simulated bone impingement at early external rotation and extension were compared between IFI and non-IFI., Results: Higher frequency of bony impingement occurred more often in IFI hips at each simulated range-of-motion combination (P < 0.05). Impingement involved the lesser trochanter more often in IFI hips (P < 0.001) and occurred at early degrees of external rotation and extension. In isolated maximum external rotation, only the greater trochanter, intertrochanteric area, or both combined were involved, in 14%, 57%, and 29% in IFI hips. In isolated maximum extension, the lesser trochanter, intertrochanteric area, or both combined were involved in 71%, 14%, and 14% in IFI hips. The simulated area of bone impingement was significantly higher in IFI hips (P = 0.02)., Conclusion: Hip MRI 3D models are feasible for simulated range-of-motion and show a higher frequency of extra-articular impingement at early stages of external rotation and extension in IFI compared to non-IFI hips., (© 2023. The Author(s), under exclusive licence to International Skeletal Society (ISS).)

Background: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too., Background: Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future., Methods: Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected., Results: The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field., Conclusions: The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.

BACKGROUND. Screening mammography has decreased performance in patients with dense breasts. Supplementary screening ultrasound is a recommended option in such patients, although it has yielded mixed results in prior investigations. OBJECTIVE. The purpose of this article is to compare the performance characteristics of screening mammography alone, standalone artificial intelligence (AI), ultrasound alone, and mammography in combination with AI and/or ultrasound in patients with dense breasts. METHODS. This retrospective study included 1325 women (mean age, 53 years) with dense breasts who underwent both screening mammography and supplementary breast ultrasound within a 1-month interval from January 2017 to December 2017; prior mammography and prior ultrasound examinations were available for comparison in 91.2% and 91.8%, respectively. Mammography and ultrasound examinations were interpreted by one of 15 radiologists (five staff; 10 fellows); clinical reports were used for the present analysis. A commercial AI tool was used to retrospectively evaluate mammographic examinations for presence of cancer. Screening performances were compared among mammography, AI, ultrasound, and test combinations, using generalized estimating equations. Benign diagnoses required 24 months or longer of imaging stability. RESULTS. Twelve cancers (six invasive ductal carcinoma; six ductal carcinoma in situ) were diagnosed. Mammography, standalone AI, and ultrasound showed cancer detection rates (per 1000 patients) of 6.0, 6.8, and 6.0 (all p > .05); recall rates of 4.4%, 11.9%, and 9.2% (all p < .05); sensitivity of 66.7%, 75.0%, and 66.7% (all p > .05); specificity of 96.2%, 88.7%, and 91.3% (all p < .05); and accuracy of 95.9%, 88.5%, and 91.1% (all p < .05). Mammography with AI, mammography with ultrasound, and mammography with both ultrasound and AI showed cancer detection rates of 7.5, 9.1, and 9.1 (all p > .05); recall rates of 14.9, 11.7, and 21.4 (all p < .05); sensitivity of 83.3%, 100.0%, and 100.0% (all p > .05); specificity of 85.8%, 89.1%, and 79.4% (all p < .05); and accuracy of 85.7%, 89.2%, and 79.5% (all p < .05). CONCLUSION. Mammography with supplementary ultrasound showed higher accuracy, higher specificity, and lower recall rate in comparison with mammography with AI and in comparison with mammography with both ultrasound and AI. CLINICAL IMPACT. The findings fail to show benefit of AI with respect to screening mammography performed with supplementary breast ultrasound in patients with dense breasts.

Background: The Lyon consensus classifies the evidence of gastroesophageal reflux (GERD) based on endoscopic features and results of pH/impedance monitoring (pH-MII) including the post-reflux swallow-induced peristaltic wave index (PSPWI) and mean nocturnal baseline impedance (MNBI). The Wingate consensus established criteria to reduce inter-reviewer variability when assessing reflux episodes and PSPWI by impedance. This study aims to assess the influence of the Wingate criteria on the different pH-MII parameters obtained by automated analysis., Methods: Thirty consecutive pH-MII off PPI were reviewed according to Wingate criteria. Number of impedance episodes and PSPWI were compared before and after censoring from automatic analysis. Reflux categorization according to Lyon consensus between censored and uncensored data was compared. Pearson correlations between impedance parameters and censored episodes were calculated., Key Results: Censoring the tracings significantly reduced the number of reflux episodes (66 [42-90.25] vs. 44.5 [21.5-61.5], p = 0.0105). Reasons for censoring were as follows: 1/ anterograde episode: 9.5 [6-13], 2/ impedance drop <50%: 1 [0-3], 3/ duration <4 s: 1 [0-2], 4/ <2 distal channels: 2.5 [1-4], and 5/ artifacts: 2 [1-5]. Censored episodes were in majority non-acid (16.5 [13-26.5] vs. 2 [0-4], p < 0.00001). Censoring altered the categorization of impedance episodes (<40 episodes, 6 vs. 13 for resp. uncensored vs. censored tracings, 40-80 episodes: 13 vs. 13, and >80 episodes: 11 vs. 4, p = 0.0264), but not the symptom index, the symptom association probability, or the categorization according to the Lyon consensus. Nevertheless, individual tracings were affected. The percentage of censored episodes was inversely correlated with the number of acidic impedance episodes (r = -0.62, p = 0.0002)., Conclusion and Inferences: Manual interpretation of impedance tracings based on the Wingate consensus reduces the number of impedance episodes, impacting on reflux categorization. Acidic reflux episodes are less likely to be censored, harboring a potential at improving automatic pH-MII analysis., (© 2023 John Wiley & Sons Ltd.)

Purpose: The purpose of this study was to develop artificial intelligence algorithms that can distinguish between orbital and conjunctival mucosa-associated lymphoid tissue (MALT) lymphomas in pathological images., Methods: Tissue blocks with residual MALT lymphoma and data from histological and flow cytometric studies and molecular genetic analyses such as gene rearrangement were procured for 129 patients treated between April 2008 and April 2020. We collected pathological hematoxylin and eosin-stained (HE) images of lymphoma from these patients and cropped 10 different image patches at a resolution of 2048 × 2048 from pathological images from each patient. A total of 990 images from 99 patients were used to create and evaluate machine-learning models. Each image patch of three different magnification rates at ×4, ×20, and ×40 underwent texture analysis to extract features, and then seven different machine-learning algorithms were applied to the results to create models. Cross-validation on a patient-by-patient basis was used to create and evaluate models, and then 300 images from the remaining 30 cases were used to evaluate the average accuracy rate., Results: Ten-fold cross-validation using the support vector machine with linear kernel algorithm was identified as the best algorithm for discriminating between conjunctival mucosa-associated lymphoid tissue and orbital MALT lymphomas, with an average accuracy rate under cross-validation of 85%. There were ×20 magnification HE images that were more accurate in distinguishing orbital and conjunctival MALT lymphomas among ×4, ×20, and ×40., Conclusion: Artificial intelligence algorithms can successfully distinguish HE images between orbital and conjunctival MALT lymphomas.

Purpose: This study aimed to investigate whether the accuracy of intraoral scanners is influenced by different scanning strategies in an in vitro setting, through a systematic review and meta-analysis., Materials and Methods: This review was conducted in accordance with the PRISMA 2020 standard. The following PICOS approach was used: population, tooth impressions; intervention, the use of intraoral scanners with scanning strategies different from the manufacturer's instructions; control, the use of intraoral scanners following the manufacturers' requirements; outcome, accuracy of intraoral scanners; type of studies, in vitro . A comprehensive literature search was conducted across various databases including Embase, SciELO, PubMed, Scopus, and Web of Science. The inclusion criteria were based on in vitro studies that reported the accuracy of digital impressions using intraoral scanners. Analysis was performed using Review Manager software (version 5.3.5; Cochrane Collaboration, Copenhagen, Denmark). Global comparisons were made using a standardized mean difference based on random-effect models, with a significance level of α = 0.05., Results: The meta-analysis included 15 articles. Digital impression accuracy significantly improved under dry conditions ( P < 0.001). Moreover, trueness and precision were enhanced when artificial landmarks were used ( P ≤ 0.02) and when an S-shaped pattern was followed ( P ≤ 0.01). However, the type of light used did not have a significant impact on the accuracy of the digital intraoral scanners ( P ≥ 0.16)., Conclusion: The accuracy of digital intraoral scanners can be enhanced by employing scanning processes using artificial landmarks and digital impressions under dry conditions., (© 2023 The Korean Academy of Prosthodontics.)

The spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is a time-consuming and repetitive process. In this study, we propose an automated spleen injury detection method using machine learning. CT scans from patients experiencing traumatic injuries were collected from Michigan Medicine and the Crash Injury Research Engineering Network (CIREN) dataset. Ninety-nine scans of healthy and lacerated spleens were split into disjoint training and test sets, with random forest (RF), naive Bayes, SVM, k-nearest neighbors (k-NN) ensemble, and subspace discriminant ensemble models trained via 5-fold cross validation. Of these models, random forest performed the best, achieving an Area Under the receiver operating characteristic Curve (AUC) of 0.91 and an F1 score of 0.80 on the test set. These results suggest that an automated, quantitative assessment of traumatic spleen injury has the potential to enable faster triage and improve patient outcomes.

Objectives: This study was conducted in order to evaluate a novel risk stratification model using dual-energy CT (DECT) texture analysis of head and neck squamous cell carcinoma (HNSCC) with machine learning to (1) predict associated cervical lymphadenopathy and (2) compare the accuracy of spectral versus single-energy (65 keV) texture evaluation for endpoint prediction.Methods: Eighty-seven patients with HNSCC were evaluated. Texture feature extraction was performed on virtual monochromatic images (VMIs) at 65 keV alone or different sets of multi-energy VMIs ranging from 40 to 140 keV, in addition to iodine material decomposition maps and other clinical information. Random forests (RF) models were constructed for outcome prediction with internal cross-validation in addition to the use of separate randomly selected training (70%) and testing (30%) sets. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were determined for predicting positive versus negative nodal status in the neck.Results: Depending on the model used and subset of patients evaluated, an accuracy, sensitivity, specificity, PPV, and NPV of up to 88, 100, 67, 83, and 100%, respectively, could be achieved using multi-energy texture analysis. Texture evaluation of VMIs at 65 keV alone or in combination with only iodine maps had a much lower accuracy.Conclusions: Multi-energy DECT texture analysis of HNSCC is superior to texture analysis of 65 keV VMIs and iodine maps alone and can be used to predict cervical nodal metastases with relatively high accuracy, providing information not currently available by expert evaluation of the primary tumor alone.Key Points: • Texture features of HNSCC tumor are predictive of nodal status. • Multi-energy texture analysis is superior to analysis of datasets at a single energy. • Dual-energy CT texture analysis with machine learning can enhance noninvasive diagnostic tumor evaluation. [ABSTRACT FROM AUTHOR]

Background: Idiopathic normal pressure hydrocephalus (iNPH) patients often develop Alzheimer's disease (AD) related brain pathology. Disease State Index (DSI) is a method to combine data from various sources for differential diagnosis and progression of neurodegenerative disorders.Objective: To apply DSI to predict clinical AD in shunted iNPH-patients in a defined population.Methods: 335 shunted iNPH-patients (median 74 years) were followed until death (n = 185) or 6/2015 (n = 150). DSI model (including symptom profile, onset age of NPH symptoms, atrophy of medial temporal lobe in CT/MRI, cortical brain biopsy finding, and APOE genotype) was applied. Performance of DSI model was evaluated with receiver operating characteristic (ROC) curve analysis.Results: A total of 70 (21%) patients developed clinical AD during median follow-up of 5.3 years. DSI-model predicted clinical AD with moderate effectiveness (AUC = 0.75). Significant factors were cortical biopsy (0.69), clinical symptoms (0.66), and medial temporal lobe atrophy (0.66).Conclusion: We found increased occurrence of clinical AD in previously shunted iNPH patients as compared with general population. DSI supported the prediction of AD. Cortical biopsy during shunt insertion seems indicated for earlier diagnosis of comorbid AD. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the common type of cancer in females across the world. An early detection and diagnosis of breast cancer may reduce the mortality rate to a great extent. To diagnose breast cancer, different types of imaging modalities are used to collect samples like mammography, Computerized Tomography, Magnetic Resonance Imaging, Ultrasound and Biopsy. Histopathological images obtained from biopsy may influence how and at which stage the cancer is being diagnosed. The Computer Assisted Diagnosis (CAD) system helps the pathologists in early diagnosis of breast cancer. In this survey, the recently reported techniques for breast cancer diagnosis using histopathological images have been summarized. This study could be beneficial for: (i) Clinicians to receive second opinion from the CAD system for early diagnosis, and (ii) Researchers to analyze and enhance the existing state-of-art techniques used in CAD system, which may further reduce the gap of variability between intra and inter observer. • Review of state-of-art computer assisted diagnosis (CAD) system for breast cancer. • Explicit categorization and remarks of techniques reported over the past 10 years. • Major recent trend analysis for segmentation and classification phase. • Provides current status and future scope of CAD system in histopathology images. • Useful for clinicians to get second opinion from CAD system for early diagnosis. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the ability of MRI radiomics to categorize ovarian masses and to determine the association between MRI radiomics and survival among ovarian epithelial cancer (OEC) patients.Method: A total of 286 patients with pathologically proven adnexal tumor were retrospectively included in this study. We evaluated diagnostic performance of the signatures derived from MRI radiomics in differentiating (1) between benign adnexal tumors and malignancies and (2) between type I and type II OEC. The least absolute shrinkage and selection operator method was used for radiomics feature selection. Risk scores were calculated from the Lasso model and were used for survival analysis.Result: For the classification between benign and malignant masses, the MRI radiomics model achieved a high accuracy of 0.90 in the leave-one-out (LOO) cross-validation cohort and an accuracy of 0.87 in the independent validation cohort. For the classification between type I and type II subtypes, our method made a satisfactory classification in the LOO cross-validation cohort (accuracy = 0.93) and in the independent validation cohort (accuracy = 0.84). Low-high-high short-run high gray-level emphasis and low-low-high variance from coronal T2-weighted imaging (T2WI) and eccentricity from axial T1-weighted imaging (T1WI) images had the best performance in two classification tasks. The patients with higher risk scores were more likely to have poor prognosis (hazard ratio = 4.1694, p = 0.001).Conclusion: Our results suggest radiomics features extracted from MRI are highly correlated with OEC classification and prognosis of patients. MRI radiomics can provide survival estimations with high accuracy.Key Points: • The MRI radiomics model could achieve a higher accuracy in discriminating benign ovarian diseases from malignancies. • Low-high-high short-run high gray-level emphasis, low-low-high variance from coronal T2WI, and eccentricity from axial T1WI had the best performance outcomes in various classification tasks. • The ovarian cancer patients with high-risk scores had poor prognosis. [ABSTRACT FROM AUTHOR]

The diagnostic imaging techniques currently used to evaluate the arterial atherosclerosis hinge on the manual marking and calculation of the stenosis degree. However, the manual assessment is highly dependent on the operator and characterized by low replicability. The study aimed to develop a fully-automated tool for the segmentation and analysis of atherosclerosis in the extracranial carotid arteries. The dataset consisted of 59 randomly-chosen individuals who had undergone head-and-neck computed tomography angiography (CTA), at the Tampere University Hospital, Tampere, Finland. The analysis algorithm was mainly based on the detection of carotid arteries, delineation of the vascular wall, and extraction of the atherosclerotic plaque. To improve the vascular detection rate, the model-based and volume-wide analytical approaches were deployed. A new fully-automated vascular imaging (VASIM) software tool was developed. For stenosis over 50%, the success rate was 83% for the detection and segmentation. Specificity and sensitivity of the algorithm were 25% and 83%, respectively. The overall accuracy was 71%. The VASIM tool is the first published approach for the fully-automated analysis of atherosclerosis in extracranial carotid arteries. The tool provides new outputs, which may help with the quantitative and qualitative, clinical evaluation of the atherosclerosis burden and evolution. The findings from this study provide a basis for the further development of automated atherosclerosis diagnosis and plaque analysis with CTA. [ABSTRACT FROM AUTHOR]

Objectives: To compare the diagnostic performance and interpretation time of digital breast tomosynthesis (DBT) for both novice and experienced readers with and without using a computer-aided detection (CAD) system for concurrent read.Methods: CAD system was developed for concurrent read in DBT interpretation. In this observer performance study, we used an enriched sample of 100 DBT cases including 70 with and 30 without breast cancers. Image interpretation was performed by four radiologists with different experience levels (two experienced and two novice). Each reader completed two reading sessions (at a minimum 2-month interval), once with and once without CAD. Three different rating scales were used to record each reader's interpretation. Reader performance with and without CAD was reported and compared for each radiologist. Reading time for each case was also recorded.Results: Average area under the receiver operating characteristic curve values for BI-RADS scale on using CAD were 0.778 and 0.776 without using CAD, demonstrating no statistically significant differences. Results were consistent when the probability of malignancy and percentage probability of malignancy scales were used. Reading times per case were 72.07 s and 62.03 s (SD, 37.54 s vs 34.38 s) without and with CAD, respectively. The average difference in reading time on using CAD was a statistically significant decrease of 10.04 ± 1.85 s, providing 14% decrease in time. The time-reducing effect was consistently observed in both novice and experienced readers.Conclusion: DBT combined with CAD reduced interpretation time without diagnostic performance loss to novice and experienced readers.Key Points: • The use of a concurrent DBT-CAD system shortened interpretation time. • The shortened interpretation time with DBT-CAD did not come at a cost to diagnostic performance to novice or experienced readers. • The concurrent DBT-CAD system improved the efficiency of DBT interpretation. [ABSTRACT FROM AUTHOR]

Background: The growth rate of thymic epithelial tumors (TETs) and thymic cysts was investigated to determine whether they can be differentiated and clinico‐radiological predictors of interval growth was identified. Methods: This retrospective study included 122 patients with pathologically proven thymic cysts (n = 56) or TETs (n = 66) who underwent two serial chest computed tomography scans at least eight weeks apart. Average diameters and attenuation were measured, volume‐doubling times (VDTs) were calculated, and clinical characteristics were recorded. VDTs were compared using the log‐rank test. Predictors of growth were analyzed using the log‐rank test and Cox regression analysis. Results: The frequency of growth did not differ significantly between TETs and thymic cysts (P = 0.279). The VDT of thymic cysts (median 324 days) was not significantly different from that of the TETs (median 475 days; P = 0.808). Water attenuation (≤ 20 Hounsfield units) predicted growth in thymic cysts (P = 0.016; hazard ratio 13.2, 95% confidence interval 1.6–107.3), while lesion size (> 17.2 mm) predicted growth in TETs (P = 0.008 for size, P = 0.029 for size*time). For the growing lesions, the positive and negative predictive values of water attenuation for thymic cysts were 93% and 80%, respectively. Conclusion: The frequencies of interval growth and VDTs were indistinguishable between TETs and thymic cysts. Water attenuation and lesion size predicted growth in thymic cysts and TETs, respectively. Among the growing lesions, water attenuation was a differential feature of thymic cysts. [ABSTRACT FROM AUTHOR]

Purpose: To determine the agreement between the manual scoring of home sleep apnea tests (HSATs) by international sleep technologists and automated scoring systems.Methods: Fifteen HSATs, previously recorded using a type 3 monitor, were saved in European Data Format. The studies were scored by nine experienced technologists from the sleep centers of the Sleep Apnea Global Interdisciplinary Consortium (SAGIC) using the locally available software. Each study was scored separately by human scorers using the nasal pressure (NP), flow derived from the NP signal (transformed NP), or respiratory inductive plethysmography (RIP) flow. The same procedure was followed using two automated scoring systems: Remlogic (RLG) and Noxturnal (NOX).Results: The intra-class correlation coefficients (ICCs) of the apnea-hypopnea index (AHI) scoring using the NP, transformed NP, and RIP flow were 0.96 [95% CI 0.93-0.99], 0.98 [0.96-0.99], and 0.97 [0.95-0.99], respectively. Using the NP signal, the mean differences in AHI between the average of the manual scoring and the automated systems were − 0.9 ± 3.1/h (AHIRLG vs AHIMANUAL) and − 1.3 ± 2.6/h (AHINOX vs AHIMANUAL). Using the transformed NP, the mean differences in AHI were − 1.9 ± 3.3/h (AHIRLG vs AHIMANUAL) and 1.6 ± 3.0/h (AHINOX vs AHIMANUAL). Using the RIP flow, the mean differences in AHI were − 2.7 ± 4.5/h (AHIRLG vs AHIMANUAL) and 2.3 ± 3.4/h (AHINOX vs AHIMANUAL).Conclusions: There is very strong agreement in the scoring of the AHI for HSATs between the automated systems and experienced international technologists. Automated scoring of HSATs using commercially available software may be useful to standardize scoring in future endeavors involving international sleep centers. [ABSTRACT FROM AUTHOR]

Copyright of CT Theory & Applications is the property of Editorial Department of CT Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To continue to provide expert specialized care during the COVID‐19 pandemic, our dermatopathology service transitioned to a secure virtual microscopy platform. In our experience, this digitally‐enabled dermatopathology practice revealed myriad benefits, including an improved diagnostic workflow and increased access to teaching. Whole slide imaging (WSI) is a related system that digitizes glass slides with high resolution and has been clinically validated for primary diagnosis. While WSI requires an initial institutional investment, its benefits include expanded access to subspecialized expertise and collaborations, digital histopathologic data generation for research, unification of patient clinical and pathologic information, and archiving of educational resources. The switch to digitally‐enabled remote dermatopathology at our institution and across the United States presents a rare opportunity to critically examine newly implemented systems and to develop permanent digital solutions, thereby taking a leap forward for the benefit of patient care, research, and medical education. [ABSTRACT FROM AUTHOR]

Colonoscopy is considered the gold standard for colorectal cancer diagnosis and prognosis. However, existing methods are less accurate and prone to overlooking lesions during gastrointestinal endoscopic examinations. Computer-assisted diagnosis combined with robot-assisted minimally invasive surgery (RMIS) can significantly help medical practitioners detect and treat lesions. Therefore, two novel architectures are developed for polyp and surgical instrument segmentation to aid colorectal cancer diagnosis, assessment, and treatment. Colorectal cancer segmentation network (CCS-Net) is the base network used in this study. It uses the maximum convolutional layers near the input image for effective feature extraction from low-level information. In addition, CCS-Net uses an efficient feature upsampling unit to efficiently increase the input spatial features' map size. Hence, CCS-Net is capable of providing a fair performance with satisfactory computational efficiency The multi-scale feature retention and aggregation network (MFRA-Net) is the final network in this study. MFRA-Net is developed to improve the segmentation accuracy of the CCS-Net further as it uses multi-scale feature retention to retain low-level spatial features and transfers them to deep stages of the network. MFRA-Net also combines multi-scale high-strided low-level information with high-level information to boost network segmentation performance. Finally, all the transferred multi-scale features from the early stages of the network are aggregated with high-level features in the deep levels of the network. This multi-scale feature retention and aggregation mechanism enables the network to maintain a better segmentation performance compared with other methods even with challenging blur, specular reflection, low contrast, and high variation cases. We evaluated both architectures on four challenging datasets: Kvasir-SEG, CVC-ClinicDB, Kvasir-Instrument, and the UW-Sinus-Surgery-Live dataset. The proposed method achieves dice similarity coefficients of 95.98%, 94.19%, 92.81%, and 88.57% for the CVC-ClinicDB, Kvasir-SEG, Kvasir-Instrument, and UW-Sinus-Surgery-Live datasets. The proposed method achieves superior segmentation performance compared with state-of-the-art methods and requires only 4.9 million trainable parameters for complete training. Therefore, the proposed networks can effectively assist health professionals in surgical procedures and colorectal cancer diagnosis through surgical instruments and polyp segmentation, respectively. • We proposed two models for diagnostic and surgical assistance of colorectal cancer. • CCS-Net is a base model using large number of convolution layers near input image. • MFRA-Net is a final network using multi-scale feature retention and aggregation. • MFRA-Net outperforms the state-of-the-art methods using only 4.9 million parameters. [ABSTRACT FROM AUTHOR]

ObjectivesThis work was a comparative study that aimed to find a proper method for accurately segmenting persistent ground glass nodules (GGN) in thin-section computed tomography (CT) images after detecting them.MethodsTo do this, we first applied five types of semi-automatic segmentation methods (i.e., level-set-based active contour model, localized region-based active contour model, seeded region growing, K-means clustering, and fuzzy C-means clustering) to preprocessed GGN images, respectively. Then, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by two radiologists.ResultsComparison experiments were performed using 40 persistent GGNs. In our experiment, the mean Dice coefficient for each semiautomatic segmentation tool with manually segmented area was 0.808 for the level-set-based active contour model, 0.8001 for the localized region-based active contour model, 0.629 for seeded region growing, 0.7953 for K-means clustering, and 0.7999 for fuzzy C-means clustering, respectively.ConclusionsThe level-set-based active contour model algorithm showed the best performance, which was most similar to the result of manual segmentation by two radiologists. From the differentiation between the normal parenchyma and the nodule, it was also the most efficient. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for more accurate early diagnosis and prognosis of lung cancer in thin-section CT images.

ObjectivesWe propose an automatic breast mass detection algorithm in three-dimensional (3D) ultrasound (US) images using the Hough transform technique.MethodsOne hundred twenty-five cropped images containing 68 benign and 60 malignant masses are acquired with clinical diagnosis by an experienced radiologist. The 3D US images are masked, subsampled, contrast-adjusted, and median-filtered as preprocessing steps before the Hough transform is used. Thereafter, we perform 3D Hough transform to detect spherical hyperplanes in 3D US breast image volumes, generate Hough spheres, and sort them in the order of votes. In order to reduce the number of the false positives in the breast mass detection algorithm, the Hough sphere with a mean or grey level value of the centroid higher than the mean of the 3D US image is excluded, and the remaining Hough sphere is converted into a circumscribing parallelepiped cube as breast mass lesion candidates. Finally, we examine whether or not the generated Hough cubes were overlapping each other geometrically, and the resulting Hough cubes are suggested as detected breast mass candidates.ResultsAn automatic breast mass detection algorithm is applied with mass detection sensitivity of 96.1% at 0.84 false positives per case, quite comparable to the results in previous research, and we note that in the case of malignant breast mass detection, every malignant mass is detected with false positives per case at a rate of 0.62.ConclusionsThe breast mass detection efficiency of our algorithm is assessed by performing a ROC analysis.