Search

Background: In recent years, breast reconstruction using autologous tissue after breast cancer surgery has become a common procedure. This study investigated the association between the occurrence of complications in breast reconstruction using deep inferior epigastric perforator (DIEP) flaps and patient risk factors among Asian women. Methods: This study included cases of breast reconstruction using DIEP flaps performed at our institution. We retrospectively investigated the relationship between preoperative and operative patient factors and postoperative complications by collecting data from medical records. Sarcopenia was also evaluated by calculating psoas muscle index from the area of the iliopsoas muscle at the level of the third lumbar vertebra using images from preoperative computed tomography. Postoperative complications were compared between a low-body mass index (BMI) group and a high-BMI group, defined using BMI values of

Ultrasound-guided, lymph node, fine-needle aspiration cytology is important in diagnosing axillary lymph node metastasis in breast cancer. However, poor needle visibility can render the procedure difficult. We describe a case in which state-of-the-art enhancement techniques using matrix linear probes can provide better needle visibility and improve the certainty and efficiency of the examination.

BACKGROUND Adenomyoepithelioma (AME) of the breast is a rare type of benign breast tumor. Many AMEs show benign behavior, but reports of the malignant type are rare. We present the case of a patient with AME with repeated local recurrences and further malignant transformation. CASE SUMMARY A 53-year-old woman visited our hospital with a 16-mm palpable mass in the right breast. A core needle biopsy was performed. The pathological diagnosis was AME. Lumpectomy with a safety margin was performed without axillary lymph node dissection (ALND). Two years later, local recurrence developed, and the patient again underwent lumpectomy with a safety margin. The pathology showed malignant AME, and the margin was negative. Eight months later, local recurrence developed again in the same location, and a total mastectomy was performed without ALND. The pathological diagnosis was malignant AME. The patient was disease-free for three years posttreatment. CONCLUSION The treatment of AME requires caution, as it may exhibit repeated recurrences after local excision as well as malignant transformation.

We aimed to evaluate the usefulness of a fast protocol of diffusion-weighted imaging (DWI) with one excitation using 3T magnetic resonance imaging (MRI) and a 16-channel breast coil. We analyzed 30 lesions from 27 women between February 2020 and June 2020. The visibility score (from 1 = extremely poor to 5 = excellent) and apparent diffusion coefficient (ADC) value between one and four excitations were evaluated by two readers. The image acquisition time was 40 s for one excitation and 1 min 52 s for four excitations. The visibility scores were 4.630 ± 0.718 and 4.267 ± 1.015 for one excitation and 4.730 ± 0.691 and 4.200 ± 1.000 for four excitations by the two readers. There was no significant difference in the visibility (P = 0.184 and P = 0.423), mean ADC value (P = 0.918 and P = 0.417), and minimum ADC value (P = 0.936 and P = 0.443) between one and four excitations by the two readers. Despite the short acquisition time, the visibility score and ADC values of one-excitation DWI were comparable to that with four excitations. Our fast DWI protocol could provide reproducible visibility and ADC value, potentially helping radiologists to efficiently diagnose patients.

The trachea is a sporadic origin of paraganglioma. The purpose of the present study was to identify the features of tracheal paraganglioma and reveal the effectiveness of computed tomography (CT) and magnetic resonance imaging (MRI) by reviewing both previous and current cases. In cases of tracheal tumors, we need to consider the bleeding risk associated with a biopsy, as the tumor may be paraganglioma, which is hypervascular. If a biopsy is not available, then CT and MRI can aid in making a pre-operative diagnosis. MRI in particular is useful for long-term observations.

Background: Sarcopenia is associated with postoperative complications in patients undergoing digestive surgery. In this study, we investigated the impact of preoperative sarcopenia on postoperative complications in breast cancer patients who underwent total mastectomy. Methods: Patients with breast cancer who underwent total mastectomy were included in the analysis. The relationship between the presence of sarcopenia and postoperative complications (e.g., skin flap necrosis and seroma) and between the incidence of these complications as well as preoperative and surgical factors was investigated. Moreover, the effects of sarcopenia on recurrence-free survival and overall survival were evaluated. The psoas muscle index calculated using values measured on preoperative computed tomography images was used to diagnose sarcopenia. Results: In total, 43 (49%) of 88 patients presented with sarcopenia. The number of patients with a Geriatric Nutritional Risk Index score

Introduction This study examined the possible associations between frailty and patient‐reported outcomes (PROs) in elderly patients with asthma. Methods Participants completed the Kihon Checklist for frailty screening as well as the following tools for measuring generic‐ and disease‐specific health‐related quality of life (HRQOL) and asthma control; the Medical Outcomes Study 36‐item short form (SF‐36), the Hyland Scale (global scale), the Asthma Quality of Life Questionnaire (AQLQ), the Asthma Control Test (ACT), and the Asthma Control Questionnaire (ACQ). Results Of 69 consecutive outpatients with asthma, 38 (55.1%), 21 (30.4%), and 10 (14.5%) were classified as robust, pre‐frail, and frail, respectively. Eight out of 52 patients with asthma in the elderly (AIE) (>65 years old) (15.4%) were considered as being frail. The Kihon Checklist total score was significantly correlated with all the scores obtained from the SF‐36, Hyland Scale, AQLQ, ACT, and ACQ. All these scores were significantly different between groups with and without frailty. From the viewpoint of correlation coefficient, SF‐36 Physical Functioning correlated most strongly with a coefficient of −0.68 (P < .01), and the Hyland Scale score was second (RS = −0.46, P < .01). The correlations between the Kihon Checklist total score and lung function parameters were weak or negative (|RS| < 0.35). Discussion There were significant associations between frailty and PROs, particularly generic perception of HRQOL. Since the Kihon Checklist and PROs such as the HRQOL overlap somewhat in their evaluation of the patients’ condition, there might be some similarities in the conceptual frameworks of frailty and quality of life.

Objectives We sought to generate realistic synthetic breast ultrasound images and express virtual interpolation images of tumors using a deep convolutional generative adversarial network (DCGAN). Methods After retrospective selection of breast ultrasound images of 528 benign masses, 529 malignant masses, and 583 normal breasts, 20 synthesized images of each were generated by the DCGAN. Fifteen virtual interpolation images of tumors were generated by changing the value of the input vector. A total of 60 synthesized images and 20 virtual interpolation images were evaluated by 2 readers, who scored them on a 5-point scale (1, very good; to 5, very poor) and then answered whether the synthesized image was benign, malignant, or normal. Results The mean score of overall quality for synthesized images was 3.05, and that of the reality of virtual interpolation images was 2.53. The readers classified the generated images with a correct answer rate of 92.5%. Conclusions A DCGAN can generate high-quality synthetic breast ultrasound images of each pathologic tissue and has the potential to create realistic virtual interpolation images of tumor development.

Although there have been many published reports on fatigue and pain in patients with chronic obstructive pulmonary disease (COPD), it is considered that these symptoms are seldom, if ever, asked about during consultations in Japanese clinical practice. To bridge this gap between the literature and daily clinical experience, the authors attempted to gain a better understanding of fatigue and pain in Japanese subjects with COPD. The Brief Fatigue Inventory (BFI) to analyse and quantify the degree of fatigue, the revised Short–Form McGill Pain Questionnaire 2 (SF-MPQ-2) for measuring pain and the Kihon Checklist to judge whether a participant is frail and elderly were administered to 89 subjects with stable COPD. The median BFI and SF-MPQ-2 Total scores were 1.00 [IQR: 0.11–2.78] and 0.00 [IQR: 0.00–0.27], respectively. They were all skewed toward the milder end of the respective scales. A floor effect was noted in around a quarter on the BFI and over half on the SF-MPQ-2. The BFI scores were significantly different between groups regarding frailty determined by the Kihon Checklist but not between groups classified by the severity of airflow limitation. Compared to the literature, neither fatigue nor pain are considered to be frequent, important problems in a real-world Japanese clinical setting, especially among subjects with mild to moderate COPD. In addition, our results might suggest that fatigue is more closely related to frailty than COPD.

We used virtual navigator real-time ultrasound (US) fusion imaging with 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to identify a lesion that could not be detected on the US alone in a preoperative breast cancer patient. Of the patient’s two lesions of breast cancer, the calcified lesion could not be identified by US alone. By fusing US with 18F-FDG PET/CT, which had been performed in advance, the location of the lesion could be estimated and marked, which benefited planning an appropriate surgery. The fusion of US and 18F-FDG PET/CT was a simple and noninvasive method for identifying the lesions detected by 18F-FDG PET/CT.

Objective The aim of this study was to evaluate the performance of preoperative axillary lymph node assessment in breast cancer using time-of-flight 18F-fluorodeoxyglucose PET/computed tomography (TOF [F-18]FDG-PET/CT). Methods Eighty-two women with breast cancer (mean age, 59.3 years; range, 30-84 years) underwent TOF [F-18]FDG-PET/CT scanning before surgery between January 2016 and June 2018 at our hospital. Visual analysis of FDG uptake and the maximum standardized uptake value (SUVmax) of axillary lymph nodes were compared with the pathological diagnoses. Results There were 77 patients with invasive breast carcinoma (mean invasive long diameter, 18.5 mm; range, 2-90 mm) and five patients with noninvasive carcinoma. Axillary lymph node metastases were histologically confirmed in 13 of 82 patients (15.9%). SUVmax showed an area under a receiver operating characteristic curve of 0.916, and the cut-off value of 1.1 was appropriate. By visual assessment, there were 11 true positives, 15 false positives, 54 true negatives and two false negatives; the sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 85%, 78%, 42%, 96% and 79%, respectively. SUVmax showed values of 69%, 99%, 90%, 94% and 94%, respectively. Conclusions The sensitivity of TOF [F-18]FDG-PET/CT was as high as 85% by visual analysis. SUVmax using TOF [F-18]FDG-PET/CT showed high diagnostic performance for N-staging in breast cancer patients, especially high negative predictive value. The specificity, positive predictive value and accuracy of SUVmax were higher than those of visual analysis.

To compare the addition of diagnostic strain elastography (SE) and shear wave elastography (SWE) values to the conventional B-mode ultrasonography in differentiating between benign and malignant breast masses by qualitative and quantitative assessments. B-mode ultrasound, SE, and SWE were simultaneously performed using one ultrasound system in 148 breast masses; 88 of them were malignant. The breast imaging reporting and data system category in the B-mode, Tsukuba score (SETsu), Fat-Lesion-Ratio (SEFLR) in SE, and five-point color assessment (SWEcol) and elasticity values (SWEela) in SWE were assessed. The results were compared using the area under the receiver-operating characteristic curve (AUC). The AUC for B-mode and each elastography were similar (B-mode, 0.889; SETsu, 0.885; SEFLR, 0.875; SWEcol, 0.881; SWEela, 0.885; P > 0.05). The combined sets between B-mode and either of the elastography technique showed good diagnostic performance (B-mode + SETsu, 0.903; B-mode + SEFLR, 0.909; B-mode + SWEcol, 0.919; B-mode + SWEela, 0.914). B-mode + SWEcol and B-mode + SWEela showed a higher AUC than B-mode alone (P = 0.026 and 0.029), and B-mode + SETsu and B-mode + SEFLR showed comparable AUC to B-mode alone (P = 0.196 and 0.085). There was no significant difference between qualitative and quantitative assessments for the combined sets of B-mode and elastography (P > 0.05). The addition of both SE and SWE to B-mode ultrasound improved the diagnostic performance with increased AUC, and especially SWE was more useful than SE, and no significant difference was found between qualitative and quantitative assessments.

Background: The study was conducted to evaluate the clinical and computed tomography (CT) findings of non-small cell lung cancer (NSCLC) patients to distinguish between ALK gene rearrangement, EGFR mutation,and non-ALK/EGFR (no genetic abnormalities). Methods: We enrolled 201 patients with primary NSCLC who had undergone molecular testing for both ALK gene rearrangement and EGFR mutation. The clinical features and CT findings of the main lesion and associated pulmonary abnormalities were investigated.Results: Female gender (P = 0.0043 vs. non-ALK/EGFR), young age (P = 0.0156 vs. EGFR),and a light or never smoking history (P = 0.0039 vs. non-ALK/EGFR) were significant clinical characteristics of NSCLC with ALK gene rearrangement. The significant CT characteristics compared to NSCLC with EGFR mutation were a large mass (P = 0.0155), solid mass (P = 0.0048), and no air bronchogram (P = 0.0148). A central location (P = 0.0322) and lymphadenopathy (P =0.0353) were also more frequently observed. Coexisting emphysema was significantly less frequent in NSCLC patients with ALK gene rearrangement (P = 0.0135) than non-ALK/EGFR. Conclusions: NSCLC with ALK gene rearrangement was more likely to develop in younger women with a light or never smoking history. The characteristic CT findings of NSCLC with ALK gene rearrangement were a large solid mass, less air bronchogram, a central location, and lymphadenopathy., Thoracic Cancer, 10(4), pp.872-879; 2019

We aimed to use deep learning with convolutional neural network (CNN) to discriminate between benign and malignant breast mass images from ultrasound. We retrospectively gathered 480 images of 96 benign masses and 467 images of 144 malignant masses for training data. Deep learning model was constructed using CNN architecture GoogLeNet and analyzed test data: 48 benign masses, 72 malignant masses. Three radiologists interpreted these test data. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated. The CNN model and radiologists had a sensitivity of 0.958 and 0.583–0.917, specificity of 0.925 and 0.604–0.771, and accuracy of 0.925 and 0.658–0.792, respectively. The CNN model had equal or better diagnostic performance compared to radiologists (AUC = 0.913 and 0.728–0.845, p = 0.01–0.14). Deep learning with CNN shows high diagnostic performance to discriminate between benign and malignant breast masses on ultrasound.

This retrospective study examined the relationship between the standardized uptake value max (SUVmax) of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) and the prognostic stage of breast cancer. We examined 358 breast cancers in 334 patients who underwent 18F-FDG PET/CT for initial staging between January 2016 and December 2019. We extracted data including SUVmax of 18F-FDG PET and pathological biomarkers, including estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and nuclear grade. Anatomical and prognostic stages were determined per the American Joint Committee on Cancer (eighth edition). We examined whether there were statistical differences in SUVmax between each prognostic stage. The mean SUVmax values for clinical prognostic stages were as follow: stage 0, 2.2 ± 1.4, stage IA, 2.6 ± 2.1, stage IB, 4.2 ± 3.5, stage IIA, 5.2 ± 2.8, stage IIB, 7.7 ± 6.7, and stage III + IV, 7.0 ± 4.5. The SUVmax values for pathological prognostic stages were as follows: stage 0, 2.2 ± 1.4, stage IA, 2.8 ± 2.2, stage IB, 5.4 ± 3.6, stage IIA, 6.3 ± 3.1, stage IIB, 9.2 ± 7.5, and stage III + IV, 6.2 ± 5.2. There were significant differences in mean SUVmax between clinical prognostic stage 0 and ≥II (p &lt, 0.001) and I and ≥II (p &lt, 0.001). There were also significant differences in mean SUVmax between pathological prognostic stage 0 and ≥II (p &lt, 0.001). In conclusion, mean SUVmax increased with all stages up to prognostic stage IIB, and there were significant differences between several stages. The SUVmax of 18F-FDG PET/CT may contribute to prognostic stage stratification, particularly in early cases of breast cancers.

A woman in her 60s presented to our hospital with a left breast mass that was diagnosed as breast cancer. 18F-Fluorodeoxyglucose positron-emission tomography/computed tomography (18F-FDG PET/CT) revealed intense, hot uptake in the cancerous mass and left axillary lymph node metastasis. After chemotherapy, another PET/CT scan was performed. Although the mass and left axillary lymph nodes shrank and FDG uptake decreased, enlarged lymph nodes with high FDG uptake appeared in the right axilla. The patient had a painful vesicular eruption on the front to the back of the right upper hemithorax, which was diagnosed as active herpes zoster. Active herpes zoster mimics a worsening axillary lymph node metastasis on the PET/CT scan.

Background and Objectives: It is necessary to properly diagnose and manage axillary lymphadenopathy caused by a variety of diseases. This study aimed to evaluate the utility of ultrasound (US)-guided sampling in patients with axillary lymphadenopathy. Materials and Methods: Patients with axillary lymphadenopathy (excluding patients with newly diagnosed breast cancer) who underwent US-guided fine needle aspiration (FNA) or core needle biopsy (CNB) at a single center between February 2016 and September 2020 were retrospectively examined. The association between US imaging findings and malignancy was investigated and the diagnostic performance of US-guided sampling was assessed. Results: Fifty-five patients (including eight males) were included in the study, of these, 34 patients (61.8%) were finally diagnosed with a malignant lymph node lesion. Twenty-two patients (40.0%) had undergone FNA and 33 (60.0%) had undergone CNB. Larger short and long axis diameters, thicker lymph node cortex, and the absence of fatty hilum on the US were significantly associated with malignancy (p &lt, 0.05). The diagnostic performance of FNA, CNB, and FNA + CNB was excellent (sensitivity, specificity, and accuracy of 0.909, 0.900, and 0.917 for FNA, 0.958, 1.000, and 0.970 for CNB, and 0.941, 0.952, and 0.945 for FNA + CNB, respectively). Conclusions: US-guided FNA and CNB play an important role in the diagnosis and management of patients with axillary lymphadenopathy

Background: Indocyanine green angiography enables real-time visualization of blood vessels at depths of up to 10 mm beneath the body surface, thereby aiding the evaluation of the viability of skin flaps and predicting necrosis in surgical fields requiring good tissue perfusion. Although skin-flap necrosis also occurs in mastectomy without reconstruction, most studies have focused on reconstructive plastic surgery. Several patients undergoing mastectomy are eligible for postoperative adjuvant therapy, but complications can lead to delays in treatment and thus require prevention. However, a lack of a standard protocol for evaluating skin-flap perfusion using indocyanine green necessitates the study of its characteristics to facilitate comparison of the perfusion rate among individuals. Methods: This retrospective study focused on the characteristics of indocyanine green and established a protocol for indocyanine green angiography using laser-assisted imaging (SPY system) to predict postoperative skin-flap necrosis from intraoperative images of 30 patients who underwent mastectomy without reconstruction. Results: Our protocol predicted postoperative skin-flap necrosis as follows. First, the intravenous dose and concentration were set at 2.5 mg/mL and 0.05 mg/kg, respectively. Second, the timing of measurement was set to 100 s after the entry of indocyanine green into the skin (plateau phase); the analysis pattern was set to single frame. Third, comparisons among individuals were made using relative values. Conclusions: We analyzed the area of postoperative flap necrosis using this protocol. We found that the intraoperative images showed decreased perfusion in that area, which was useful in predicting skin-flap necrosis, as reported by previous breast reconstruction studies.

PURPOSE Synthetic MRI reconstructs multiple sequences in a single acquisition. In the present study, we aimed to compare the image quality and utility of synthetic MRI with that of conventional MRI in the breast. METHODS We retrospectively collected the imaging data of 37 women (mean age: 55.1 years; range: 20-78 years) who had undergone both synthetic and conventional MRI of T2-weighted, T1-weighted, and fat-suppressed (FS)-T2-weighted images. Two independent breast radiologists evaluated the overall image quality, anatomical sharpness, contrast between tissues, image homogeneity, and presence of artifacts of synthetic and conventional MRI on a 5-point scale (5 = very good to 1 = very poor). The interobserver agreement between the radiologists was evaluated using weighted kappa. RESULTS For synthetic MRI, the acquisition time was 3 min 28 s. On the 5-point scale evaluation of overall image quality, although the scores of synthetic FS-T2-weighted images (4.01 ± 0.56) were lower than that of conventional images (4.95 ± 0.23; P < 0.001), the scores of synthetic T1- and T2-weighted images (4.95 ± 0.23 and 4.97 ± 0.16) were comparable with those of conventional images (4.92 ± 0.27 and 4.97 ± 0.16; P = 0.484 and 1.000, respectively). The kappa coefficient of conventional MRI was fair (0.53; P < 0.001), and that of conventional MRI was fair (0.46; P < 0.001). CONCLUSION The image quality of synthetic T1- and T2-weighted images was similar to that of conventional images and diagnostically acceptable, whereas the quality of synthetic T2-weighted FS images was inferior to conventional images. Although synthetic MRI images of the breast have the potential to provide efficient image diagnosis, further validation and improvement are required for clinical application.

The authors examined predictive properties and the longitudinal stability of blood eosinophil count (BEC) or three strata (&lt, 100 cells/mm3, 100–299 cells/mm3 and ≥300 cells/mm3) in patients with chronic obstructive pulmonary disease (COPD) for up to six and a half years as part of a hospital-based cohort study. Of the 135 patients enrolled, 21 (15.6%) were confirmed to have died during the follow-up period. Episodes of acute exacerbation of COPD (AECOPD) were identified in 74 out of 130 available patients (56.9%), and admission due to AECOPD in 35 out of 132 (26.5%). Univariate Cox proportional hazards analyses revealed that almost all the age, forced expiratory volume in 1 s (FEV1) and health status measures using St. George’s Respiratory Questionnaire (SGRQ) Total and COPD Assessment Test (CAT) Score were significantly related to these types of events, but the relationship between age and AECOPD did not reach statistical significance (p = 0.05). Neither BEC nor the three different groups stratified by BEC were significant predictors of any subsequent events. There were no significant differences in the BEC between Visits 1–3 (p = 0.127, Friedman test). The ICC value was 0.755 using log-transformed data, indicating excellent repeatability. In the case of assigning to strata, Fleiss’ kappa was calculated to be 0.464, indicating moderate agreement. The predictive properties of BEC may be limited in a real-world Japanese clinical setting. Attention must be paid to the fact that the longitudinal stability of the three strata is regarded as moderate.

At our institution (Tokyo Medical and Dental University, Medical Hospital), latissimus dorsi flap (LD flap) reconstruction without a prosthetic implant is a popular surgical strategy following total mastectomy in patients with breast cancer. The LD flap, especially the extended LD flap, is usually rotated anteriorly through the axilla. However, if future additional surgery is required for axillary recurrence after LD flap reconstruction, the flap interferes with the visual field, making the surgical procedure more difficult. Because cases of axillary lymph node recurrence alone are rare, to the best of our knowledge, no paper has reported in detail on the technique and course of lymph node recurrence after LD flap reconstruction. The present study describes two cases of successful axillary lymph node dissection without sacrificing the flap for breast cancer recurrence after LD flap reconstruction. A brief analysis of immediate breast reconstruction with an LD flap performed in patients with breast cancer at our institution is also reported.

Breast cancer is the most frequently diagnosed cancer in women; it poses a serious threat to women’s health. Thus, early detection and proper treatment can improve patient prognosis. Breast ultrasound is one of the most commonly used modalities for diagnosing and detecting breast cancer in clinical practice. Deep learning technology has made significant progress in data extraction and analysis for medical images in recent years. Therefore, the use of deep learning for breast ultrasonic imaging in clinical practice is extremely important, as it saves time, reduces radiologist fatigue, and compensates for a lack of experience and skills in some cases. This review article discusses the basic technical knowledge and algorithms of deep learning for breast ultrasound and the application of deep learning technology in image classification, object detection, segmentation, and image synthesis. Finally, we discuss the current issues and future perspectives of deep learning technology in breast ultrasound.

A 74 year old Japanese woman was diagnosed with invasive breast carcinoma. Her axillary lymph node was slightly swollen and had a short-axis diameter of 8 mm, but fine-needle aspiration did not lead to the diagnosis of metastasis. Subsequent 18F-fluorodeoxyglucose positron emission tomography/computed tomography showed no abnormal accumulation on the lymph node. Ultrafast dynamic magnetic resonance imaging yielded a very fast contrast enhancement like that of the primary lesion based on which we suspected lymph node metastasis. To our knowledge, this is the first report that shows that ultrafast imaging has contributed to the diagnosis of axillary lymph node metastasis.

The accuracy of modern imaging techniques for the diagnosis of peritoneal carcinomatosis is poor. A breast cancer patient with a high serum CA15-3 level did not receive a definitive diagnosis of peritoneal dissemination by imaging examination and then underwent laparoscopy. Pathological examination showed peritoneal dissemination of breast cancer, but the biological markers were different from the primary lesion: ER(−), PgR(−), and Her2:3 +. T-DM1 therapy was very effective, and her systemic symptoms disappeared. Since biomarkers of metastatic lesions may sometimes change, laparoscopic biopsy is very important and useful.

We aimed to use deep learning with convolutional neural networks (CNNs) to discriminate images of benign and malignant breast masses on ultrasound shear wave elastography (SWE). We retrospectively gathered 158 images of benign masses and 146 images of malignant masses as training data for SWE. A deep learning model was constructed using several CNN architectures (Xception, InceptionV3, InceptionResNetV2, DenseNet121, DenseNet169, and NASNetMobile) with 50, 100, and 200 epochs. We analyzed SWE images of 38 benign masses and 35 malignant masses as test data. Two radiologists interpreted these test data through a consensus reading using a 5-point visual color assessment (SWEc) and the mean elasticity value (in kPa) (SWEe). Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. The best CNN model (which was DenseNet169 with 100 epochs), SWEc, and SWEe had a sensitivity of 0.857, 0.829, and 0.914 and a specificity of 0.789, 0.737, and 0.763 respectively. The CNNs exhibited a mean AUC of 0.870 (range, 0.844–0.898), and SWEc and SWEe had an AUC of 0.821 and 0.855. The CNNs had an equal or better diagnostic performance compared with radiologist readings. DenseNet169 with 100 epochs, Xception with 50 epochs, and Xception with 100 epochs had a better diagnostic performance compared with SWEc ( P = 0.018–0.037). Deep learning with CNNs exhibited equal or higher AUC compared with radiologists when discriminating benign from malignant breast masses on ultrasound SWE.

We aimed to evaluate an artificial intelligence (AI) system that can detect and diagnose lesions of maximum intensity projection (MIP) in dynamic contrast-enhanced (DCE) breast magnetic resonance imaging (MRI). We retrospectively gathered MIPs of DCE breast MRI for training and validation data from 30 and 7 normal individuals, 49 and 20 benign cases, and 135 and 45 malignant cases, respectively. Breast lesions were indicated with a bounding box and labeled as benign or malignant by a radiologist, while the AI system was trained to detect and calculate possibilities of malignancy using RetinaNet. The AI system was analyzed using test sets of 13 normal, 20 benign, and 52 malignant cases. Four human readers also scored these test data with and without the assistance of the AI system for the possibility of a malignancy in each breast. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were 0.926, 0.828, and 0.925 for the AI system; 0.847, 0.841, and 0.884 for human readers without AI; and 0.889, 0.823, and 0.899 for human readers with AI using a cutoff value of 2%, respectively. The AI system showed better diagnostic performance compared to the human readers (p = 0.002), and because of the increased performance of human readers with the assistance of the AI system, the AUC of human readers was significantly higher with than without the AI system (p = 0.039). Our AI system showed a high performance ability in detecting and diagnosing lesions in MIPs of DCE breast MRI and increased the diagnostic performance of human readers.

Purpose We aimed to evaluate deep learning approach with convolutional neural networks (CNNs) to discriminate between benign and malignant lesions on maximum intensity projections of dynamic contrast-enhanced breast magnetic resonance imaging (MRI). Methods We retrospectively gathered maximum intensity projections of dynamic contrast-enhanced breast MRI of 106 benign (including 22 normal) and 180 malignant cases for training and validation data. CNN models were constructed to calculate the probability of malignancy using CNN architectures (DenseNet121, DenseNet169, InceptionResNetV2, InceptionV3, NasNetMobile, and Xception) with 500 epochs and analyzed that of 25 benign (including 12 normal) and 47 malignant cases for test data. Two human readers also interpreted these test data and scored the probability of malignancy for each case using Breast Imaging Reporting and Data System. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated. Results The CNN models showed a mean AUC of 0.830 (range, 0.750–0.895). The best model was InceptionResNetV2. This model, Reader 1, and Reader 2 had sensitivities of 74.5%, 72.3%, and 78.7%; specificities of 96.0%, 88.0%, and 80.0%; and AUCs of 0.895, 0.823, and 0.849, respectively. No significant difference arose between the CNN models and human readers (p > 0.125). Conclusion Our CNN models showed comparable diagnostic performance in differentiating between benign and malignant lesions to human readers on maximum intensity projection of dynamic contrast-enhanced breast MRI.

The oncological safety of immediate breast reconstruction (IBR) in lymph node-positive patients is unclear. In the present study, the impact of IBR on recurrence based on data of patients with axillary lymph node metastases only was examined. The subjects were 232 patients who underwent breast surgery. The patients were grouped into 2 cohorts: non-IBR patients who underwent mastectomy with axillary lymph node dissection; and IBR patients with tissue expander or flap transfer and axillary lymph node dissection. The Non-IBR group included 165 patients, and the IBR group included 67 patients. For the comparison of oncological outcomes between the 2 groups, propensity score matching was performed. The propensity scores were calculated by logistic regression analysis, including age, tumor staging, human epidermal growth factor receptor 2 status, and estrogen receptor status. There was no difference in locoregional recurrence-free survival (LRRFS) between the non-IBR and IBR groups. The 5-year LRRFS rate was 78.9% in the non-IBR group and 85.1% in the IBR group. There was no difference in recurrence-free survival (RFS) between the non-IBR and IBR groups. The 5-year RFS rate was 75.6% in the non-IBR group and 78.8% in the IBR group. In all patients, the 5-year LRRFS rate was 77.3%, and the RFS rate was 70.5%. Multivariate Cox regression analysis to identify factors affecting RFS in all patients showed that estrogen receptor status and high nuclear grade were significant prognostic factors; IBR was irrelevant. This is the first report of an analysis using propensity score matching limited to node-positive breast cancer patients, and it showed that IBR is relatively safe in such patients.

The purpose of this study was to use the Coronavirus Disease 2019 (COVID-19) Reporting and Data System (CO-RADS) to evaluate the chest computed tomography (CT) images of patients suspected of having COVID-19, and to investigate its diagnostic performance and interobserver agreement. The Dutch Radiological Society developed CO-RADS as a diagnostic indicator for assessing suspicion of lung involvement of COVID-19 on a scale of 1 (very low) to 5 (very high). We investigated retrospectively 154 adult patients with clinically suspected COVID-19, between April and June 2020, who underwent chest CT and reverse transcription-polymerase chain reaction (RT-PCR). The patients&rsquo, average age was 61.3 years (range, 21&ndash, 93), 101 were male, and 76 were RT-PCR positive. Using CO-RADS, four radiologists evaluated the chest CT images. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Interobserver agreement was calculated using the intraclass correlation coefficient (ICC) by comparing the individual reader&rsquo, s score to the median of the remaining three radiologists. The average sensitivity was 87.8% (range, 80.2&ndash, 93.4%), specificity was 66.4% (range, 51.3&ndash, 84.5%), and AUC was 0.859 (range, 0.847&ndash, 0.881), there was no significant difference between the readers (p &gt, 0.200). In 325 (52.8%) of 616 observations, there was absolute agreement among observers. The average ICC of readers was 0.840 (range, 0.800&ndash, 0.874, p &lt, 0.001). CO-RADS is a categorical taxonomic evaluation scheme for COVID-19 pneumonia, using chest CT images, that provides outstanding performance and from substantial to almost perfect interobserver agreement for predicting COVID-19.

We aimed to use generative adversarial network (GAN)-based anomaly detection to diagnose images of normal tissue, benign masses, or malignant masses on breast ultrasound. We retrospectively collected 531 normal breast ultrasound images from 69 patients. Data augmentation was performed and 6372 (531 × 12) images were available for training. Efficient GAN-based anomaly detection was used to construct a computational model to detect anomalous lesions in images and calculate abnormalities as an anomaly score. Images of 51 normal tissues, 48 benign masses, and 72 malignant masses were analyzed for the test data. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of this anomaly detection model were calculated. Malignant masses had significantly higher anomaly scores than benign masses (p < 0.001), and benign masses had significantly higher scores than normal tissues (p < 0.001). Our anomaly detection model had high sensitivities, specificities, and AUC values for distinguishing normal tissues from benign and malignant masses, with even greater values for distinguishing normal tissues from malignant masses. GAN-based anomaly detection shows high performance for the detection and diagnosis of anomalous lesions in breast ultrasound images.

Deep convolutional generative adversarial networks (DCGANs) are newly developed tools for generating synthesized images. To determine the clinical utility of synthesized images, we generated breast ultrasound images and assessed their quality and clinical value. After retrospectively collecting 528 images of 144 benign masses and 529 images of 216 malignant masses in the breasts, synthesized images were generated using a DCGAN with 50, 100, 200, 500, and 1000 epochs. The synthesized (n = 20) and original (n = 40) images were evaluated by two radiologists, who scored them for overall quality, definition of anatomic structures, and visualization of the masses on a five-point scale. They also scored the possibility of images being original. Although there was no significant difference between the images synthesized with 1000 and 500 epochs, the latter were evaluated as being of higher quality than all other images. Moreover, 2.5%, 0%, 12.5%, 37.5%, and 22.5% of the images synthesized with 50, 100, 200, 500, and 1000 epochs, respectively, and 14% of the original images were indistinguishable from one another. Interobserver agreement was very good (|r| = 0.708−0.825, p < 0.001). Therefore, DCGAN can generate high-quality and realistic synthesized breast ultrasound images that are indistinguishable from the original images.