A Novel Structure Fusion Attention Model to Detect Architectural Distortion on Mammography.

Architectural distortion (AD) is one of the most common findings on mammograms, and it may represent not only cancer but also a lesion such as a radial scar that may have an associated cancer. AD accounts for 18-45% missed cancer, and the positive predictive value of AD is approximately 74.5%. Early detection of AD leads to early diagnosis and treatment of the cancer and improves the overall prognosis. However, detection of AD is a challenging task. In this work, we propose a new approach for detecting architectural distortion in mammography images by combining preprocessing methods and a novel structure fusion attention model. The proposed structure-focused weighted orientation preprocessing method is composed of the original image, the architecture enhancement map, and the weighted orientation map, highlighting suspicious AD locations. The proposed structure fusion attention model captures the information from different channels and outperforms other models in terms of false positives and top sensitivity, which refers to the maximum sensitivity that a model can achieve under the acceptance of the highest number of false positives, reaching 0.92 top sensitivity with only 0.6590 false positive per image. The findings suggest that the combination of preprocessing methods and a novel network architecture can lead to more accurate and reliable AD detection. Overall, the proposed approach offers a novel perspective on detecting ADs, and we believe that our method can be applied to clinical settings in the future, assisting radiologists in the early detection of ADs from mammography, ultimately leading to early treatment of breast cancer patients.

Suspicious Ultrasound-Occult Non-Calcified Mammographic Masses, Asymmetries, and Architectural Distortions Are Moderate Probability for Malignancy.

Suspicious non-calcified mammographic findings have not been evaluated with modern mammographic technique, and the purpose of this work is to compare the likelihood of malignancy for those findings. To do this, 5018 consecutive mammographically guided biopsies performed during 2016-2019 at a large metropolitan, community-based hospital system were retrospectively reviewed. In total, 4396 were excluded for targeting calcifications, insufficient follow-up, or missing data. Thirty-seven of 126 masses (29.4%) were malignant, 44 of 194 asymmetries (22.7%) were malignant, and 77 of 302 architectural distortions (AD, 25.5%) were malignant. The combined likelihood of malignancy was 25.4%. Older age was associated with a higher likelihood of malignancy for each imaging finding type (all p ≤ 0.006), and a possible ultrasound correlation was associated with a higher likelihood of malignancy when all findings were considered together (p = 0.012). Two-view asymmetries were more frequently malignant than one-view asymmetries (p = 0.03). There were two false-negative biopsies (98.7% sensitivity and 100% specificity). In conclusion, the 25.4% likelihood of malignancy confirms the recommendation for biopsy of suspicious, ultrasound-occult, mammographic findings. Mammographically guided biopsies were highly sensitive and specific in this study. Older patient age and a possible ultrasound correlation should raise concern given the increased likelihood of malignancy in those scenarios.

Atypical architectural distortion detection in digital breast tomosynthesis: a multi-view computer-aided detection model with ipsilateral learning.

Objective.Breast architectural distortion (AD), a common imaging symptom of breast cancer, is associated with a particularly high rate of missed clinical detection. In clinical practice, atypical ADs that lack an obvious radiating appearance constitute most cases, and detection models based on single-view images often exhibit poor performance in detecting such ADs. Existing multi-view deep learning methods have overlooked the correspondence between anatomical structures across different views.Approach.To develop a computer-aided detection (CADe) model for AD detection that effectively utilizes the craniocaudal (CC) and mediolateral oblique (MLO) views of digital breast tomosynthesis (DBT) images, we proposed an anatomic-structure-based multi-view information fusion approach by leveraging the related anatomical structure information between these ipsilateral views. To obtain a representation that can effectively capture the similarity between ADs in images from ipsilateral views, our approach utilizes a Siamese network architecture to extract and compare information from both views. Additionally, we employed a triplet module that utilizes the anatomical structural relationship between the ipsilateral views as supervision information.Main results.Our method achieved a mean true positive fraction (MTPF) of 0.05-2.0, false positives (FPs) per volume of 64.40%, and a number of FPs at 80% sensitivity (FPs@0.8) of 3.5754; this indicates a 6% improvement in MPTF and 16% reduction in FPs@0.8 compared to the state-of-the-art baseline model.Significance.From our experimental results, it can be observed that the anatomic-structure-based fusion of ipsilateral view information contributes significantly to the improvement of CADe model performance for atypical AD detection based on DBT. The proposed approach has the potential to lead to earlier diagnosis and better patient outcomes.

The Japan Society of Ultrasonics in Medicine guidelines on non-mass abnormalities of the breast.

It is possible to appropriately diagnose non-mass abnormalities by elucidating ultrasound non-mass abnormality findings and sharing the concept. If non-mass abnormalities can be diagnosed early, the number of curable cases could increase, leading to fewer breast cancer deaths. The Japan Society of Ultrasonics in Medicine (JSUM) Terminology/Diagnostic Criteria Committee has classified non-mass abnormalities into five subtypes: hypoechoic area in the mammary gland, abnormalities of the ducts, architectural distortion, multiple small cysts, and echogenic foci without a hypoechoic area. We herein define the findings for each of these subtypes and present a summary of the JSUM guidelines on non-mass abnormalities of the breast generated based on those findings.

Tomosynthesis-Detected Architectural Distortions: Correlations between Imaging Characteristics and Histopathologic Outcomes.

OBJECTIVE: to determine the positive predictive value (PPV) of tomosynthesis (DBT)-detected architectural distortions (ADs) and evaluate correlations between AD's imaging characteristics and histopathologic outcomes. METHODS: biopsies performed between 2019 and 2021 on ADs were included. Images were interpreted by dedicated breast imaging radiologists. Pathologic results after DBT-vacuum assisted biopsy (DBT-VAB) and core needle biopsy were compared with AD detected by DBT, synthetic2D (synt2D) and ultrasound (US). RESULTS: US was performed to assess a correlation for ADs in all 123 cases and a US correlation was identified in 12/123 (9.7%) cases, which underwent US-guided core needle biopsy (CNB). The remaining 111/123 (90.2%) ADs were biopsied under DBT guidance. Among the 123 ADs included, 33/123 (26.8%) yielded malignant results. The overall PPV for malignancy was 30.1% (37/123). The imaging-specific PPV for malignancy was 19.2% (5/26) for DBT-only ADs, 28.2% (24/85) for ADs visible on DBT and synth2D mammography and 66.7% (8/12) for ADs with a US correlation with a statistically significant difference among the three groups (p = 0.01). CONCLUSIONS: DBT-only ADs demonstrated a lower PPV of malignancy when compared with syntD mammography, and DBT detected ADs but not low enough to avoid biopsy. As the presence of a US correlate was found to be related with malignancy, it should increase the radiologist's level of suspicion, even when CNB returned a B3 result.

Identification and diagnosis of mammographic malignant architectural distortion using a deep learning based mask regional convolutional neural network.

Background: Architectural distortion (AD) is a common imaging manifestation of breast cancer, but is also seen in benign lesions. This study aimed to construct deep learning models using mask regional convolutional neural network (Mask-RCNN) for AD identification in full-field digital mammography (FFDM) and evaluate the performance of models for malignant AD diagnosis. Methods: This retrospective diagnostic study was conducted at the Second Affiliated Hospital of Guangzhou University of Chinese Medicine between January 2011 and December 2020. Patients with AD in the breast in FFDM were included. Machine learning models for AD identification were developed using the Mask RCNN method. Receiver operating characteristics (ROC) curves, their areas under the curve (AUCs), and recall/sensitivity were used to evaluate the models. Models with the highest AUCs were selected for malignant AD diagnosis. Results: A total of 349 AD patients (190 with malignant AD) were enrolled. EfficientNetV2, EfficientNetV1, ResNext, and ResNet were developed for AD identification, with AUCs of 0.89, 0.87, 0.81 and 0.79. The AUC of EfficientNetV2 was significantly higher than EfficientNetV1 (0.89 vs. 0.78, P=0.001) for malignant AD diagnosis, and the recall/sensitivity of the EfficientNetV2 model was 0.93. Conclusion: The Mask-RCNN-based EfficientNetV2 model has a good diagnostic value for malignant AD.

Atypical architectural distortion detection in digital breast tomosynthesis: a computer-aided detection model with adaptive receptive field.

Objective. In digital breast tomosynthesis (DBT), architectural distortion (AD) is a breast lesion that is difficult to detect. Compared with typical ADs, which have radial patterns, identifying a typical ADs is more difficult. Most existing computer-aided detection (CADe) models focus on the detection of typical ADs. This study focuses on atypical ADs and develops a deep learning-based CADe model with an adaptive receptive field in DBT.Approach. Our proposed model uses a Gabor filter and convergence measure to depict the distribution of fibroglandular tissues in DBT slices. Subsequently, two-dimensional (2D) detection is implemented using a deformable-convolution-based deep learning framework, in which an adaptive receptive field is introduced to extract global features in slices. Finally, 2D candidates are aggregated to form the three-dimensional AD detection results. The model is trained on 99 positive cases with ADs and evaluated on 120 AD-positive cases and 100 AD-negative cases.Main results. A convergence-measure-based model and deep-learning model without an adaptive receptive field are reproduced as controls. Their mean true positive fractions (MTPF) ranging from 0.05 to 4 false positives per volume are 0.3846 ± 0.0352 and 0.6501 ± 0.0380, respectively. Our proposed model achieves an MTPF of 0.7148 ± 0.0322, which is a significant improvement (p< 0.05) compared with the other two methods. In particular, our model detects more atypical ADs, primarily contributing to the performance improvement.Significance. The adaptive receptive field helps the model improve the atypical AD detection performance. It can help radiologists identify more ADs in breast cancer screening.

Pathologic Outcomes in Single Versus Multiple Areas of Architectural Distortion on Digital Breast Tomosynthesis.

BACKGROUND. Digital breast tomosynthesis (DBT) has led to increased detection of architectural distortion (AD). Management of patients with multiple areas of AD is not established. OBJECTIVE. The purpose of this article is to compare pathologic outcomes between single and multiple areas of AD identified on DBT. METHODS. This retrospective study included 402 patients (mean age, 56 years) who underwent image-guided core needle biopsy of AD visualized on DBT between April 7, 2017, and April 16, 2019. Patients were classified as having a single or multiple areas of AD according to the presence of distinct areas of AD described in the clinical radiology reports. The pathologic diagnosis for each AD was on the basis of the most aggressive pathology identified on either biopsy or surgical excision, if performed. Patients with single and multiple areas of AD were compared. RESULTS. The sample included 372 patients with a single AD (145 benign, 121 high risk, 105 malignant, one other) and 30 patients with multiple visualized ADs, including 66 biopsied ADs (10 benign, 35 high risk, 21 malignant). At pathologic assessment on a per-lesion basis, multiple compared with single ADs showed higher frequency of high-risk pathology (53.0% vs 32.5%, p = .002) but no difference in frequency of malignancy (31.8% vs 28.2%, p = .56). In multivariable analysis of a range of patient-related characteristics, the presence of single versus multiple areas of AD was not independently associated with malignancy (p = .51). In patients with multiple areas of AD, the most aggressive pathology (benign, high risk, or malignant) across all ADs was not associated with the number of ADs (p = .73). In 8 of 24 patients with at least two ipsilateral biopsied ADs, the ipsilateral areas varied in terms of most aggressive pathology; in 5 of 10 patients with contralateral biopsied ADs, the contralateral areas varied in most aggressive pathology. CONCLUSION. The presence of multiple areas of AD, compared with a single AD, was significantly more likely to yield high-risk pathology but was not significantly different in yield of malignancy. In patients with multiple ADs, multiple ipsilateral or contralateral ADs commonly varied in pathologic classification (benign, high risk, or malignant). CLINICAL IMPACT. These findings may help guide management of AD visualized by DBT, including multiple ADs. For patients with multiple areas of AD, biopsy of all areas may be warranted given variation in pathologic diagnoses.

Digital tomosynthesis spot view in architectural distortions: outcomes in management and radiation dose.

PURPOSE: To evaluate if digital breast tomosynthesis spot compression view (DBT-SCV) could be an additional projection to confirm or deny architectural distortions (ADs) detected by digital breast tomosynthesis (DBT) while assessing the average glandular radiation dose. METHODS: This is a retrospective cohort study enrolling 8864 DBT exams, of which only cases detecting primary AD and with BI-RADS 2-5 score were considered. Seventy-one AD cases examined with DBT-SCV, US and MRI were evaluated for correlation in terms of BI-RADS score; variables among exams were assessed for inter-relationships. RESULTS: Of all ADs identified at DBT, biopsy yielded malignancy in only 38%. PPV in identifying malignancy of ADs was higher for DBT-SCV than DBT (p < 0.05); the NPV of DBT-SCV was 94%. The difference between DBT and DBT-SCV in the detection of benign ADs was statistically significant (p < 0.05). AD without US or MRI confirmation was less likely to represent malignancy (p < 0.05). In detecting malignant cases of ADs, both DBT and DBT-SCV were strongly correlated with US and RM (Kappa > 0.90). In identifying benign cases of ADs, DBT-SCV was poorly/moderately correlated with US and RM (Kappa 0.25 and 0.66); DBT was negatively correlated with US and MRI. CONCLUSION: DBT-SCV could be useful to better characterize AD firstly identified by DBT, keeping dose levels within the reference limits. If AD is detected by DBT without an US or MRI correlate, that is not confirmed by DBT-SCV, a "wait and see" approach can be applied to reduce unnecessary biopsy.

Management of Mammographic Architectural Distortion Based on Contrast-enhanced MRI and US Correlation.

OBJECTIVE: The objective was to evaluate outcomes of mammographic architectural distortion (AD) with and without MRI and US correlates. METHODS: A retrospective review of unexplained mammographic AD with subsequent MRI from January 1, 2007 to September 30, 2017 was performed using a reader-based study design. Mammographic, MRI, and US features and outcomes were documented. Truth was based on biopsy results or minimum two-year imaging follow-up. Measures of diagnostic accuracy were calculated. RESULTS: Fifty-six cases of AD were included: 29 (51.8%) detected on 2D mammogram and 27 (48.2%) detected on digital breast tomosynthesis. Of 35.7% (20/56) with MRI correlate, 40.0% (8/20) were enhancing masses, 55.0% (11/20) were non-mass enhancement (NME), and 5.0% (1/20) were nonenhancing AD. Of eight enhancing masses, 75.0% (6/8) were invasive cancers, and 25.0% (2/8) were high-risk lesions. Of 11 NME, 18.2% (2/11) were ductal carcinoma in situ, 36.4% (4/11) were high-risk lesions, and 45.4% (5/11) were benign. Of 64.3% (36/56) without MRI correlate, 94.4% (34/36) were benign by pathology or follow-up, one (2.8%, 1/36) was a 4-mm focus of invasive cancer with US correlate, and one (1/36, 2.8%) was a high-risk lesion. Of cases without MRI and US correlates, one (3.0%, 1/33) was a high-risk lesion and 97.0% (32/33) were benign. The negative predictive value of mammographic AD without MRI correlate was 97.2% (35/36) and without both MRI and US correlates was 100.0% (33/33). CONCLUSION: Mammographic AD without MRI or US correlate was not cancer in our small cohort and follow-up could be considered, reducing interventions.

Diagnosis of architectural distortion on digital breast tomosynthesis using radiomics and deep learning.

Purpose: To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images. Materials and Methods: A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant. Results: The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p<0.01), which was presumably due to the use of the entire image as input. The Grad-CAM could localize the architectural distortion areas. Conclusion: The radiomics model can achieve a satisfactory diagnostic accuracy, and the high specificity in the benign group can be used to avoid unnecessary biopsies. Deep learning can be used to localize the architectural distortion areas, which may provide an automatic method for ROI delineation to facilitate the development of a fully-automatic computer-aided diagnosis system using combined AI strategies.

Outcomes of Canceled Tomosynthesis-Guided Biopsy of Architectural Distortion Due to Nonvisualization.

Objective: Architectural distortion without a sonographic correlate is an indication for digital breast tomosynthesis-guided vacuum-assisted biopsy (DBT-VAB). However, when the finding is not visualized on the day of biopsy, the procedure is canceled. This study reports the outcomes of canceled DBT-VAB of architectural distortion due to nonvisualization. Methods: In this IRB-approved retrospective study, chart review was performed to identify DBT-VABs of architectural distortion at our institution between June 1, 2017, and November 1, 2020, that were canceled because of nonvisualization at the time of biopsy. Cases without follow-up imaging were excluded. Statistical analysis, including the frequency of cases yielding malignancy by the end of the study period, was performed. Results: In total, 7.2% (39/544) of architectural distortions recommended for biopsy during the study period were canceled because of nonvisualization, 30 of which had follow-up imaging and were included in the study. Mean patient age was 56 years (standard deviation [SD], 9.6 years) and mean follow-up time was 26.7 months (SD, 11.2 months; range, 8.4-50.9 months). During the follow-up period, 16.7% (5/30) underwent repeat biopsy attempt, with one malignant result (1/30, 3.3%; SD, 18%; 95% confidence interval: 0.6%-16.7%). In total, 86.7% (26/30) of cases were declared benign during the follow-up period and 10% (3/30) remained stable with a BI-RADS 3 assessment category. Conclusion: During available follow-up, there was a low likelihood that distortions not visualized at the time of DBT-VAB represented malignancy (3.3%, 1/30). While this low malignancy rate is reassuring, imaging follow-up is warranted.

Evaluation of the Combination of Artificial Intelligence and Radiologist Assessments to Interpret Malignant Architectural Distortion on Mammography.

Purpose: To compare the mammographic malignant architectural distortion (AD) detection performance of radiologists who read mammographic examinations unaided versus those who read these examinations with the support of artificial intelligence (AI) systems. Material and Methods: This retrospective case-control study was based on a double-reading of clinical mammograms between January 2011 and December 2016 at a large tertiary academic medical center. The study included 177 malignant and 90 benign architectural distortion (AD) patients. The model was built based on the ResNeXt-50 network. Algorithms used deep learning convolutional neural networks, feature classifiers, image analysis algorithms to depict AD and output a score that translated to malignant. The accuracy for malignant AD detection was evaluated using area under the curve (AUC). Results: The overall AUC was 0.733 (95% CI, 0.673-0.792) for Reader First-1, 0.652 (95% CI, 0.586-0.717) for Reader First-2, and 0.655 (95% CI, 0.590-0.719) for Reader First-3. and the overall AUCs for Reader Second-1, 2, 3 were 0.875 (95% CI, 0.830-0.919), 0.882 (95% CI, 0.839-0.926), 0.884 (95% CI, 0.841-0.927),respectively. The AUCs for all the reader-second radiologists were significantly higher than those for all the reader-first radiologists (Reader First-1 vs. Reader Second-1, P= 0.004). The overall AUC was 0.792 (95% CI, 0.660-0.925) for AI algorithms. The combination assessment of AI algorithms and Reader First-1 achieved an AUC of 0.880 (95% CI, 0.793-0.968), increased than the Reader First-1 alone and AI algorithms alone. AI algorithms alone achieved a specificity of 61.1% and a sensitivity of 80.6%. The specificity for Reader First-1 was 55.5%, and the sensitivity was 86.1%. The results of the combined assessment of AI and Reader First-1 showed a specificity of 72.7% and sensitivity of 91.7%. The performance showed significant improvements compared with AI alone (p<0.001) as well as the reader first-1 alone (p=0.006). Conclusion: While the single AI algorithm did not outperform radiologists, an ensemble of AI algorithms combined with junior radiologist assessments were found to improve the overall accuracy. This study underscores the potential of using machine learning methods to enhance mammography interpretation, especially in remote areas and primary hospitals.

Multilevel musculo-fascial defect magnetic resonance study of female pelvic floor: retrospective case control study in women with pelvic floor dysfunction after the first vaginal delivery.

INTRODUCTION: Magnetic resonance imaging (MRI) provides a detailed display of the pelvic floor structures responsible for normal pelvic floor anatomy. The aim of the study is to assess the appearance of musculo-fascial defects in women with pelvic floor dysfunction following first vaginal delivery. MATERIAL AND METHODS: Analysis of axial T3 (Tesla 3) MRI scans from a case control study of symptomatic (n = 149) and asymptomatic (n = 60) women after first vaginal delivery. Presence and severity of pelvic organ support and attachment system defects in three axial pelvic planes were assessed. RESULTS: In the symptomatic group, major muscular defects were found in 67.1% (for pubovisceral muscle complex) and 87.9% (for iliococcygeal muscle). Only 6.7% of major pubovisceral and 35.0% of major iliococcygeal defects were identified in the controls (p = 0.000). Prolapse patients had an odds ratio (OR) of 22.1 (95% CI 8.94-54.67) to have major pubovisceral muscle complex defect and OR of 4.9 (95% CI 1.51-15.71) to have major iliococcygeal muscle defect. Fascial defects were found in 60.4% and 83.2% the symptomatic group, respectively. Those with prolapse had an OR of 29.1 (95% CI 9.77-86.31) to have facial defect at the level of pubovisceral muscle complex and an OR of 16.9 (95% CI 7.62-37.69) to have fascial defect at the level of iliococcygeal muscle. Uterosacral ligaments detachment was associated with prolapse with an OR of 10.1 (95% CI 4.01-25.29). For the model based on combination on all MRI markers, the area under the receiver operating characteristic curve is 0.921. CONCLUSIONS: This study provides comprehensive data about first vaginal delivery-induced changes in the levator ani muscle and endopelvic fascial attachment system. These changes are seen also in asymptomatic controls, but they are significantly less expressed.

Architectural distortion detection based on superior-inferior directional context and anatomic prior knowledge in digital breast tomosynthesis.

BACKGROUND: In 2020, breast cancer becomes the most leading diagnosed cancer all over the world. The burden is increasing in the prevention and treatment of breast cancer. Accurately detecting breast lesions in screening images is important for early detection of cancer. Architectural distortion (AD) is one of the breast lesions that need to be detected. PURPOSE: To develop a deep-learning-based computer-aided detection (CADe) model for AD in digital breast tomosynthesis (DBT). This model uses the superior-inferior directional context of DBT and anatomic prior knowledge to reduce false positive (FP). It can identify some negative samples that cannot be distinguished by deep learning features. METHODS: The proposed CADe model consists of three steps. In the first step, a deep learning detection network detects two-dimensional (2D) candidates of ADs in DBT slices with the inputs preprocessed by Gabor filters and convergence measure. In the second step, three-dimensional (3D) candidates are obtained by stacking 2D candidates along superior-inferior direction. In the last step, FP reduction for 3D candidates is implemented based on superior-inferior directional context and anatomic prior knowledge of breast. DBT data from 99 cases with AD were used as the training set to train the CADe model, and data from 208 cases were used as an independent test set (including 108 cases with AD and 100 cases without AD as the control group). The free-response receiver operating characteristic and mean true positive fraction (MTPF) in the range of 0.05-2.0 FPs per volume are used to evaluate the model. RESULTS: Compared with the baseline model based on convergence measure, our proposed method demonstrates significant improvement (MTPF: 0.2826 ± 0.0321 vs. 0.6640 ± 0.0399). Results of an ablation study show that our proposed context- and anatomy-based FP reduction methods improve the detection performance. The number of FPs per DBT volume reduces from 2.47 to 1.66 at 80% sensitivity after employing these two schemes. CONCLUSIONS: The deep learning model demonstrates practical value for AD detection. The results indicate that introducing superior-inferior directional context and anatomic prior knowledge into model can indeed reduce FPs and improve the performance of CADe model.

Management of Architectural Distortion on Digital Breast Tomosynthesis With Nonmalignant Pathology at Biopsy.

BACKGROUND. Digital breast tomosynthesis (DBT) has led to increased detection and biopsy of architectural distortion, which may yield malignancy, radial scar, or other benign pathologies. Management of nonmalignant architectural distortion on DBT remains controversial. OBJECTIVE. The purpose of this study was to determine upgrade rates of architectural distortion on DBT from nonmalignant pathology at biopsy to malignancy at surgery. METHODS. This retrospective study included cases of mammographically detected architectural distortion from July 1, 2016, to June 30, 2019, that were nonmalignant at image-guided needle biopsy and underwent surgical excision. Mammographic examinations included digital 2D mammography and DBT. Imaging data were extracted from radiology reports. Upgrade rates were summarized using descriptive statistics. Features of upgraded and nonupgraded cases were compared using Pearson chi-square test and Wilcoxon signed rank test. RESULTS. The study included 129 cases of architectural distortion with nonmalignant pathology at biopsy that underwent excision in 125 women (mean age, 54 years; range, 23-90 years). At biopsy, 92 (71.3%) were radial scars and 37 (28.7%) were other nonmalignant pathologies. Of 66 radial scars without atypia at biopsy, one (1.5%) was upgraded to ductal carcinoma in situ (DCIS) at surgery and none to invasive cancer. Of 24 benign pathologies without atypia at biopsy, one was considered discordant. Of the 23 remaining concordant cases, one (4.3%) was upgraded to DCIS at surgery and none to invasive cancer. The overall upgrade rate to cancer of architectural distortion with concordant nonmalignant pathology at biopsy was 10.2% (13/128). The upgrade rate to cancer of architectural distortion without atypia was 2.2% (2/89) and with atypia was 28.2% (11/39). Explored features (age, personal or family breast cancer history, presentation by screening vs diagnostic mammography, breast density, associated mammographic findings, presence and size of ultrasound correlate, biopsy modality) showed no signifi-cant associations with upgrade risk (p > .05). CONCLUSION. Architectural distortion on DBT with concordant nonmalignant pathology at biopsy has an overall upgrade rate to malignancy at surgery of 10.2%. Architectural distortion without atypia has a low upgrade rate of 2.2%. CLINICAL IMPACT. Imaging surveillance can be considered for architectural distortion on DBT yielding radial scar without atypia or other concordant benign pathologies without atypia at biopsy.

Meta-analysis: Architectural distortion and breast MRI.

BACKGROUND: The implementation of digital breast tomosynthesis has increased the detection of architectural distortion (AD). Managing this finding may be experienced as a clinical dilemma in daily practice. Breast Contrast-Enhanced MRI (CE-BMR) is a known modality in case of problem-solving tool for mammographic abnormalities. However, the data about AR and CE-BMR are scant. OBJECTIVE: The purpose was to estimate the benefit of CE-BMR in the setting of architectural distortion detected mammographically through a systematic review and meta-analysis of the literature. METHODS: A search of MEDLINE and EMBASE databases were conducted in 2020. Based on the PRISMA guidelines, an analysis was performed using the chi-square test of independence to determine if there was a significant association between the result of the test (positive or negative) and the participant condition (malignant or non-malignant). RESULTS: Four studies were available. The negative predictive value (NPV) was 98.3% to 100%. The result of the chi-square indicated that there was significant association between the participant test result and the participant condition for the included publications (X(1,175)2= 84.051, p = 0.0001). CONCLUSIONS: The high NPV could allow for deferral of a biopsy in favor of a short-interval imaging follow-up in the setting of a negative CE-BMR.

Pathological outcome of sonographically occult architectural distortions (AD) visible only on digital breast tomosynthesis, and comparison with AD visible also on 2D mammography.

PURPOSE: To evaluate the rates of malignant and of high-risk lesions among sonographically occult architectural distortions (AD) visible only on digital breast tomosynthesis (DBT) and compare them with AD visible on 2D mammography (2D) and DBT. METHOD: The records of 1104 DBT-vacuum assisted biopsies (DBT-VAB) were retrospectively reviewed and 218 cases of AD were identified. Complete radiologic examinations and pathologic results were available for 113 sonographically occult AD (1 clinically-detected, 112 clinically-occult). 2D and DBT images were reviewed and AD were divided into a "DBT-detected" group (visible on only DBT) and a "2D-detected" group (visible both in 2D and DBT). The rates of malignant and of high-risk lesions in the "DBT-detected" AD group were calculated and compared to those of the "2D-detected" AD group. RESULTS: Thirty-five (31%) of 113 AD were assessed as "DBT-detected", while 78 (69%) as "2D-detected". DBT-VAB results were benign lesions in 63 (56%) AD, high-risk lesions in 32 (28%) AD and malignant lesions in 18 (16%) AD. Four (12.5%) high-risk lesions were upgraded to malignancy at surgery. Based on final pathology, the malignancy rate was significantly higher in the "DBT-detected" group than the "2D-detected" group (34% [12/35 cases] vs 13% [10/78]; p < 0.05). The high-risk lesion rates were 32% (11/35 cases) in the "DBT-detected" group and 22% (17/78 cases) in the "2D-detected" group (p > 0.05). CONCLUSIONS: AD visible on only DBT proved to be malignant in about one third of cases, which exceeded the malignancy rate of AD visible on also 2D. A similar proportion of DBT-only AD was represented by high-risk lesions.

The Challenge of Digital Breast Tomosynthesis-Detected Architectural Distortion of the Breast: Inter-reader Variability and Imaging Characteristics That May Improve Positive Predictive Value.

OBJECTIVE: To compare readers' performances when detecting architectural distortion (AD) on digital breast tomosynthesis (DBT). To determine the risk of malignancy of DBT with synthetic mammogram (SM)-detected AD and evaluate imaging features that are associated with malignancy risk. METHODS: This IRB-approved retrospective review included all cases of DBT-detected AD that were recommended for biopsy from October 2013 to July 2019. Cases were reviewed by three breast radiologists and the overall agreement between radiologists was calculated. Medical records were reviewed for pathological outcomes and imaging findings. Statistical analyses used were Cohen's kappa and its 95% confidence interval, and one-way analysis of variance. RESULTS: A total of 172 lesions were included. The overall agreement for the presence of AD in our study was fair (0.253). The majority (20/36, 55.5%) of the malignant ADs were associated with asymmetries (13/36, 36.1%), calcifications (4/36, 11.1%), or both (3/36, 8.3%), compared to nonmalignant ADs (40/136, 31.0%; P = 0.038). The positive predictive value (PPV) of DBT with SM-detected AD for malignancy was 21.8% (36/165), 18.8% (18/96) for DBT-detected AD, and 26.0% (18/69) for SM-detected AD, although the difference was not statistically significant (P = 0.258). A breast MRI correlate was identified for all malignant AD lesions (17/17, 100.0%; P = 0.004). CONCLUSION: The detection of AD remains a challenging task for radiologists, with moderate-to-fair interobserver agreement. With a PPV for malignancy of 21.8%, percutaneous biopsy and subsequent pathology-imaging correlation are necessary for AD to exclude the possibility of malignancy.

Imaging Spectrum of Lobular Carcinoma In Situ and Correlation with Pathology Findings.

Background Lobular carcinoma in situ (LCIS) is a noninvasive neoplasm that is known to have an increased relative risk for developing subsequent invasive breast carcinoma. Pure LCIS is usually an incidental finding on histopathological examination (HPE) of tissue samples. However, in the recent years, there has been an increasing trend seen in the diagnosis of LCIS. Purpose This article aims to bring out the spectrum of appearances on breast imaging in confirmed cases of pure LCIS on HPE and immunohistochemical. Materials and Methods Cases that were confirmed as pure LCIS on HPE from core or excision biopsy were retrospectively analyzed for abnormalities on breast imaging. Digital breast tomosynthesis mammography was performed with high-resolution ultrasound with elastography for all cases. Magnetic resonance imaging (MRI) was performed in cases wherever indicated, with dynamic postcontrast imaging after injecting intravenous gadolinium. Conclusion LCIS is recognized as an intermediate risk factor for the development of breast cancer. Pure LCIS has varied histology and imaging patterns on mammography, high-resolution ultrasound, and MRI. It is important to recognize the imaging appearances of these lesions to enable the radiologist to detect LCIS early for proper management.