Clinical application of convolutional neural network for mass analysis on mammograms.

Background: The detection of masses on mammogram represents one of the earliest signs of a malignant breast cancer. However, masses may be hard to detect due to dense breast tissue, leading to false negative results. In this study, we aimed to explore the clinical application of the convolutional neural network (CNN)-based deep learning (DL) system constructed in our previous work as an objective and accurate tool for breast cancer screening and diagnosis in Asian women. Methods: This retrospective analysis included 324 patients with masses detected on mammograms at Shenzhen People's Hospital between April and December 2019. (I) Detection: images were independently analyzed by two junior radiologists who were blinded to relative results. Then, a senior radiologist analyzed the images after reviewing all the relevant information as the reference. (II) Classification: masses were classified by the same two junior radiologists and in consensus by two other seniors. Images were also input into the DL system. The sensitivity of detection by junior radiologists and the DL system, effects of different factors [breast density; patient age; morphology, margin, size, breast imaging reporting and data system (BI-RADS) category of the mass] on detection, the accuracy, sensitivity, and specificity of classification, and the area under the receiver operating characteristic (ROC) curve (AUC), were evaluated. Results: A total of 618 masses were detected. The detection sensitivity of the two junior radiologists [78.0% (482/618) and 84.0% (519/618), respectively] was lower than that of the DL system [86.2% (533/618)]. Breast density significantly affected the detection by two junior radiologists (both P=0.030), but not by the DL system (P=0.385). The AUC for classifying masses as negative (BI-RADS 1, 2, 3) or positive (BI-RADS 4A, 4B, 4C, 5) for the DL system was significantly higher compared to those of the two junior radiologists, but not significantly different compared to seniors [DL system, 0.697; junior, 0.612 and 0.620 (P=0.021, 0.019); senior in consensus, 0.748 (P=0.071)]. Conclusions: The CNN-based DL system could assist junior radiologists in improving mass detection and is not affected by breast density. This DL system may have clinical utility in women with dense breasts, including reducing the impact caused by inexperienced radiologists and the potential for missed diagnoses.

Classification of asymmetry in mammography via the DenseNet convolutional neural network.

Purpose: To investigate the effectiveness of a deep learning system based on the DenseNet convolutional neural network in diagnosing benign and malignant asymmetric lesions in mammography. Methods: Clinical and image data from 460 women aged 23-82 years (47.57 ± 8.73 years) with asymmetric lesions who underwent mammography at Shenzhen People's Hospital, Shenzhen Luohu District People's Hospital, and Shenzhen Hospital of Peking University from December 2019 to December 2020 were retrospectively analyzed. Two senior radiologists, two junior radiologists, and the DL system read the mammographic images of 460 patients, respectively, and finally recorded the BI-RADS classification of asymmetric lesions. We then used the area under the curve (AUC) of the receiver operating characteristic (ROC) to evaluate the diagnostic efficacy and the difference between AUCs by the Delong method. Results: Specificity (0.909 vs. 0.835, 0.790, χ2=8.21 and 17.22, p＜0.05) and precision (0.872 vs. 0.763, 0.726, χ2=9.23 and 5.22, p＜0.05) of the DL system in the diagnosis of benign and malignant asymmetric lesions were higher than those of junior radiologist A and B, and there was a statistically significant difference between AUCs (0.778 vs. 0.579, 0.564, Z = 4.033 and 4.460, p＜0.05). Furthermore, the AUC (0.778 vs. 0.904, 0.862, Z = 3.191, and 2.167, p＜0.05) of benign and malignant asymmetric lesions diagnosed by the DL system was lower than that of senior radiologist A and senior radiologist B. Conclusions: The DL system based on the DenseNet convolution neural network has high diagnostic efficiency, which can help junior radiologists evaluate benign and malignant asymmetric lesions more accurately. It can also improve diagnostic accuracy and reduce missed diagnoses caused by inexperienced junior radiologists.

Automatic mammographic breast density classification in Chinese women: clinical validation of a deep learning model.

BACKGROUND: High breast density is a strong risk factor for breast cancer. As such, high consistency and accuracy in breast density assessment is necessary. PURPOSE: To validate our proposed deep learning (DL) model and explore its impact on radiologists on density assessments. MATERIAL AND METHODS: A total of 3732 mammographic cases were collected as a validated set: 1686 cases before the implementation of the DL model and 2046 cases after the DL model. Five radiologists were divided into two groups (junior and senior groups) to assess all mammograms using either two- or four-category evaluation. Linear-weighted kappa (K) and intraclass correlation coefficient (ICC) statistics were used to analyze the consistency between radiologists before and after implementation of the DL model. RESULTS: The accuracy and clinical acceptance of the DL model for the junior group were 96.3% and 96.8% for two-category evaluation, and 85.6% and 89.6% for four-category evaluation, respectively. For the senior group, the accuracy and clinical acceptance were 95.5% and 98.0% for two-category evaluation, and 84.3% and 95.3% for four-category evaluation, respectively. The consistency within the junior group, the senior group, and among all radiologists improved with the help of the DL model. For two-category, their K and ICC values improved to 0.81, 0.81, and 0.80 from 0.73, 0.75, and 0.76. And for four-category, their K and ICC values improved to 0.81, 0.82, and 0.82 from 0.73, 0.79, and 0.78, respectively. CONCLUSION: The DL model showed high accuracy and clinical acceptance in breast density categories. It is helpful to improve radiologists' consistency.

The added value of an artificial intelligence system in assisting radiologists on indeterminate BI-RADS 0 mammograms.

OBJECTIVES: To investigate the value of an artificial intelligence (AI) system in assisting radiologists to improve the assessment accuracy of BI-RADS 0 cases in mammograms. METHODS: We included 34,654 consecutive digital mammography studies, collected between January 2011 and January 2019, among which, 1088 cases from 1010 unique patients with initial BI-RADS 0 assessment who were recalled during 2 years of follow-up were used in this study. Two mid-level radiologists retrospectively re-assessed these BI-RADS 0 cases with the assistance of an AI system developed by us previously. In addition, four entry-level radiologists were split into two groups to cross-read 80 cases with and without the AI. Diagnostic performance was evaluated using the follow-up diagnosis or biopsy results as the reference standard. RESULTS: Of the 1088 cases, 626 were actually normal (BI-RADS 1 and no recall required). Assisted by the AI system, 351 (56%) and 362 (58%) normal cases were correctly identified by the two mid-level radiologists hence can be avoided for unnecessary follow-ups. However, they would have missed 12 (10 invasive cancers and 2 ductal carcinoma in situ cancers) and 6 (invasive cancers) malignant lesions respectively as a result. These missed lesions were not highly malignant tumors. The inter-rater reliability of entry-level radiologists increased from 0.20 to 0.30 (p < 0.005) by introducing the AI. CONCLUSION: The AI system can effectively assist mid-level radiologists in reducing unnecessary follow-ups of mammographically indeterminate breast lesions and reducing the benign biopsy rate without missing highly malignant tumors. KEY POINTS: • The artificial intelligence system could assist mid-level radiologists in effectively reducing unnecessary BI-RADS 0 mammogram recalls and the benign biopsy rate without missing highly malignant tumors. • The artificial intelligence system was capable of detecting low suspicion lesions from heterogeneously and extremely dense breasts that radiologists tended to miss. • The use of an artificial intelligence system may improve the inter-rater reliability and sensitivity, and reduce the reading time of entry-level radiologists in assessing potential lesions in BI-RADS 0 mammograms.

MommiNet-v2: Mammographic multi-view mass identification networks.

Many existing approaches for mammogram analysis are based on single view. Some recent DNN-based multi-view approaches can perform either bilateral or ipsilateral analysis, while in practice, radiologists use both to achieve the best clinical outcome. MommiNet is the first DNN-based tri-view mass identification approach, which can simultaneously perform bilateral and ipsilateral analysis of mammographic images, and in turn, can fully emulate the radiologists' reading practice. In this paper, we present MommiNet-v2, with improved network architecture and performance. Novel high-resolution network (HRNet)-based architectures are proposed to learn the symmetry and geometry constraints, to fully aggregate the information from all views for accurate mass detection. A multi-task learning scheme is adopted to incorporate both Breast Imaging-Reporting and Data System (BI-RADS) and biopsy information to train a mass malignancy classification network. Extensive experiments have been conducted on the public DDSM (Digital Database for Screening Mammography) dataset and our in-house dataset, and state-of-the-art results have been achieved in terms of mass detection accuracy. Satisfactory mass malignancy classification result has also been obtained on our in-house dataset.