An Ad Hoc Random Initialization Deep Neural Network Architecture for Discriminating Malignant Breast Cancer Lesions in Mammographic Images

Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature

Background  Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. Purpose  To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods  The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. Results  A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. Conclusion  While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.

Spatially localized sparse approximations of deep features for breast mass characterization

We propose a deep feature-based sparse approximation classification technique for classification of breast masses into benign and malignant categories in film screen mammographs. This is a significant application as breast cancer is a leading cause of death in the modern world and improvements in diagnosis may help to decrease rates of mortality for large populations. While deep learning techniques have produced remarkable results in the field of computer-aided diagnosis of breast cancer, there are several aspects of this field that remain under-studied. In this work, we investigate the applicability of deep-feature-generated dictionaries to sparse approximation-based classification. To this end we construct dictionaries from deep features and compute sparse approximations of Regions Of Interest (ROIs) of breast masses for classification. Furthermore, we propose block and patch decomposition methods to construct overcomplete dictionaries suitable for sparse coding. The effectiveness of our deep feature spatially localized ensemble sparse analysis (DF-SLESA) technique is evaluated on a merged dataset of mass ROIs from the CBIS-DDSM and MIAS datasets. Experimental results indicate that dictionaries of deep features yield more discriminative sparse approximations of mass characteristics than dictionaries of imaging patterns and dictionaries learned by unsupervised machine learning techniques such as K-SVD. Of note is that the proposed block and patch decomposition strategies may help to simplify the sparse coding problem and to find tractable solutions. The proposed technique achieves competitive performances with state-of-the-art techniques for benign/malignant breast mass classification, using 10-fold cross-validation in merged datasets of film screen mammograms.

Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network

Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses.

Deep-Learning-Based Computer-Aided Systems for Breast Cancer Imaging: A Critical Review

This paper provides a critical review of the literature on deep learning applications in breast tumor diagnosis using ultrasound and mammography images. It also summarizes recent advances in computer-aided diagnosis/detection (CAD) systems, which make use of new deep learning methods to automatically recognize breast images and improve the accuracy of diagnoses made by radiologists. This review is based upon published literature in the past decade (January 2010–January 2020), where we obtained around 250 research articles, and after an eligibility process, 59 articles were presented in more detail. The main findings in the classification process revealed that new DL-CAD methods are useful and effective screening tools for breast cancer, thus reducing the need for manual feature extraction. The breast tumor research community can utilize this survey as a basis for their current and future studies.

Novel insights into breast cancer progression and metastasis: A multidisciplinary opportunity to transition from biology to clinical oncology

According to the most recent epidemiological studies, breast cancer shows the highest incidence and the second leading cause of death in women. Cancer progression and metastasis are the main events related to poor survival of breast cancer patients. This can be explained by the presence of highly resistant to chemo- and radiotherapy stem cells in many breast tumor tissues. In this context, numerous studies highlighted the possible involvement of epithelial to mesenchymal transition phenomenon as biological program to generate cancer stem cells, and thus participate to both metastatic and drug resistance process. Therefore, the comprehension of mechanisms (both cellular and molecular) involved in breast cancer occurrence and progression can lay the foundation for the development of new diagnostic and therapeutical protocols. In this review, we reported the most important findings in the field of breast cancer highlighting the most recent data concerning breast tumor biology, diagnosis and therapy.