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

Abstract

PurposeTo 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 MethodsA 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.ResultsThe 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.ConclusionThe 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.

Clinical-radiomic models based on digital breast tomosynthesis images: a preliminary investigation of a predictive tool for cancer diagnosis

“…In a recently published paper (20), it was shown that the proposed radiomic model could help reduce unnecessary biopsies. In fact, especially in the presence of architectural distortion, DBT can detect some apparently benign lesions as suspicious because of its high sensitivity.…”

Machine learning and new insights for breast cancer diagnosis

“…28 This current review extracted and organized the data in tabular form and summarized the use of MG in the diagnosis of breast cancer (Table 1). 2,4,5,7,9,24,29–79…”

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

“…Xiao et al. proposed two AI methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images ( 17 ).…”

“…Rehman et al recently developed an automated computer-aided diagnostic system using computer vision and deep learning to predict breast cancer based on the architectural distortion on DM and reported great accuracy (16). Xiao et al proposed two AI methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images (17).…”