Contextual Features and Information Bottleneck-Based Multi-Input Network for Breast Cancer Classification from Contrast-Enhanced Spectral Mammography

Abstract

In computer-aided diagnosis methods for breast cancer, deep learning has been shown to be an effective method to distinguish whether lesions are present in tissues. However, traditional methods only classify masses as benign or malignant, according to their presence or absence, without considering the contextual features between them and their adjacent tissues. Furthermore, for contrast-enhanced spectral mammography, the existing studies have only performed feature extraction on a single image per breast. In this paper, we propose a multi-input deep learning network for automatic breast cancer classification. Specifically, we simultaneously input four images of each breast with different feature information into the network. Then, we processed the feature maps in both horizontal and vertical directions, preserving the pixel-level contextual information within the neighborhood of the tumor during the pooling operation. Furthermore, we designed a novel loss function according to the information bottleneck theory to optimize our multi-input network and ensure that the common information in the multiple input images could be fully utilized. Our experiments on 488 images (256 benign and 232 malignant images) from 122 patients show that the method’s accuracy, precision, sensitivity, specificity, and f1-score values are 0.8806, 0.8803, 0.8810, 0.8801, and 0.8806, respectively. The qualitative, quantitative, and ablation experiment results show that our method significantly improves the accuracy of breast cancer classification and reduces the false positive rate of diagnosis. It can reduce misdiagnosis rates and unnecessary biopsies, helping doctors determine accurate clinical diagnoses of breast cancer from multiple CESM images.

Deep Learning for Contrast Enhanced Mammography - a Systematic Review

“…Two studies that assessed the combination of an attention mechanism with CNN (33, 34). First, Li et al (33) incorporated a CNN algorithm with attention for CEM images classification.…”

“…Two studies that assessed the combination of an attention mechanism with CNN (33, 34). First, Li et al (33) incorporated a CNN algorithm with attention for CEM images classification. Their network extracts information from all four images acquired for each breast (low energy and subtracted contrast images).…”

“…Two studies that assessed the combination of an attention mechanism with CNN (33,34). They have also compared the best model performance to that of a radiomics model, as well as to radiologists.…”

AI-Based Cancer Detection Model for Contrast-Enhanced Mammography

“…Without manual extraction of the region of interest, DL-based breast classification has been recently studied in the literature. Li et al developed a DL architecture with attention mechanism to classify a breast malignancy using all available views of the patient exam [ 22 ]. This study was developed from 122 patients.…”

BIM Product Style Classification and Retrieval Based on Long-Range Style Dependencies

“…Deep learning models make solid contributions to image feature representation. Many studies [34][35][36] adopt deep learning, e.g., VGG-16 [37], as the feature extractor in image classification and regression tasks. However, the mainstream deep models are Visual saliency computation has been widely applied in many studies to locate and recognize the areas that draw the most prominent visual attention [31][32][33].…”