Cosine Additive Angular Margin Loss for Breast Cancer Classification in Histopathological Images with Small AI Systems

Abstract

Breast cancer claims thousands of lives annually, emphasizing the need for swift and accurate histopathology image classification to expedite diagnoses. Despite the rapid evolution of Convolutional Neural Networks (CNNs), the conventional softmax loss lacks the robustness required to discern intricate features in breast cancer classification from histopathological images. In response, our study introduces the Cosine Additive Angular Margin Loss (CAAM) to address this limitation and achieve both enhanced intra-class cohesion and distinct inter-class boundaries concurrently. By normalizing weight and feature vectors, we eliminate radial variations before imposing angular and cosine margin constraints on the softmax angle space. This process maximizes the decision margin, resulting in a discriminative feature embedding. Extensive experiments conducted on the BreakHis dataset demonstrate that CAAM consistently outperforms existing methods in breast cancer histopathological image classification. Our findings underscore the efficacy of angular margin-based softmax losses in bolstering the performance of advanced CNN models for breast cancer classification.