Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning Method

TL;DR

This paper proposes a modified supervised contrastive learning approach that improves breast cancer histopathology image classification accuracy by addressing false positives and negatives, especially effective with limited data.

Contribution

It introduces a two-stage supervised contrastive learning method with a modified loss and a relaxing mechanism to enhance model robustness and accuracy.

Findings

Achieved 93.63% classification accuracy on BreakHis dataset.

Improved accuracy by 1.45% over state-of-the-art methods.

Enhanced model robustness with limited data.

Abstract

Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical vulnerability, often succumbing to overfitting by excessively memorizing the limited information available. This work addresses the challenge mentioned above by improving the supervised contrastive learning method leveraging both image-level labels and domain-specific augmentations to enhance model robustness. This approach integrates self-supervised pre-training with a two-stage supervised contrastive learning strategy. In the first stage, we employ a modified supervised contrastive loss that not only focuses on reducing false negatives but also introduces an elimination effect to address false positives. In the second stage, a relaxing mechanism is introduced that refines positive and negative pairs based on similarity, ensuring that only relevant image representations are aligned. We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images, and demonstrate an increase in classification accuracy by 1.45% in the image level, compared to the state-of-the-art method. This improvement corresponds to 93.63% absolute accuracy, highlighting the effectiveness of our approach in leveraging properties of data to learn more appropriate representation space.