Exploring Regions of Interest: Visualizing Histological Image Classification for Breast Cancer using Deep Learning

TL;DR

This paper investigates visualization techniques for CNN-based breast cancer histological image classification, aiming to interpret model decisions by highlighting regions of interest and comparing them with pathologist annotations.

Contribution

It evaluates and compares different visualization and pixel selection methods to improve interpretability of deep learning models in breast cancer diagnosis.

Findings

Gradient visualization with MeanShift best highlights relevant regions.

The study demonstrates the potential of visualization methods to justify CNN decisions.

Results support using specific visualization techniques for better interpretability.

Abstract

Computer aided detection and diagnosis systems based on deep learning have shown promising performance in breast cancer detection. However, there are cases where the obtained results lack justification. In this study, our objective is to highlight the regions of interest used by a convolutional neural network (CNN) for classifying histological images as benign or malignant. We compare these regions with the regions identified by pathologists. To achieve this, we employed the VGG19 architecture and tested three visualization methods: Gradient, LRP Z, and LRP Epsilon. Additionally, we experimented with three pixel selection methods: Bins, K-means, and MeanShift. Based on the results obtained, the Gradient visualization method and the MeanShift selection method yielded satisfactory outcomes for visualizing the images.