Localisation of Mammographic masses by Greedy Backtracking of Activations in the Stacked Auto-Encoders

TL;DR

This paper introduces a novel mammographic mass localisation method using maximal class activations of stacked auto-encoders, outperforming existing CNN-based techniques in accuracy and efficiency, and requiring fewer labeled images.

Contribution

The paper presents a new auto-encoder based localisation framework that improves accuracy and efficiency over CNN methods, with less dependence on large labeled datasets.

Findings

Outperforms existing CNN-based methods in salient region detection accuracy.

Requires fewer labeled images compared to deep CNN approaches.

Provides an efficient automatic localisation tool to assist clinical decision-making.

Abstract

Mammographic image analysis requires accurate localisation of salient mammographic masses. In mammographic computer-aided diagnosis, mass or Region of Interest (ROI) is often marked by physicians and features are extracted from the marked ROI. In this paper, we present a novel mammographic mass localisation framework, based on the maximal class activations of the stacked auto-encoders. We hypothesize that the image regions activating abnormal classes in mammographic images will be the breast masses which causes the anomaly. The experiment is conducted using randomly selected 200 mammographic images (100 normal and 100 abnormal) from IRMA mammographic dataset. Abnormal mass regions marked by an expert radiologist are used as the ground truth. The proposed method outperforms existing Deep Convolutional Neural Network (DCNN) based techniques in terms of salient region detection accuracy. The proposed greedy backtracking method is more efficient and does not require a vast number of labelled training images as in DCNN based method. Such automatic localisation method will assist physicians to make accurate decisions on biopsy recommendations and treatment evaluations.