Towards Robust Natural-Looking Mammography Lesion Synthesis on Ipsilateral Dual-Views Breast Cancer Analysis

TL;DR

This paper introduces two novel methods for mammogram analysis: enhancing the main view with auxiliary view features and synthesizing malignant images to address class imbalance, improving classification accuracy.

Contribution

It proposes simple, explainable frameworks for multi-view feature enhancement and malignant image synthesis, overcoming limitations of existing methods like CutMix.

Findings

Outperforms previous methods on VinDr-Mammo and CMMD datasets

Effective in multi-view training enhancement

Improves minority class sample synthesis

Abstract

In recent years, many mammographic image analysis methods have been introduced for improving cancer classification tasks. Two major issues of mammogram classification tasks are leveraging multi-view mammographic information and class-imbalance handling. In the first problem, many multi-view methods have been released for concatenating features of two or more views for the training and inference stage. Having said that, most multi-view existing methods are not explainable in the meaning of feature fusion, and treat many views equally for diagnosing. Our work aims to propose a simple but novel method for enhancing examined view (main view) by leveraging low-level feature information from the auxiliary view (ipsilateral view) before learning the high-level feature that contains the cancerous features. For the second issue, we also propose a simple but novel malignant mammogram synthesis framework for upsampling minor class samples. Our easy-to-implement and no-training framework has eliminated the current limitation of the CutMix algorithm which is unreliable synthesized images with random pasted patches, hard-contour problems, and domain shift problems. Our results on VinDr-Mammo and CMMD datasets show the effectiveness of our two new frameworks for both multi-view training and synthesizing mammographic images, outperforming the previous conventional methods in our experimental settings.