SIFT-DBT: Self-supervised Initialization and Fine-Tuning for Imbalanced Digital Breast Tomosynthesis Image Classification

TL;DR

This paper introduces SIFT-DBT, a self-supervised learning approach with multi-instance learning to improve classification of imbalanced digital breast tomosynthesis images, achieving high accuracy.

Contribution

It proposes a novel self-supervised initialization and fine-tuning method combined with patch-level multi-instance learning for DBT image classification.

Findings

Achieved 92.69% volume-wise AUC on 970 studies.

Effectively addresses data imbalance in DBT classification.

Outperforms existing methods in accuracy.

Abstract

Digital Breast Tomosynthesis (DBT) is a widely used medical imaging modality for breast cancer screening and diagnosis, offering higher spatial resolution and greater detail through its 3D-like breast volume imaging capability. However, the increased data volume also introduces pronounced data imbalance challenges, where only a small fraction of the volume contains suspicious tissue. This further exacerbates the data imbalance due to the case-level distribution in real-world data and leads to learning a trivial classification model that only predicts the majority class. To address this, we propose a novel method using view-level contrastive Self-supervised Initialization and Fine-Tuning for identifying abnormal DBT images, namely SIFT-DBT. We further introduce a patch-level multi-instance learning method to preserve spatial resolution. The proposed method achieves 92.69% volume-wise AUC on an evaluation of 970 unique studies.