Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis

TL;DR

This paper introduces a multi-task deep learning framework for breast ultrasound diagnosis that leverages lesion recognition through contrastive learning, improving classification accuracy by capturing view-invariant and fine-grained lesion features.

Contribution

It proposes a novel multi-task framework combining lesion recognition with classification, utilizing contrastive learning to better model multiple views of the same lesion.

Findings

Boosts classification performance with multi-task learning.

Leverages contrastive learning for view-invariant lesion features.

Enhances lesion representation by capturing fine-grained details.

Abstract

Previous deep learning based Computer Aided Diagnosis (CAD) system treats multiple views of the same lesion as independent images. Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the semantic relationship between different views of a lesion, which is inconsistent with the traditional diagnosis where sonographers analyze a lesion from at least two views. In this paper, we propose a multi-task framework that complements Benign/Malignant classification task with lesion recognition (LR) which helps leveraging relationship among multiple views of a single lesion to learn a complete representation of the lesion. To be specific, LR task employs contrastive learning to encourage representation that pulls multiple views of the same lesion and repels those of different lesions. The task therefore facilitates a representation that is not only invariant to the view change of the lesion, but also capturing fine-grained features to distinguish between different lesions. Experiments show that the proposed multi-task framework boosts the performance of Benign/Malignant classification as two sub-tasks complement each other and enhance the learned representation of ultrasound images.