Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer

TL;DR

This paper introduces a transfer learning framework that leverages mass breast ultrasound data to improve non-mass lesion classification, addressing data scarcity and domain shift issues with domain alignment and data generation techniques.

Contribution

The study proposes a novel transfer learning approach with domain alignment and CrossMix data generation to enhance non-mass breast ultrasound cancer classification.

Findings

10% improvement in AUC for non-mass lesion malignancy prediction

Effective domain adaptation between mass and non-mass ultrasound data

Enhanced generalizability of DNN models for non-mass breast ultrasound

Abstract

Much progress has been made in the deep neural network (DNN) based diagnosis of mass lesions breast ultrasound (BUS) images. However, the non-mass lesion is less investigated because of the limited data. Based on the insight that mass data is sufficient and shares the same knowledge structure with non-mass data of identifying the malignancy of a lesion based on the ultrasound image, we propose a novel transfer learning framework to enhance the generalizability of the DNN model for non-mass BUS with the help of mass BUS. Specifically, we train a shared DNN with combined non-mass and mass data. With the prior of different marginal distributions in input and output space, we employ two domain alignment strategies in the proposed transfer learning framework with the insight of capturing domain-specific distribution to address the issue of domain shift. Moreover, we propose a cross-domain semantic-preserve data generation module called CrossMix to recover the missing distribution between non-mass and mass data that is not presented in training data. Experimental results on an in-house dataset demonstrate that the DNN model trained with combined data by our framework achieves a 10% improvement in AUC on the malignancy prediction task of non-mass BUS compared to training directly on non-mass data.