Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications

TL;DR

This paper introduces a discriminative cross-modal data augmentation method for medical imaging that enhances model training by translating images between modalities, addressing data scarcity issues.

Contribution

It proposes a novel unpaired image-to-image translation model guided by prediction tasks, improving data augmentation in medical imaging.

Findings

Effective in two medical imaging applications

Improves model performance with limited data

Guided translation enhances augmentation quality

Abstract

While deep learning methods have shown great success in medical image analysis, they require a number of medical images to train. Due to data privacy concerns and unavailability of medical annotators, it is oftentimes very difficult to obtain a lot of labeled medical images for model training. In this paper, we study cross-modality data augmentation to mitigate the data deficiency issue in the medical imaging domain. We propose a discriminative unpaired image-to-image translation model which translates images in source modality into images in target modality where the translation task is conducted jointly with the downstream prediction task and the translation is guided by the prediction. Experiments on two applications demonstrate the effectiveness of our method.