Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation

TL;DR

This paper introduces a task-driven data augmentation method optimized for medical image segmentation, effectively improving accuracy with limited labeled data by modeling intensity and shape variations in a semi-supervised framework.

Contribution

It proposes a novel semi-supervised data augmentation technique that models intensity and shape variations, optimized specifically for segmentation tasks with limited annotations.

Findings

Significantly outperforms standard augmentation methods.

Effective on multiple medical datasets: cardiac, prostate, pancreas.

Demonstrates the benefit of task-driven augmentation in limited data scenarios.

Abstract

Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large number of annotated samples from experts is time-consuming and expensive. Consequently, numerous methods have been proposed in the literature for learning with limited annotated examples. Unfortunately, the proposed approaches in the literature have not yet yielded significant gains over random data augmentation for image segmentation, where random augmentations themselves do not yield high accuracy. In this work, we propose a novel task-driven data augmentation method for learning with limited labeled data where the synthetic data generator, is optimized for the segmentation task. The generator of the proposed method models intensity and shape variations using two sets of transformations, as additive intensity transformations and deformation fields. Both transformations are optimized using labeled as well as unlabeled examples in a semi-supervised framework. Our experiments on three medical datasets, namely cardic, prostate and pancreas, show that the proposed approach significantly outperforms standard augmentation and semi-supervised approaches for image segmentation in the limited annotation setting. The code is made publicly available at https://github.com/krishnabits001/task$\_$driven$\_$data$\_$augmentation.