Segmenting Medical Images with Limited Data

TL;DR

This paper introduces DEMS, a semi-supervised, consistency-based medical image segmentation method that effectively handles limited data by using novel augmentation, robustness blocks, and a sensitive loss, outperforming existing methods.

Contribution

The paper proposes a new data-efficient segmentation approach with innovative augmentation and robustness techniques tailored for small datasets in medical imaging.

Findings

DEMS outperforms U-Net and state-of-the-art methods under data scarcity.

Achieves 16.85% and 10.37% improvements in dice score.

Effective in small data regimes for medical segmentation.

Abstract

While computer vision has proven valuable for medical image segmentation, its application faces challenges such as limited dataset sizes and the complexity of effectively leveraging unlabeled images. To address these challenges, we present a novel semi-supervised, consistency-based approach termed the data-efficient medical segmenter (DEMS). The DEMS features an encoder-decoder architecture and incorporates the developed online automatic augmenter (OAA) and residual robustness enhancement (RRE) blocks. The OAA augments input data with various image transformations, thereby diversifying the dataset to improve the generalization ability. The RRE enriches feature diversity and introduces perturbations to create varied inputs for different decoders, thereby providing enhanced variability. Moreover, we introduce a sensitive loss to further enhance consistency across different decoders and stabilize the training process. Extensive experimental results on both our own and three public datasets affirm the effectiveness of DEMS. Under extreme data shortage scenarios, our DEMS achieves 16.85\% and 10.37\% improvement in dice score compared with the U-Net and top-performed state-of-the-art method, respectively. Given its superior data efficiency, DEMS could present significant advancements in medical segmentation under small data regimes. The project homepage can be accessed at https://github.com/NUS-Tim/DEMS.