Differential-UMamba: Rethinking Tumor Segmentation Under Limited Data Scenarios

TL;DR

Diff-UMamba is a novel medical image segmentation architecture that enhances performance in limited data scenarios by combining long-range dependency modeling with noise reduction techniques.

Contribution

The paper introduces Diff-UMamba, a new architecture integrating UNet with a mamba mechanism and noise reduction for improved low-data medical segmentation.

Findings

Achieves 1-3% accuracy improvements on public datasets.

Demonstrates 4-5% improvement on lung tumor segmentation.

Performs robustly across multiple datasets and limited data conditions.

Abstract

In data-scarce scenarios, deep learning models often overfit to noise and irrelevant patterns, which limits their ability to generalize to unseen samples. To address these challenges in medical image segmentation, we introduce Diff-UMamba, a novel architecture that combines the UNet framework with the mamba mechanism to model long-range dependencies. At the heart of Diff-UMamba is a noise reduction module, which employs a signal differencing strategy to suppress noisy or irrelevant activations within the encoder. This encourages the model to filter out spurious features and enhance task-relevant representations, thereby improving its focus on clinically significant regions. As a result, the architecture achieves improved segmentation accuracy and robustness, particularly in low-data settings. Diff-UMamba is evaluated on multiple public datasets, including medical segmentation decathalon dataset (lung and pancreas) and AIIB23, demonstrating consistent performance gains of 1-3% over baseline methods in various segmentation tasks. To further assess performance under limited data conditions, additional experiments are conducted on the BraTS-21 dataset by varying the proportion of available training samples. The approach is also validated on a small internal non-small cell lung cancer dataset for the segmentation of gross tumor volume in cone beam CT, where it achieves a 4-5% improvement over baseline.