SimTxtSeg: Weakly-Supervised Medical Image Segmentation with Simple Text Cues

TL;DR

SimTxtSeg introduces a novel weakly-supervised medical image segmentation framework that uses simple text cues to generate pseudo-labels and fuse cross-modal information, achieving state-of-the-art results.

Contribution

The paper proposes a new framework with a Textual-to-Visual Cue Converter and Text-Vision Hybrid Attention for improved weakly-supervised segmentation.

Findings

Achieves state-of-the-art performance on colonic polyp segmentation.

Achieves state-of-the-art performance on MRI brain tumor segmentation.

Effectively leverages text cues for high-quality pseudo-label generation.

Abstract

Weakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance. In this paper, we present a novel framework, SimTxtSeg, that leverages simple text cues to generate high-quality pseudo-labels and study the cross-modal fusion in training segmentation models, simultaneously. Our contribution consists of two key components: an effective Textual-to-Visual Cue Converter that produces visual prompts from text prompts on medical images, and a text-guided segmentation model with Text-Vision Hybrid Attention that fuses text and image features. We evaluate our framework on two medical image segmentation tasks: colonic polyp segmentation and MRI brain tumor segmentation, and achieve consistent state-of-the-art performance. Source code is available at: https://github.com/xyx1024/SimTxtSeg.