Query Nearby: Offset-Adjusted Mask2Former enhances small-organ segmentation

TL;DR

This paper introduces Offset-Adjusted Mask2Former, a novel method that improves small-organ segmentation in medical images by integrating offset adjustment strategies and auxiliary training to achieve state-of-the-art results.

Contribution

It proposes offset adjustment strategies and auxiliary training techniques to enhance Mask2Former for better small-organ segmentation in medical images.

Findings

Achieves state-of-the-art performance on HaNSeg and SegRap2023 datasets.

Significantly improves segmentation accuracy for mid-sized and small organs.

Reduces computational complexity while maintaining high accuracy.

Abstract

Medical segmentation plays an important role in clinical applications like radiation therapy and surgical guidance, but acquiring clinically acceptable results is difficult. In recent years, progress has been witnessed with the success of utilizing transformer-like models, such as combining the attention mechanism with CNN. In particular, transformer-based segmentation models can extract global information more effectively, compensating for the drawbacks of CNN modules that focus on local features. However, utilizing transformer architecture is not easy, because training transformer-based models can be resource-demanding. Moreover, due to the distinct characteristics in the medical field, especially when encountering mid-sized and small organs with compact regions, their results often seem unsatisfactory. For example, using ViT to segment medical images directly only gives a DSC of less than 50\%, which is far lower than the clinically acceptable score of 80\%. In this paper, we used Mask2Former with deformable attention to reduce computation and proposed offset adjustment strategies to encourage sampling points within the same organs during attention weights computation, thereby integrating compact foreground information better. Additionally, we utilized the 4th feature map in Mask2Former to provide a coarse location of organs, and employed an FCN-based auxiliary head to help train Mask2Former more quickly using Dice loss. We show that our model achieves SOTA (State-of-the-Art) performance on the HaNSeg and SegRap2023 datasets, especially on mid-sized and small organs.Our code is available at link https://github.com/earis/Offsetadjustment\_Background-location\_Decoder\_Mask2former.