# Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

Source: [Recurrent Mask Refinement for Few-Shot Medical Image Segmentation](<https://www.sota2.com/research/paper/68fa6a7c1e209131cea288bb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:26:28.956Z

Authors: Hao Tang, Xingwei Liu, Shanlin Sun, Xiangyi Yan, Xiaohui Xie

Published: 2021-08-02T04:06:12.000Z

## Abstract

Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot learning has the potential to address these challenges by learning new classes from only a few labeled examples. In this work, we propose a new framework for few-shot medical image segmentation based on prototypical networks. Our innovation lies in the design of two key modules: 1) a context relation encoder (CRE) that uses correlation to capture local relation features between foreground and background regions; and 2) a recurrent mask refinement module that repeatedly uses the CRE and a prototypical network to recapture the change of context relationship and refine the segmentation mask iteratively. Experiments on two abdomen CT datasets and an abdomen MRI dataset show the proposed method obtains substantial improvement over the state-of-the-art methods by an average of 16.32%, 8.45% and 6.24% in terms of DSC, respectively. Code is publicly available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Few-Shot 3D Volumetric Segmentation on Abdomen-CT Setting 2](<https://www.sota2.com/research/sota/few-shot-3d-volumetric-segmentation-on-abdomen-ct-setting-2.md>): Few-Shot 3D Volumetric Segmentation; Abdomen-CT Setting 2; Dice (LK): 65.14.

- [Few-Shot 3D Volumetric Segmentation on CHAOS-MRI Setting 2](<https://www.sota2.com/research/sota/few-shot-3d-volumetric-segmentation-on-chaos-mri-setting-2.md>): Few-Shot 3D Volumetric Segmentation; CHAOS-MRI Setting 2; Dice (Kidney L): 71.46.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.00622>)

[PDF](<https://arxiv.org/pdf/2108.00622.pdf>)