Cycle Context Verification for In-Context Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Shishuai, Liao, Zehui, Zhen, Liangli, Fu, Huazhu, Xia, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911050659528704
author Hu, Shishuai
Liao, Zehui
Zhen, Liangli
Fu, Huazhu
Xia, Yong
author_facet Hu, Shishuai
Liao, Zehui
Zhen, Liangli
Fu, Huazhu
Xia, Yong
contents In-context learning (ICL) is emerging as a promising technique for achieving universal medical image segmentation, where a variety of objects of interest across imaging modalities can be segmented using a single model. Nevertheless, its performance is highly sensitive to the alignment between the query image and in-context image-mask pairs. In a clinical scenario, the scarcity of annotated medical images makes it challenging to select optimal in-context pairs, and fine-tuning foundation ICL models on contextual data is infeasible due to computational costs and the risk of catastrophic forgetting. To address this challenge, we propose Cycle Context Verification (CCV), a novel framework that enhances ICL-based medical image segmentation by enabling self-verification of predictions and accordingly enhancing contextual alignment. Specifically, CCV employs a cyclic pipeline in which the model initially generates a segmentation mask for the query image. Subsequently, the roles of the query and an in-context pair are swapped, allowing the model to validate its prediction by predicting the mask of the original in-context image. The accuracy of this secondary prediction serves as an implicit measure of the initial query segmentation. A query-specific prompt is introduced to alter the query image and updated to improve the measure, thereby enhancing the alignment between the query and in-context pairs. We evaluated CCV on seven medical image segmentation datasets using two ICL foundation models, demonstrating its superiority over existing methods. Our results highlight CCV's ability to enhance ICL-based segmentation, making it a robust solution for universal medical image segmentation. The code will be available at https://github.com/ShishuaiHu/CCV.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08357
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cycle Context Verification for In-Context Medical Image Segmentation
Hu, Shishuai
Liao, Zehui
Zhen, Liangli
Fu, Huazhu
Xia, Yong
Computer Vision and Pattern Recognition
In-context learning (ICL) is emerging as a promising technique for achieving universal medical image segmentation, where a variety of objects of interest across imaging modalities can be segmented using a single model. Nevertheless, its performance is highly sensitive to the alignment between the query image and in-context image-mask pairs. In a clinical scenario, the scarcity of annotated medical images makes it challenging to select optimal in-context pairs, and fine-tuning foundation ICL models on contextual data is infeasible due to computational costs and the risk of catastrophic forgetting. To address this challenge, we propose Cycle Context Verification (CCV), a novel framework that enhances ICL-based medical image segmentation by enabling self-verification of predictions and accordingly enhancing contextual alignment. Specifically, CCV employs a cyclic pipeline in which the model initially generates a segmentation mask for the query image. Subsequently, the roles of the query and an in-context pair are swapped, allowing the model to validate its prediction by predicting the mask of the original in-context image. The accuracy of this secondary prediction serves as an implicit measure of the initial query segmentation. A query-specific prompt is introduced to alter the query image and updated to improve the measure, thereby enhancing the alignment between the query and in-context pairs. We evaluated CCV on seven medical image segmentation datasets using two ICL foundation models, demonstrating its superiority over existing methods. Our results highlight CCV's ability to enhance ICL-based segmentation, making it a robust solution for universal medical image segmentation. The code will be available at https://github.com/ShishuaiHu/CCV.
title Cycle Context Verification for In-Context Medical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.08357