Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding

About

Medical image segmentation plays a critical role in clinical decision-making, treatment planning, and disease monitoring. However, accurate segmentation of medical images is challenging due to several factors, such as the lack of high-quality annotation, imaging noise, and anatomical differences across patients. In addition, there is still a considerable gap in performance between the existing label-efficient methods and fully-supervised methods. To address the above challenges, we propose ScribbleVC, a novel framework for scribble-supervised medical image segmentation that leverages vision and class embeddings via the multimodal information enhancement mechanism. In addition, ScribbleVC uniformly utilizes the CNN features and Transformer features to achieve better visual feature extraction. The proposed method combines a scribble-based approach with a segmentation network and a class-embedding module to produce accurate segmentation masks. We evaluate ScribbleVC on three benchmark datasets and compare it with state-of-the-art methods. The experimental results demonstrate that our method outperforms existing approaches in terms of accuracy, robustness, and efficiency. The datasets and code are released on GitHub.

Zihan Li, Yuan Zheng, Xiangde Luo, Dandan Shan, Qingqi Hong• 2023

Related benchmarks

TaskDatasetResultRank
Medical Image SegmentationACDC (test)
Avg DSC88.4
135
Medical Image SegmentationMSCMRseg 25 scribbles
LV Segmentation Score92.1
10
Medical Image SegmentationNCI-ISBI (Prostate)
PZ0.743
9
Medical Image SegmentationMSCMRseg
LV Segmentation Score92.1
6
Scribble-supervised cardiac segmentationACDC (test)
LV Segmentation Score91.4
6
Medical Image SegmentationMSCMRseg 25 masks--
5
Showing 6 of 6 rows

Other info

Code

Follow for update