Logo image
Back
Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network
Conference proceeding   Open access

Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network

Delin An, Pengfei Gu, Milan Sonka, Chaoli Wang and Danny Z. Chen
Proceedings / IEEE Workshop on Applications of Computer Vision, pp.3624-3634
IEEE Winter Conference on Applications of Computer Vision
02/26/2025
DOI: 10.1109/WACV61041.2025.00357
PMCID: PMC12459605
PMID: 41001582
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC12459605/pdf/nihms-2067218.pdfView
Open Access

Abstract

Deep learning (DL) methods have shown remarkable successes in medical image segmentation, often using large amounts of annotated data for model training. However, acquiring a large number of diverse labeled 3D medical image datasets is highly difficult and expensive. Recently, mask propagation DL methods were developed to reduce the annotation burden on 3D medical images. For example, Sli2Vol [59] proposed a self-supervised framework (SSF) to learn correspondences by matching neighboring slices via slice reconstruction in the training stage; the learned correspondences were then used to propagate a labeled slice to other slices in the test stage. But, these methods are still prone to error accumulation due to the inter-slice propagation of reconstruction errors. Also, they do not handle discontinuities well, which can occur between consecutive slices in 3D images, as they emphasize exploiting object continuity. To address these challenges, in this work, we propose a new SSF, called Sli2Vol+, for segmenting any anatomical structures in 3D medical images using only a single annotated slice per training and testing volume. Specifically, in the training stage, we first propagate an annotated 2D slice of a training volume to the other slices, generating pseudo-labels (PLs). Then, we develop a novel Object Estimation Guided Correspondence Flow Network to learn reliable correspondences between consecutive slices and corresponding PLs in a self-supervised manner. In the test stage, such correspondences are utilized to propagate a single annotated slice to the other slices of a test volume. We demonstrate the effectiveness of our method on various medical image segmentation tasks with different datasets, showing better generalizability across different organs, modalities, and modals. Code is available at https://github.com/adlsn/Sli2Volplus
 Anatomical structure Biomedical imaging Computer network reliability deep learning Estimation Image reconstruction Image segmentation medical image segmentation Reliability Testing Three-dimensional displays Training

Details

Metrics

61 Record Views
2 Times Cited - Web of Science
Logo image