G-SET-DCL: a guided sequential episodic training with dual contrastive learning approach for colon segmentation.

Journal: International journal of computer assisted radiology and surgery

PMID: 39789205

Abstract

PURPOSE: This article introduces a novel deep learning approach to substantially improve the accuracy of colon segmentation even with limited data annotation, which enhances the overall effectiveness of the CT colonography pipeline in clinical settings.

Authors

Samir Farag Harb

Computer Vision and Image Processing Lab., UofL, Louisville, KY, 40292, USA. samir.farag@louisville.edu.
Asem Ali

Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville, KY, 40292, USA.
Mohamed Yousuf

Computer Vision and Image Processing Lab., UofL, Louisville, KY, 40292, USA.
Salwa Elshazly

Kentucky Imaging Technologies, LLC., Louisville, KY, USA.
Aly Farag

Computer Vision and Image Processing Lab., UofL, Louisville, KY, 40292, USA.

Keywords

Algorithms Colon Colonic Polyps Colonography, Computed Tomographic Deep Learning Humans Imaging, Three-Dimensional Radiographic Image Interpretation, Computer-Assisted Reproducibility of Results

External Resources

View on PubMed Access via DOI PubMed (39789205)

G-SET-DCL: a guided sequential episodic training with dual contrastive learning approach for colon segmentation.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals