A bi-directional segmentation method for prostate ultrasound images under semantic constraints

Abstract Due to the lack of sufficient labeled data for the prostate and the extensive and complex semantic information in ultrasound images, accurately and quickly segmenting the prostate in transrectal ultrasound (TRUS) images remains a challenging task. In this context, this paper proposes a solu...

Full description

Saved in:
Bibliographic Details
Main Authors: Zexiang Li, Wei Du, Yongtao Shi, Wei Li, Chao Gao
Format: Article
Language:English
Published: Nature Portfolio 2024-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-61238-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121792960200704
author Zexiang Li
Wei Du
Yongtao Shi
Wei Li
Chao Gao
author_facet Zexiang Li
Wei Du
Yongtao Shi
Wei Li
Chao Gao
author_sort Zexiang Li
collection DOAJ
description Abstract Due to the lack of sufficient labeled data for the prostate and the extensive and complex semantic information in ultrasound images, accurately and quickly segmenting the prostate in transrectal ultrasound (TRUS) images remains a challenging task. In this context, this paper proposes a solution for TRUS image segmentation using an end-to-end bidirectional semantic constraint method, namely the BiSeC model. The experimental results show that compared with classic or popular deep learning methods, this method has better segmentation performance, with the Dice Similarity Coefficient (DSC) of 96.74% and the Intersection over Union (IoU) of 93.71%. Our model achieves a good balance between actual boundaries and noise areas, reducing costs while ensuring the accuracy and speed of segmentation.
format Article
id doaj-art-671e6e16eff941f3abb28733faeea5b3
institution Kabale University
issn 2045-2322
language English
publishDate 2024-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-671e6e16eff941f3abb28733faeea5b32024-12-15T12:08:50ZengNature PortfolioScientific Reports2045-23222024-05-0114111810.1038/s41598-024-61238-5A bi-directional segmentation method for prostate ultrasound images under semantic constraintsZexiang Li0Wei Du1Yongtao Shi2Wei Li3Chao Gao4College of Electrical Engineering and New Energy, China Three Gorges UniversityCollege of Computer and Information Technology, China Three Gorges UniversityCollege of Computer and Information Technology, China Three Gorges UniversityCollege of Computer and Information Technology, China Three Gorges UniversityCollege of Computer and Information Technology, China Three Gorges UniversityAbstract Due to the lack of sufficient labeled data for the prostate and the extensive and complex semantic information in ultrasound images, accurately and quickly segmenting the prostate in transrectal ultrasound (TRUS) images remains a challenging task. In this context, this paper proposes a solution for TRUS image segmentation using an end-to-end bidirectional semantic constraint method, namely the BiSeC model. The experimental results show that compared with classic or popular deep learning methods, this method has better segmentation performance, with the Dice Similarity Coefficient (DSC) of 96.74% and the Intersection over Union (IoU) of 93.71%. Our model achieves a good balance between actual boundaries and noise areas, reducing costs while ensuring the accuracy and speed of segmentation.https://doi.org/10.1038/s41598-024-61238-5
spellingShingle Zexiang Li
Wei Du
Yongtao Shi
Wei Li
Chao Gao
A bi-directional segmentation method for prostate ultrasound images under semantic constraints
Scientific Reports
title A bi-directional segmentation method for prostate ultrasound images under semantic constraints
title_full A bi-directional segmentation method for prostate ultrasound images under semantic constraints
title_fullStr A bi-directional segmentation method for prostate ultrasound images under semantic constraints
title_full_unstemmed A bi-directional segmentation method for prostate ultrasound images under semantic constraints
title_short A bi-directional segmentation method for prostate ultrasound images under semantic constraints
title_sort bi directional segmentation method for prostate ultrasound images under semantic constraints
url https://doi.org/10.1038/s41598-024-61238-5
work_keys_str_mv AT zexiangli abidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT weidu abidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT yongtaoshi abidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT weili abidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT chaogao abidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT zexiangli bidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT weidu bidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT yongtaoshi bidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT weili bidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints
AT chaogao bidirectionalsegmentationmethodforprostateultrasoundimagesundersemanticconstraints