Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism

Conclusion: A multiscale feature pyramid network effectively reduces the semantic gap, and the bidirectional cross-attention mechanism facilitates feature alignment between the encoding and decoding stages.

Saved in:
Bibliographic Details
Main Authors: Yu Xiao, Xin Yang, Sijuan Huang, Lihua Guo
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:International Journal of Biomedical Imaging
Online Access:http://dx.doi.org/10.1155/ijbi/7560099
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706639364456448
author Yu Xiao
Xin Yang
Sijuan Huang
Lihua Guo
author_facet Yu Xiao
Xin Yang
Sijuan Huang
Lihua Guo
author_sort Yu Xiao
collection DOAJ
description Conclusion: A multiscale feature pyramid network effectively reduces the semantic gap, and the bidirectional cross-attention mechanism facilitates feature alignment between the encoding and decoding stages.
format Article
id doaj-art-006acb1b985644d2978466b7fbdbe662
institution DOAJ
issn 1687-4196
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series International Journal of Biomedical Imaging
spelling doaj-art-006acb1b985644d2978466b7fbdbe6622025-08-20T03:16:08ZengWileyInternational Journal of Biomedical Imaging1687-41962025-01-01202510.1155/ijbi/7560099Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention MechanismYu Xiao0Xin Yang1Sijuan Huang2Lihua Guo3School of Electronic and Information EngineeringState Key Laboratory of Oncology in South ChinaState Key Laboratory of Oncology in South ChinaSchool of Electronic and Information EngineeringConclusion: A multiscale feature pyramid network effectively reduces the semantic gap, and the bidirectional cross-attention mechanism facilitates feature alignment between the encoding and decoding stages.http://dx.doi.org/10.1155/ijbi/7560099
spellingShingle Yu Xiao
Xin Yang
Sijuan Huang
Lihua Guo
Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
International Journal of Biomedical Imaging
title Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
title_full Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
title_fullStr Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
title_full_unstemmed Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
title_short Enhancing Deep Learning–Based Subabdominal MR Image Segmentation During Rectal Cancer Treatment: Exploiting Multiscale Feature Pyramid Network and Bidirectional Cross-Attention Mechanism
title_sort enhancing deep learning based subabdominal mr image segmentation during rectal cancer treatment exploiting multiscale feature pyramid network and bidirectional cross attention mechanism
url http://dx.doi.org/10.1155/ijbi/7560099
work_keys_str_mv AT yuxiao enhancingdeeplearningbasedsubabdominalmrimagesegmentationduringrectalcancertreatmentexploitingmultiscalefeaturepyramidnetworkandbidirectionalcrossattentionmechanism
AT xinyang enhancingdeeplearningbasedsubabdominalmrimagesegmentationduringrectalcancertreatmentexploitingmultiscalefeaturepyramidnetworkandbidirectionalcrossattentionmechanism
AT sijuanhuang enhancingdeeplearningbasedsubabdominalmrimagesegmentationduringrectalcancertreatmentexploitingmultiscalefeaturepyramidnetworkandbidirectionalcrossattentionmechanism
AT lihuaguo enhancingdeeplearningbasedsubabdominalmrimagesegmentationduringrectalcancertreatmentexploitingmultiscalefeaturepyramidnetworkandbidirectionalcrossattentionmechanism