Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network

Abstract Objective To create a deep‐learning automatic segmentation model for esophageal cancer (EC), metastatic lymph nodes (MLNs) and their adjacent structures using the UperNet Swin network and computed tomography angiography (CTA) images and to improve the effectiveness and precision of EC autom...

Full description

Saved in:
Bibliographic Details
Main Authors: Runyuan Wang, Xingcai Chen, Xiaoqin Zhang, Ping He, Jinfeng Ma, Huilin Cui, Ximei Cao, Yongjian Nian, Ximing Xu, Wei Wu, Yi Wu
Format: Article
Language:English
Published: Wiley 2024-09-01
Series:Cancer Medicine
Subjects:
Online Access:https://doi.org/10.1002/cam4.70188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849716362371399680
author Runyuan Wang
Xingcai Chen
Xiaoqin Zhang
Ping He
Jinfeng Ma
Huilin Cui
Ximei Cao
Yongjian Nian
Ximing Xu
Wei Wu
Yi Wu
author_facet Runyuan Wang
Xingcai Chen
Xiaoqin Zhang
Ping He
Jinfeng Ma
Huilin Cui
Ximei Cao
Yongjian Nian
Ximing Xu
Wei Wu
Yi Wu
author_sort Runyuan Wang
collection DOAJ
description Abstract Objective To create a deep‐learning automatic segmentation model for esophageal cancer (EC), metastatic lymph nodes (MLNs) and their adjacent structures using the UperNet Swin network and computed tomography angiography (CTA) images and to improve the effectiveness and precision of EC automatic segmentation and TN stage diagnosis. Methods Attention U‐Net, UperNet Swin, UNet++ and UNet were used to train the EC segmentation model to automatically segment the EC, esophagus, pericardium, aorta and MLN from CTA images of 182 patients with postoperative pathologically proven EC. The Dice similarity coefficient (DSC), sensitivity, and positive predictive value (PPV) were used to assess their segmentation effectiveness. The volume of EC was calculated using the segmentation results, and the outcomes and times of automatic and human segmentation were compared. All statistical analyses were completed using SPSS 25.0 software. Results Among the four EC autosegmentation models, the UperNet Swin had the best autosegmentation results with a DSC of 0.7820 and the highest values of EC sensitivity and PPV. The esophagus, pericardium, aorta and MLN had DSCs of 0.7298, 0.9664, 0.9496 and 0.5091. The DSCs of the UperNet Swin were 0.6164, 0.7842, 0.8190, and 0.7259 for T1‐4 EC. The volume of EC and its adjacent structures between the ground truth and UperNet Swin model were not significantly different. Conclusions The UperNet Swin showed excellent efficiency in autosegmentation and volume measurement of EC, MLN and its adjacent structures in different T stage, which can help to T and N stage diagnose EC and will save clinicians time and energy.
format Article
id doaj-art-128807c0ec4d4b88bc39b356ced28a3b
institution DOAJ
issn 2045-7634
language English
publishDate 2024-09-01
publisher Wiley
record_format Article
series Cancer Medicine
spelling doaj-art-128807c0ec4d4b88bc39b356ced28a3b2025-08-20T03:13:01ZengWileyCancer Medicine2045-76342024-09-011318n/an/a10.1002/cam4.70188Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin networkRunyuan Wang0Xingcai Chen1Xiaoqin Zhang2Ping He3Jinfeng Ma4Huilin Cui5Ximei Cao6Yongjian Nian7Ximing Xu8Wei Wu9Yi Wu10Department of Digital Medicine, College of Biomedical Engineering and Medical Imaging Army Medical University (Third Military Medical University) Chongqing ChinaDepartment of Digital Medicine, College of Biomedical Engineering and Medical Imaging Army Medical University (Third Military Medical University) Chongqing ChinaDepartment of Digital Medicine, College of Biomedical Engineering and Medical Imaging Army Medical University (Third Military Medical University) Chongqing ChinaDepartment of Cardiac Surgery, Southwest Hospital Army Medical University (Third Military Medical University) Chongqing ChinaDepartment of General Surgery Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences/Cancer Hospital Affiliated to Shanxi Medical University Taiyuan ChinaDepartment of Histology and Embryology Shanxi Medical University Taiyuan ChinaDepartment of Histology and Embryology Shanxi Medical University Taiyuan ChinaDepartment of Digital Medicine, College of Biomedical Engineering and Medical Imaging Army Medical University (Third Military Medical University) Chongqing ChinaMinistry of Education Key Laboratory of Child Development and Disorders, National Clinical Research Center for Child Health and Disorders Children's Hospital of Chongqing Medical University Chongqing ChinaDepartment of Thoracic Surgery, Southwest Hospital Army Medical University (Third Military Medical University) Chongqing ChinaDepartment of Digital Medicine, College of Biomedical Engineering and Medical Imaging Army Medical University (Third Military Medical University) Chongqing ChinaAbstract Objective To create a deep‐learning automatic segmentation model for esophageal cancer (EC), metastatic lymph nodes (MLNs) and their adjacent structures using the UperNet Swin network and computed tomography angiography (CTA) images and to improve the effectiveness and precision of EC automatic segmentation and TN stage diagnosis. Methods Attention U‐Net, UperNet Swin, UNet++ and UNet were used to train the EC segmentation model to automatically segment the EC, esophagus, pericardium, aorta and MLN from CTA images of 182 patients with postoperative pathologically proven EC. The Dice similarity coefficient (DSC), sensitivity, and positive predictive value (PPV) were used to assess their segmentation effectiveness. The volume of EC was calculated using the segmentation results, and the outcomes and times of automatic and human segmentation were compared. All statistical analyses were completed using SPSS 25.0 software. Results Among the four EC autosegmentation models, the UperNet Swin had the best autosegmentation results with a DSC of 0.7820 and the highest values of EC sensitivity and PPV. The esophagus, pericardium, aorta and MLN had DSCs of 0.7298, 0.9664, 0.9496 and 0.5091. The DSCs of the UperNet Swin were 0.6164, 0.7842, 0.8190, and 0.7259 for T1‐4 EC. The volume of EC and its adjacent structures between the ground truth and UperNet Swin model were not significantly different. Conclusions The UperNet Swin showed excellent efficiency in autosegmentation and volume measurement of EC, MLN and its adjacent structures in different T stage, which can help to T and N stage diagnose EC and will save clinicians time and energy.https://doi.org/10.1002/cam4.701883D reconstructionautomatic segmentationcomputed tomography angiography (CTA)deep learningesophageal cancer
spellingShingle Runyuan Wang
Xingcai Chen
Xiaoqin Zhang
Ping He
Jinfeng Ma
Huilin Cui
Ximei Cao
Yongjian Nian
Ximing Xu
Wei Wu
Yi Wu
Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
Cancer Medicine
3D reconstruction
automatic segmentation
computed tomography angiography (CTA)
deep learning
esophageal cancer
title Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
title_full Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
title_fullStr Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
title_full_unstemmed Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
title_short Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
title_sort automatic segmentation of esophageal cancer metastatic lymph nodes and their adjacent structures in cta images based on the upernet swin network
topic 3D reconstruction
automatic segmentation
computed tomography angiography (CTA)
deep learning
esophageal cancer
url https://doi.org/10.1002/cam4.70188
work_keys_str_mv AT runyuanwang automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT xingcaichen automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT xiaoqinzhang automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT pinghe automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT jinfengma automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT huilincui automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT ximeicao automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT yongjiannian automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT ximingxu automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT weiwu automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork
AT yiwu automaticsegmentationofesophagealcancermetastaticlymphnodesandtheiradjacentstructuresinctaimagesbasedontheupernetswinnetwork