Automatic Segmentation and Radiomics for Identification and Activity Assessment of CTE Lesions in Crohn's Disease.

IF 4.5 3区 医学 Q1 GASTROENTEROLOGY & HEPATOLOGY Inflammatory Bowel Diseases Pub Date : 2024-11-04 DOI:10.1093/ibd/izad285
Yankun Gao, Bo Zhang, Dehan Zhao, Shuai Li, Chang Rong, Mingzhai Sun, Xingwang Wu
{"title":"Automatic Segmentation and Radiomics for Identification and Activity Assessment of CTE Lesions in Crohn's Disease.","authors":"Yankun Gao, Bo Zhang, Dehan Zhao, Shuai Li, Chang Rong, Mingzhai Sun, Xingwang Wu","doi":"10.1093/ibd/izad285","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The purpose of this article is to develop a deep learning automatic segmentation model for the segmentation of Crohn's disease (CD) lesions in computed tomography enterography (CTE) images. Additionally, the radiomics features extracted from the segmented CD lesions will be analyzed and multiple machine learning classifiers will be built to distinguish CD activity.</p><p><strong>Methods: </strong>This was a retrospective study with 2 sets of CTE image data. Segmentation datasets were used to establish nnU-Net neural network's automatic segmentation model. The classification dataset was processed using the automatic segmentation model to obtain segmentation results and extract radiomics features. The most optimal features were then selected to build 5 machine learning classifiers to distinguish CD activity. The performance of the automatic segmentation model was evaluated using the Dice similarity coefficient, while the performance of the machine learning classifier was evaluated using the area under the curve, sensitivity, specificity, and accuracy.</p><p><strong>Results: </strong>The segmentation dataset had 84 CTE examinations of CD patients (mean age 31 ± 13 years, 60 males), and the classification dataset had 193 (mean age 31 ± 12 years, 136 males). The deep learning segmentation model achieved a Dice similarity coefficient of 0.824 on the testing set. The logistic regression model showed the best performance among the 5 classifiers in the testing set, with an area under the curve, sensitivity, specificity, and accuracy of 0.862, 0.697, 0.840, and 0.759, respectively.</p><p><strong>Conclusion: </strong>The automated segmentation model accurately segments CD lesions, and machine learning classifier distinguishes CD activity well. This method can assist radiologists in promptly and precisely evaluating CD activity.</p>","PeriodicalId":13623,"journal":{"name":"Inflammatory Bowel Diseases","volume":" ","pages":"1957-1964"},"PeriodicalIF":4.5000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Inflammatory Bowel Diseases","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/ibd/izad285","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: The purpose of this article is to develop a deep learning automatic segmentation model for the segmentation of Crohn's disease (CD) lesions in computed tomography enterography (CTE) images. Additionally, the radiomics features extracted from the segmented CD lesions will be analyzed and multiple machine learning classifiers will be built to distinguish CD activity.

Methods: This was a retrospective study with 2 sets of CTE image data. Segmentation datasets were used to establish nnU-Net neural network's automatic segmentation model. The classification dataset was processed using the automatic segmentation model to obtain segmentation results and extract radiomics features. The most optimal features were then selected to build 5 machine learning classifiers to distinguish CD activity. The performance of the automatic segmentation model was evaluated using the Dice similarity coefficient, while the performance of the machine learning classifier was evaluated using the area under the curve, sensitivity, specificity, and accuracy.

Results: The segmentation dataset had 84 CTE examinations of CD patients (mean age 31 ± 13 years, 60 males), and the classification dataset had 193 (mean age 31 ± 12 years, 136 males). The deep learning segmentation model achieved a Dice similarity coefficient of 0.824 on the testing set. The logistic regression model showed the best performance among the 5 classifiers in the testing set, with an area under the curve, sensitivity, specificity, and accuracy of 0.862, 0.697, 0.840, and 0.759, respectively.

Conclusion: The automated segmentation model accurately segments CD lesions, and machine learning classifier distinguishes CD activity well. This method can assist radiologists in promptly and precisely evaluating CD activity.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
自动分割和放射组学用于克罗恩病CTE病变的识别和活性评估。
背景:本文的目的是开发一种用于克罗恩病(CD) ct肠摄影(CTE)图像中病变分割的深度学习自动分割模型。此外,将分析从分割的CD病变中提取的放射组学特征,并构建多个机器学习分类器来区分CD活动。方法:采用2组CTE影像资料进行回顾性研究。利用分割数据集建立nnU-Net神经网络的自动分割模型。利用自动分割模型对分类数据集进行处理,得到分割结果并提取放射组学特征。然后选择最优特征构建5个机器学习分类器来区分CD活动。使用Dice相似系数评估自动分割模型的性能,而使用曲线下面积,灵敏度,特异性和准确性评估机器学习分类器的性能。结果:分割数据集有84例CD患者的CTE检查(平均年龄31±13岁,男性60例),分类数据集有193例(平均年龄31±12岁,男性136例)。深度学习分割模型在测试集上的Dice相似系数为0.824。logistic回归模型在测试集中5个分类器中表现最好,曲线下面积为0.862,灵敏度为0.697,特异性为0.840,准确率为0.759。结论:自动分割模型能准确分割CD病灶,机器学习分类器能很好地区分CD活动。该方法可帮助放射科医师及时准确地评估CD活动性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Inflammatory Bowel Diseases
Inflammatory Bowel Diseases 医学-胃肠肝病学
CiteScore
9.70
自引率
6.10%
发文量
462
审稿时长
1 months
期刊介绍: Inflammatory Bowel Diseases® supports the mission of the Crohn''s & Colitis Foundation by bringing the most impactful and cutting edge clinical topics and research findings related to inflammatory bowel diseases to clinicians and researchers working in IBD and related fields. The Journal is committed to publishing on innovative topics that influence the future of clinical care, treatment, and research.
期刊最新文献
Iron Deficiency Anemia in Patients with Inflammatory Bowel Disease: A Call to Action to Improve Patient Care. Long-Term Course and Prognostic Factors in Pediatric Ulcerative Proctitis: A Multicenter Cohort Study. Enhancing Gut Microbiome Research for Inflammatory Bowel Diseases Therapy: Addressing Study Limitations and Advancing Clinical Translation. Comment on: "The Burden of Psychiatric Manifestations in Inflammatory Bowel Diseases: A Systematic Review With Meta-analysis". Factors Associated With Biologic Therapy After Ileal Pouch-Anal Anastomosis in Patients With Ulcerative Colitis.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1