Development of an MRI-Based Comprehensive Model Fusing Clinical, Habitat Radiomics, and Deep Learning Models for Preoperative Identification of Tumor Deposits in Rectal Cancer.

IF 3.5 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Xiang Li, Ying Zhu, Yaru Wei, Zhongwei Chen, Zhishan Wang, Yanyan Li, Xuebo Jin, Ziyi Chen, Jiashan Zhan, Xiaobo Chen, Meihao Wang
{"title":"Development of an MRI-Based Comprehensive Model Fusing Clinical, Habitat Radiomics, and Deep Learning Models for Preoperative Identification of Tumor Deposits in Rectal Cancer.","authors":"Xiang Li, Ying Zhu, Yaru Wei, Zhongwei Chen, Zhishan Wang, Yanyan Li, Xuebo Jin, Ziyi Chen, Jiashan Zhan, Xiaobo Chen, Meihao Wang","doi":"10.1002/jmri.70075","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Tumor deposits (TDs) are an important prognostic factor in rectal cancer. However, integrated models combining clinical, habitat radiomics, and deep learning (DL) features for preoperative TDs detection remain unexplored.</p><p><strong>Purpose: </strong>To investigate fusion models based on MRI for preoperative TDs identification and prognosis in rectal cancer.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Population: </strong>Surgically diagnosed rectal cancer patients (n = 635): training (n = 259) and internal validation (n = 112) from center 1; center 2 (n = 264) for external validation.</p><p><strong>Field strength/sequence: </strong>1.5/3T, T2-weighted image (T2WI) using fast spin echo sequence.</p><p><strong>Assessment: </strong>Four models (clinical, habitat radiomics, DL, fusion) were developed for preoperative TDs diagnosis (184 TDs positive). T2WI was segmented using nnUNet, and habitat radiomics and DL features were extracted separately. Clinical parameters were analyzed independently. The fusion model integrated selected features from all three approaches through two-stage selection. Disease-free survival (DFS) analysis was used to assess the models' prognostic performance.</p><p><strong>Statistical tests: </strong>Intraclass correlation coefficient (ICC), logistic regression, Mann-Whitney U tests, Chi-squared tests, LASSO, area under the curve (AUC), decision curve analysis (DCA), calibration curves, Kaplan-Meier analysis.</p><p><strong>Results: </strong>The AUCs for the four models ranged from 0.778 to 0.930 in the training set. In the internal validation cohort, the AUCs of clinical, habitat radiomics, DL, and fusion models were 0.785 (95% CI 0.767-0.803), 0.827 (95% CI 0.809-0.845), 0.828 (95% CI 0.815-0.841), and 0.862 (95% CI 0.828-0.896), respectively. In the external validation cohort, the corresponding AUCs were 0.711 (95% CI 0.599-0.644), 0.817 (95% CI 0.801-0.833), 0.759 (95% CI 0.743-0.773), and 0.820 (95% CI 0.770-0.860), respectively. TDs-positive patients predicted by the fusion model had significantly poorer DFS (median: 30.7 months) than TDs-negative patients (median follow-up period: 39.9 months).</p><p><strong>Data conclusion: </strong>A fusion model may identify TDs in rectal cancer and could allow to stratify DFS risk.</p><p><strong>Level of evidence: 3: </strong></p><p><strong>Technical efficacy stage: </strong>3.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.5000,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Magnetic Resonance Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/jmri.70075","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Tumor deposits (TDs) are an important prognostic factor in rectal cancer. However, integrated models combining clinical, habitat radiomics, and deep learning (DL) features for preoperative TDs detection remain unexplored.

Purpose: To investigate fusion models based on MRI for preoperative TDs identification and prognosis in rectal cancer.

Study type: Retrospective.

Population: Surgically diagnosed rectal cancer patients (n = 635): training (n = 259) and internal validation (n = 112) from center 1; center 2 (n = 264) for external validation.

Field strength/sequence: 1.5/3T, T2-weighted image (T2WI) using fast spin echo sequence.

Assessment: Four models (clinical, habitat radiomics, DL, fusion) were developed for preoperative TDs diagnosis (184 TDs positive). T2WI was segmented using nnUNet, and habitat radiomics and DL features were extracted separately. Clinical parameters were analyzed independently. The fusion model integrated selected features from all three approaches through two-stage selection. Disease-free survival (DFS) analysis was used to assess the models' prognostic performance.

Statistical tests: Intraclass correlation coefficient (ICC), logistic regression, Mann-Whitney U tests, Chi-squared tests, LASSO, area under the curve (AUC), decision curve analysis (DCA), calibration curves, Kaplan-Meier analysis.

Results: The AUCs for the four models ranged from 0.778 to 0.930 in the training set. In the internal validation cohort, the AUCs of clinical, habitat radiomics, DL, and fusion models were 0.785 (95% CI 0.767-0.803), 0.827 (95% CI 0.809-0.845), 0.828 (95% CI 0.815-0.841), and 0.862 (95% CI 0.828-0.896), respectively. In the external validation cohort, the corresponding AUCs were 0.711 (95% CI 0.599-0.644), 0.817 (95% CI 0.801-0.833), 0.759 (95% CI 0.743-0.773), and 0.820 (95% CI 0.770-0.860), respectively. TDs-positive patients predicted by the fusion model had significantly poorer DFS (median: 30.7 months) than TDs-negative patients (median follow-up period: 39.9 months).

Data conclusion: A fusion model may identify TDs in rectal cancer and could allow to stratify DFS risk.

Level of evidence: 3:

Technical efficacy stage: 3.

基于mri的综合模型的发展,融合临床、栖息地放射组学和深度学习模型,用于直肠癌肿瘤沉积物的术前识别。
背景:肿瘤沉积(TDs)是直肠癌预后的重要因素。然而,结合临床、栖息地放射组学和深度学习(DL)特征的术前TDs检测集成模型仍未被探索。目的:探讨基于MRI的融合模型在直肠癌术前TDs识别及预后中的应用价值。研究类型:回顾性。人群:手术诊断的直肠癌患者(n = 635):来自中心1的培训(n = 259)和内部验证(n = 112);中心2 (n = 264)用于外部验证。场强/序列:1.5/3T,采用快速自旋回波序列的t2加权图像(T2WI)。评估:建立了临床、栖息地放射组学、DL、融合4种模型用于术前TDs诊断(184例TDs阳性)。采用nnUNet对T2WI进行分割,分别提取栖息地放射组学和DL特征。临床参数独立分析。该融合模型通过两阶段选择将三种方法中选择的特征集成在一起。采用无病生存(DFS)分析评估模型的预后表现。统计检验:类内相关系数(ICC)、logistic回归、Mann-Whitney U检验、卡方检验、LASSO、曲线下面积(AUC)、决策曲线分析(DCA)、校准曲线、Kaplan-Meier分析。结果:4个模型在训练集中的auc在0.778 ~ 0.930之间。在内部验证队列中,临床、栖息地放射组学、DL和融合模型的auc分别为0.785 (95% CI 0.767-0.803)、0.827 (95% CI 0.809-0.845)、0.828 (95% CI 0.815-0.841)和0.862 (95% CI 0.828-0.896)。在外部验证队列中,相应的auc分别为0.711 (95% CI 0.599-0.644)、0.817 (95% CI 0.801-0.833)、0.759 (95% CI 0.743-0.773)和0.820 (95% CI 0.770-0.860)。融合模型预测的tds阳性患者的DFS(中位:30.7个月)明显低于tds阴性患者(中位随访时间:39.9个月)。数据结论:融合模型可以识别直肠癌中的TDs,并可以对DFS风险进行分层。证据等级:3;技术功效阶段:3。
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 求助全文
来源期刊
CiteScore
9.70
自引率
6.80%
发文量
494
审稿时长
2 months
期刊介绍: The Journal of Magnetic Resonance Imaging (JMRI) is an international journal devoted to the timely publication of basic and clinical research, educational and review articles, and other information related to the diagnostic applications of magnetic resonance.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信