多维深度集成学习模型预测食管癌新辅助放化疗的病理反应和预后:一项多中心研究。

IF 5.3 1区 医学 Q1 ONCOLOGY
Yunsong Liu , Yang Su , Jun Peng , Wencheng Zhang , Fangdong Zhao , Yue Li , Xinyun Song , Zeliang Ma , Wanting Zhang , Jianrui Ji , Ye Chen , Yu Men , Feng Ye , Kuo Men , Jianjun Qin , Wenyang Liu , Xin Wang , Nan Bi , Liyan Xue , Wen Yu , Zhouguang Hui
{"title":"多维深度集成学习模型预测食管癌新辅助放化疗的病理反应和预后:一项多中心研究。","authors":"Yunsong Liu ,&nbsp;Yang Su ,&nbsp;Jun Peng ,&nbsp;Wencheng Zhang ,&nbsp;Fangdong Zhao ,&nbsp;Yue Li ,&nbsp;Xinyun Song ,&nbsp;Zeliang Ma ,&nbsp;Wanting Zhang ,&nbsp;Jianrui Ji ,&nbsp;Ye Chen ,&nbsp;Yu Men ,&nbsp;Feng Ye ,&nbsp;Kuo Men ,&nbsp;Jianjun Qin ,&nbsp;Wenyang Liu ,&nbsp;Xin Wang ,&nbsp;Nan Bi ,&nbsp;Liyan Xue ,&nbsp;Wen Yu ,&nbsp;Zhouguang Hui","doi":"10.1016/j.radonc.2025.111133","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>Neoadjuvant chemoradiotherapy (nCRT) followed by esophagectomy remains standard for locally advanced esophageal squamous cell carcinoma (ESCC). However, accurately predicting pathological complete response (pCR) and treatment outcomes remains challenging. This study aimed to develop and validate a multidimensional deep ensemble learning model (DELRN) using pretreatment CT imaging to predict pCR and stratify prognostic risk in ESCC patients undergoing nCRT.</div></div><div><h3>Methods</h3><div>In this multicenter, retrospective cohort study, 485 ESCC patients were enrolled from four hospitals (May 2009–August 2023, December 2017–September 2021, May 2014–September 2019, and March 2013–July 2019). Patients were divided into a discovery cohort (n = 194), an internal cohort (n = 49), and three external validation cohorts (n = 242). A multidimensional deep ensemble learning model (DELRN) integrating radiomics and 3D convolutional neural networks was developed based on pretreatment CT images to predict pCR and clinical outcomes. The model’s performance was evaluated by discrimination, calibration, and clinical utility. Kaplan-Meier analysis assessed overall survival (OS) and disease-free survival (DFS) at two follow-up centers.</div></div><div><h3>Results</h3><div>The DELRN model demonstrated robust predictive performance for pCR across the discovery, internal, and external validation cohorts, with area under the curve (AUC) values of 0.943 (95 % CI: 0.912–0.973), 0.796 (95 % CI: 0.661–0.930), 0.767 (95 % CI: 0.646–0.887), 0.829 (95 % CI: 0.715–0.942), and 0.782 (95 % CI: 0.664–0.900), respectively, surpassing single-domain radiomics or deep learning models. DELRN effectively stratified patients into high-risk and low-risk groups for OS (log-rank P = 0.018 and 0.0053) and DFS (log-rank P = 0.00042 and 0.035). Multivariate analysis confirmed DELRN as an independent prognostic factor for OS and DFS.</div></div><div><h3>Conclusion</h3><div>The DELRN model demonstrated promising clinical potential as an effective, non-invasive tool for predicting nCRT response and treatment outcome in ESCC patients, enabling personalized treatment strategies and improving clinical decision-making with future prospective multicenter validation.</div></div>","PeriodicalId":21041,"journal":{"name":"Radiotherapy and Oncology","volume":"212 ","pages":"Article 111133"},"PeriodicalIF":5.3000,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A multidimensional deep ensemble learning model predicts pathological response and outcomes in esophageal squamous cell carcinoma treated with neoadjuvant chemoradiotherapy from pretreatment CT imaging: A multicenter study\",\"authors\":\"Yunsong Liu ,&nbsp;Yang Su ,&nbsp;Jun Peng ,&nbsp;Wencheng Zhang ,&nbsp;Fangdong Zhao ,&nbsp;Yue Li ,&nbsp;Xinyun Song ,&nbsp;Zeliang Ma ,&nbsp;Wanting Zhang ,&nbsp;Jianrui Ji ,&nbsp;Ye Chen ,&nbsp;Yu Men ,&nbsp;Feng Ye ,&nbsp;Kuo Men ,&nbsp;Jianjun Qin ,&nbsp;Wenyang Liu ,&nbsp;Xin Wang ,&nbsp;Nan Bi ,&nbsp;Liyan Xue ,&nbsp;Wen Yu ,&nbsp;Zhouguang Hui\",\"doi\":\"10.1016/j.radonc.2025.111133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Purpose</h3><div>Neoadjuvant chemoradiotherapy (nCRT) followed by esophagectomy remains standard for locally advanced esophageal squamous cell carcinoma (ESCC). However, accurately predicting pathological complete response (pCR) and treatment outcomes remains challenging. This study aimed to develop and validate a multidimensional deep ensemble learning model (DELRN) using pretreatment CT imaging to predict pCR and stratify prognostic risk in ESCC patients undergoing nCRT.</div></div><div><h3>Methods</h3><div>In this multicenter, retrospective cohort study, 485 ESCC patients were enrolled from four hospitals (May 2009–August 2023, December 2017–September 2021, May 2014–September 2019, and March 2013–July 2019). Patients were divided into a discovery cohort (n = 194), an internal cohort (n = 49), and three external validation cohorts (n = 242). A multidimensional deep ensemble learning model (DELRN) integrating radiomics and 3D convolutional neural networks was developed based on pretreatment CT images to predict pCR and clinical outcomes. The model’s performance was evaluated by discrimination, calibration, and clinical utility. Kaplan-Meier analysis assessed overall survival (OS) and disease-free survival (DFS) at two follow-up centers.</div></div><div><h3>Results</h3><div>The DELRN model demonstrated robust predictive performance for pCR across the discovery, internal, and external validation cohorts, with area under the curve (AUC) values of 0.943 (95 % CI: 0.912–0.973), 0.796 (95 % CI: 0.661–0.930), 0.767 (95 % CI: 0.646–0.887), 0.829 (95 % CI: 0.715–0.942), and 0.782 (95 % CI: 0.664–0.900), respectively, surpassing single-domain radiomics or deep learning models. DELRN effectively stratified patients into high-risk and low-risk groups for OS (log-rank P = 0.018 and 0.0053) and DFS (log-rank P = 0.00042 and 0.035). Multivariate analysis confirmed DELRN as an independent prognostic factor for OS and DFS.</div></div><div><h3>Conclusion</h3><div>The DELRN model demonstrated promising clinical potential as an effective, non-invasive tool for predicting nCRT response and treatment outcome in ESCC patients, enabling personalized treatment strategies and improving clinical decision-making with future prospective multicenter validation.</div></div>\",\"PeriodicalId\":21041,\"journal\":{\"name\":\"Radiotherapy and Oncology\",\"volume\":\"212 \",\"pages\":\"Article 111133\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2025-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiotherapy and Oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167814025046377\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiotherapy and Oncology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167814025046377","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:新辅助放化疗(nCRT)后食管切除术仍然是局部晚期食管鳞状细胞癌(ESCC)的标准治疗方法。然而,准确预测病理完全缓解(pCR)和治疗结果仍然具有挑战性。本研究旨在开发并验证一种多维深度集成学习模型(DELRN),该模型使用预处理CT成像来预测ESCC患者接受nCRT的pCR和预后风险分层。方法:在这项多中心、回顾性队列研究中,从4家医院(2009年5月- 2023年8月、2017年12月- 2021年9月、2014年5月- 2019年9月和2013年3月- 2019年7月)招募了485例ESCC患者。患者被分为发现队列(n = 194)、内部队列(n = 49)和三个外部验证队列(n = 242)。结合放射组学和三维卷积神经网络,建立了基于预处理CT图像的多维深度集成学习模型(DELRN),用于预测pCR和临床结果。通过区分、校准和临床应用来评估模型的性能。Kaplan-Meier分析评估了两个随访中心的总生存期(OS)和无病生存期(DFS)。结果:DELRN模型在发现、内部和外部验证队列中显示出稳健的pCR预测性能,曲线下面积(AUC)值分别为0.943(95 % CI: 0.912-0.973)、0.796(95 % CI: 0.661-0.930)、0.767(95 % CI: 0.646-0.887)、0.829(95 % CI: 0.715-0.942)和0.782(95 % CI: 0.664-0.900),超过了单域放射组学或深度学习模型。DELRN有效地将患者分为OS (log-rank P = 0.018和0.0053)和DFS (log-rank P = 0.00042和0.035)的高危和低危组。多因素分析证实DELRN是OS和DFS的独立预后因素。结论:DELRN模型具有良好的临床潜力,可作为预测ESCC患者nCRT反应和治疗结果的有效、无创工具,实现个性化治疗策略,改善临床决策,并具有未来前瞻性多中心验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A multidimensional deep ensemble learning model predicts pathological response and outcomes in esophageal squamous cell carcinoma treated with neoadjuvant chemoradiotherapy from pretreatment CT imaging: A multicenter study

Purpose

Neoadjuvant chemoradiotherapy (nCRT) followed by esophagectomy remains standard for locally advanced esophageal squamous cell carcinoma (ESCC). However, accurately predicting pathological complete response (pCR) and treatment outcomes remains challenging. This study aimed to develop and validate a multidimensional deep ensemble learning model (DELRN) using pretreatment CT imaging to predict pCR and stratify prognostic risk in ESCC patients undergoing nCRT.

Methods

In this multicenter, retrospective cohort study, 485 ESCC patients were enrolled from four hospitals (May 2009–August 2023, December 2017–September 2021, May 2014–September 2019, and March 2013–July 2019). Patients were divided into a discovery cohort (n = 194), an internal cohort (n = 49), and three external validation cohorts (n = 242). A multidimensional deep ensemble learning model (DELRN) integrating radiomics and 3D convolutional neural networks was developed based on pretreatment CT images to predict pCR and clinical outcomes. The model’s performance was evaluated by discrimination, calibration, and clinical utility. Kaplan-Meier analysis assessed overall survival (OS) and disease-free survival (DFS) at two follow-up centers.

Results

The DELRN model demonstrated robust predictive performance for pCR across the discovery, internal, and external validation cohorts, with area under the curve (AUC) values of 0.943 (95 % CI: 0.912–0.973), 0.796 (95 % CI: 0.661–0.930), 0.767 (95 % CI: 0.646–0.887), 0.829 (95 % CI: 0.715–0.942), and 0.782 (95 % CI: 0.664–0.900), respectively, surpassing single-domain radiomics or deep learning models. DELRN effectively stratified patients into high-risk and low-risk groups for OS (log-rank P = 0.018 and 0.0053) and DFS (log-rank P = 0.00042 and 0.035). Multivariate analysis confirmed DELRN as an independent prognostic factor for OS and DFS.

Conclusion

The DELRN model demonstrated promising clinical potential as an effective, non-invasive tool for predicting nCRT response and treatment outcome in ESCC patients, enabling personalized treatment strategies and improving clinical decision-making with future prospective multicenter validation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Radiotherapy and Oncology
Radiotherapy and Oncology 医学-核医学
CiteScore
10.30
自引率
10.50%
发文量
2445
审稿时长
45 days
期刊介绍: Radiotherapy and Oncology publishes papers describing original research as well as review articles. It covers areas of interest relating to radiation oncology. This includes: clinical radiotherapy, combined modality treatment, translational studies, epidemiological outcomes, imaging, dosimetry, and radiation therapy planning, experimental work in radiobiology, chemobiology, hyperthermia and tumour biology, as well as data science in radiation oncology and physics aspects relevant to oncology.Papers on more general aspects of interest to the radiation oncologist including chemotherapy, surgery and immunology are also published.
×
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