中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中国科学院分子影像重点实验室
Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study

文献类型：期刊论文

作者Feng, Lili1,14; Liu, Zhenyu13; Li, Chaofeng12; Li, Zhenhui10; Lou, Xiaoying17; Shao, Lizhi9,13; Wang, Yunlong1,14; Huang, Yan17; Chen, Haiyang1; Pang, Xiaolin1
刊名LANCET DIGITAL HEALTH
出版日期2022
卷号4期号:1页码:E8-E17
通讯作者Tian, Jie(jie.tian@ia.ac.cn) ; Wan, Xiangbo(wanxbo@mail.sysu.edu.cn)
英文摘要Background Accurate prediction of tumour response to neoadjuvant chemoradiotherapy enables personalised perioperative therapy for locally advanced rectal cancer. We aimed to develop and validate an artificial intelligence radiopathomics integrated model to predict pathological complete response in patients with locally advanced rectal cancer using pretreatment MRI and haematoxylin and eosin (H&E)-stained biopsy slides. Methods In this multicentre observational study, eligible participants who had undergone neoadjuvant chemoradiotherapy followed by radical surgery were recruited, with their pretreatment pelvic MRI (T2-weighted imaging, contrast-enhanced T1-weighted imaging, and diffusion-weighted imaging) and whole slide images of H&E-stained biopsy sections collected for annotation and feature extraction. The RAdioPathomics Integrated preDiction System (RAPIDS) was constructed by machine learning on the basis of three feature sets associated with pathological complete response: radiomics MRI features, pathomics nucleus features, and pathomics microenvironment features from a retrospective training cohort. The accuracy of RAPIDS for the prediction of pathological complete response in locally advanced rectal cancer was verified in two retrospective external validation cohorts and further validated in a multicentre, prospective observational study (ClinicalTrials.gov, NCT04271657). Model performances were evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Findings Between Sept 25, 2009, and Nov 3, 2017, 303 patients were retrospectively recruited in the training cohort, 480 in validation cohort 1, and 150 in validation cohort 2; 100 eligible patients were enrolled in the prospective study between Jan 10 and June 10, 2020. RAPIDS had favourable accuracy for the prediction of pathological complete response in the training cohort (AUC 0.868 [95% CI 0.825-0.912]), and in validation cohort 1 (0.860 [0.828-0.892]) and validation cohort 2 (0.872 [0.810-0.934]). In the prospective validation study, RAPIDS had an AUC of 0.812 (95% CI 0-717-0.907), sensitivity of 0.888 (0.728-0.999), specificity of 0.740 (0.593-0.886), NPV of 0.929 (0.862-0.995), and PPV of 0.512 (0.313-0.710). RAPIDS also significantly outperformed single-modality prediction models (AUC 0.630 [0.507-0.754] for the pathomics microenvironment model, 0.716 [0.580-0-852] for the radiomics MRI model, and 0.733 [0.620-0.845] for the pathomics nucleus model; all p<0.0001). Interpretation RAPIDS was able to predict pathological complete response to neoadjuvant chemoradiotherapy based on pretreatment radiopathomics images with high accuracy and robustness and could therefore provide a novel tool to assist in individualised management of locally advanced rectal cancer. Copyright (C) 2021 The Author(s). Published by Elsevier Ltd.
WOS关键词ARTIFICIAL-INTELLIGENCE ; RADIOMICS ; IMAGES
资助项目National Natural Science Foundation of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
WOS研究方向Medical Informatics ; General & Internal Medicine
语种英语
出版者ELSEVIER
WOS记录号WOS:000736243900006
资助机构National Natural Science Foundation of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/47103]  
专题自动化研究所_中国科学院分子影像重点实验室
通讯作者Tian, Jie; Wan, Xiangbo
作者单位1.Sun Yat Sen Univ, Affiliated Hosp 6, Dept Radiat Oncol, Guangzhou 510000, Peoples R China
2.Univ Michigan, Canc Ctr, Ann Arbor, MI 48109 USA
3.Univ Michigan, Dept Radiat Oncol, Ann Arbor, MI 48109 USA
4.Asia Univ, Dept Biotechnol, Taichung, Taiwan
5.China Med Univ, Res Ctr Canc Biol & Mol Med, Taichung, Taiwan
6.China Med Univ, Grad Inst Biomed Sci, Taichung, Taiwan
7.Univ Texas MD Anderson Canc Ctr, Dept Mol & Cellular Oncol, Houston, TX 77030 USA
8.Southern Med Univ, Nanfang Hosp, Dept Radiat Oncol, Guangzhou, Peoples R China
9.Southeast Univ, Sch Comp Sci & Engn, Nanjing, Peoples R China
10.Kunming Med Univ, Yunnan Canc Hosp, Dept Radiol, Affiliated Hosp 3, Kunming, Yunnan, Peoples R China
推荐引用方式
GB/T 7714		 Feng, Lili,Liu, Zhenyu,Li, Chaofeng,et al. Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study[J]. LANCET DIGITAL HEALTH,2022,4(1):E8-E17.
APA Feng, Lili.,Liu, Zhenyu.,Li, Chaofeng.,Li, Zhenhui.,Lou, Xiaoying.,...&Wan, Xiangbo.(2022).Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study.LANCET DIGITAL HEALTH,4(1),E8-E17.
MLA Feng, Lili,et al."Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicentre observational study".LANCET DIGITAL HEALTH 4.1(2022):E8-E17.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。