Survival analysis of clear cell renal cell carcinoma based on radiomics and deep learning features from CT images.

IF 1.3 4区 医学 Q2 MEDICINE, GENERAL & INTERNAL
Zhennan Lu, Sijia Wu, Dan Ni, Meng Zhou, Tao Wang, Xiaobo Zhou, Liyu Huang, Yu Yan
{"title":"Survival analysis of clear cell renal cell carcinoma based on radiomics and deep learning features from CT images.","authors":"Zhennan Lu, Sijia Wu, Dan Ni, Meng Zhou, Tao Wang, Xiaobo Zhou, Liyu Huang, Yu Yan","doi":"10.1097/MD.0000000000040723","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To create a nomogram for accurate prognosis of patients with clear cell renal cell carcinoma (ccRCC) based on computed tomography images.</p><p><strong>Methods: </strong>Eight hundred twenty-two ccRCC patients with contrast-enhanced computed tomography images involved in this study were collected. A rectangular region of interest surrounding the tumor was used to extract quantitative radiomics and deep-learning features, which were filtered by Cox proportional hazard regression model and least absolute shrinkage and selection operator. Then the selected features formed a fusion signature, which was assessed by Cox proportional hazard regression model method, Kaplan-Meier analysis, receiver operating characteristic curves, and concordance index (C-index) in different clinical subgroups. Finally, a nomogram constructed with this signature and clinicopathologic risk factors was assessed by C-index and survival calibration curves.</p><p><strong>Results: </strong>The fusion signature performed better than the radiomics signature. Then we combined this signature and 2 clinicopathologic risk factors. This nomogram showed an increase of about 20% in C-index values when compared to clinical nomogram in both datasets. Its prediction probability was also in good agreement with the actual ratio.</p><p><strong>Conclusion: </strong>The proposed fusion nomogram provided a noninvasive and easy-to-use model for survival prognosis of ccRCC patients in future clinical use, without the requirement to perform a detailed segmentation for radiologists.</p>","PeriodicalId":18549,"journal":{"name":"Medicine","volume":"103 51","pages":"e40723"},"PeriodicalIF":1.3000,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11666162/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/MD.0000000000040723","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To create a nomogram for accurate prognosis of patients with clear cell renal cell carcinoma (ccRCC) based on computed tomography images.

Methods: Eight hundred twenty-two ccRCC patients with contrast-enhanced computed tomography images involved in this study were collected. A rectangular region of interest surrounding the tumor was used to extract quantitative radiomics and deep-learning features, which were filtered by Cox proportional hazard regression model and least absolute shrinkage and selection operator. Then the selected features formed a fusion signature, which was assessed by Cox proportional hazard regression model method, Kaplan-Meier analysis, receiver operating characteristic curves, and concordance index (C-index) in different clinical subgroups. Finally, a nomogram constructed with this signature and clinicopathologic risk factors was assessed by C-index and survival calibration curves.

Results: The fusion signature performed better than the radiomics signature. Then we combined this signature and 2 clinicopathologic risk factors. This nomogram showed an increase of about 20% in C-index values when compared to clinical nomogram in both datasets. Its prediction probability was also in good agreement with the actual ratio.

Conclusion: The proposed fusion nomogram provided a noninvasive and easy-to-use model for survival prognosis of ccRCC patients in future clinical use, without the requirement to perform a detailed segmentation for radiologists.

基于CT影像放射组学和深度学习特征的透明细胞肾细胞癌生存分析。
目的:建立透明细胞肾细胞癌(ccRCC) ct影像准确预后的影像学图。方法:本研究收集822例ccRCC患者的ct增强图像。使用肿瘤周围的矩形感兴趣区域提取定量放射组学和深度学习特征,并通过Cox比例风险回归模型和最小绝对收缩和选择算子进行过滤。选取的特征形成融合特征,采用Cox比例风险回归模型法、Kaplan-Meier分析、受试者工作特征曲线和不同临床亚组的一致性指数(C-index)进行评价。最后,通过c -指数和生存校准曲线对该特征和临床病理危险因素构建的nomogram进行评估。结果:融合特征优于放射组学特征。然后我们把这个特征和两个临床病理危险因素结合起来。与两个数据集的临床nomogram相比,该nomogram显示c -指数值增加了约20%。其预测概率也与实际比值吻合较好。结论:本文提出的融合图为今后临床使用的ccRCC患者的生存预后提供了一种无创且易于使用的模型,无需放射科医生进行详细的分割。
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
Medicine
Medicine 医学-医学:内科
CiteScore
2.80
自引率
0.00%
发文量
4342
审稿时长
>12 weeks
期刊介绍: Medicine is now a fully open access journal, providing authors with a distinctive new service offering continuous publication of original research across a broad spectrum of medical scientific disciplines and sub-specialties. As an open access title, Medicine will continue to provide authors with an established, trusted platform for the publication of their work. To ensure the ongoing quality of Medicine’s content, the peer-review process will only accept content that is scientifically, technically and ethically sound, and in compliance with standard reporting guidelines.
×
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:481959085
Book学术官方微信