基于光谱 CT 多参数图像的临床放射组学提名图,用于术前预测结直肠癌淋巴结转移。

IF 4.2 3区 医学 Q2 ONCOLOGY
Clinical & Experimental Metastasis Pub Date : 2024-10-01 Epub Date: 2024-05-20 DOI:10.1007/s10585-024-10293-3
Qian Li, Rui Hong, Ping Zhang, Liting Hou, Hailun Bao, Lin Bai, Jian Zhao
{"title":"基于光谱 CT 多参数图像的临床放射组学提名图,用于术前预测结直肠癌淋巴结转移。","authors":"Qian Li, Rui Hong, Ping Zhang, Liting Hou, Hailun Bao, Lin Bai, Jian Zhao","doi":"10.1007/s10585-024-10293-3","DOIUrl":null,"url":null,"abstract":"<p><p>To develop a clinical-radiomics nomogram based on spectral CT multi-parameter images for predicting lymph node metastasis in colorectal cancer. A total of 76 patients with colorectal cancer and 156 lymph nodes were included. The clinical data of the patients were collected, including gender, age, tumor location and size, preoperative tumor markers, etc. Three sets of conventional images in the arterial, venous, and delayed phases were obtained, and six sets of spectral images were reconstructed using the arterial phase spectral data, including virtual monoenergetic images (40 keV, 70 keV, 100 keV), iodine density maps, iodine no water maps, and virtual non-contrast images. Radiomics features of lymph nodes were extracted from the above images, respectively. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select features. A clinical model was constructed based on age and carcinoembryonic antigen (CEA) levels. The radiomics features selected were used to generate a composed radiomics signature (Com-RS). A nomogram was developed using age, CEA, and the Com-RS. The models' prediction efficiency, calibration, and clinical application value were evaluated by the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis, respectively. The nomogram outperforms the clinical model and the Com-RS (AUC = 0.879, 0.824). It is well calibrated and has great clinical application value. This study developed a clinical-radiomics nomogram based on spectral CT multi-parameter images, which can be used as an effective tool for preoperative personalized prediction of lymph node metastasis in colorectal cancer.</p>","PeriodicalId":10267,"journal":{"name":"Clinical & Experimental Metastasis","volume":" ","pages":"639-653"},"PeriodicalIF":4.2000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A clinical-radiomics nomogram based on spectral CT multi-parameter images for preoperative prediction of lymph node metastasis in colorectal cancer.\",\"authors\":\"Qian Li, Rui Hong, Ping Zhang, Liting Hou, Hailun Bao, Lin Bai, Jian Zhao\",\"doi\":\"10.1007/s10585-024-10293-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>To develop a clinical-radiomics nomogram based on spectral CT multi-parameter images for predicting lymph node metastasis in colorectal cancer. A total of 76 patients with colorectal cancer and 156 lymph nodes were included. The clinical data of the patients were collected, including gender, age, tumor location and size, preoperative tumor markers, etc. Three sets of conventional images in the arterial, venous, and delayed phases were obtained, and six sets of spectral images were reconstructed using the arterial phase spectral data, including virtual monoenergetic images (40 keV, 70 keV, 100 keV), iodine density maps, iodine no water maps, and virtual non-contrast images. Radiomics features of lymph nodes were extracted from the above images, respectively. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select features. A clinical model was constructed based on age and carcinoembryonic antigen (CEA) levels. The radiomics features selected were used to generate a composed radiomics signature (Com-RS). A nomogram was developed using age, CEA, and the Com-RS. The models' prediction efficiency, calibration, and clinical application value were evaluated by the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis, respectively. The nomogram outperforms the clinical model and the Com-RS (AUC = 0.879, 0.824). It is well calibrated and has great clinical application value. This study developed a clinical-radiomics nomogram based on spectral CT multi-parameter images, which can be used as an effective tool for preoperative personalized prediction of lymph node metastasis in colorectal cancer.</p>\",\"PeriodicalId\":10267,\"journal\":{\"name\":\"Clinical & Experimental Metastasis\",\"volume\":\" \",\"pages\":\"639-653\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical & Experimental Metastasis\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s10585-024-10293-3\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/20 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical & Experimental Metastasis","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10585-024-10293-3","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/20 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

基于光谱 CT 多参数图像开发临床放射组学提名图,用于预测结直肠癌淋巴结转移。研究共纳入 76 名结直肠癌患者和 156 个淋巴结。收集了患者的临床数据,包括性别、年龄、肿瘤位置和大小、术前肿瘤标志物等。研究人员获得了动脉期、静脉期和延迟期的三组常规图像,并利用动脉期的光谱数据重建了六组光谱图像,包括虚拟单能图像(40 keV、70 keV、100 keV)、碘密度图、碘无水图和虚拟非对比图像。分别从上述图像中提取淋巴结的放射组学特征。采用单变量分析和最小绝对收缩与选择算子(LASSO)回归来选择特征。根据年龄和癌胚抗原(CEA)水平构建临床模型。选定的放射组学特征用于生成放射组学特征组合(Com-RS)。利用年龄、癌胚抗原和 Com-RS 建立了一个提名图。模型的预测效率、校准和临床应用价值分别通过接收者操作特征曲线下面积(AUC)、校准曲线和决策曲线分析进行评估。提名图优于临床模型和 Com-RS(AUC = 0.879,0.824)。其校准效果良好,具有很高的临床应用价值。该研究建立了基于CT多参数光谱图像的临床放射组学提名图,可作为结直肠癌术前淋巴结转移个性化预测的有效工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

A clinical-radiomics nomogram based on spectral CT multi-parameter images for preoperative prediction of lymph node metastasis in colorectal cancer.

A clinical-radiomics nomogram based on spectral CT multi-parameter images for preoperative prediction of lymph node metastasis in colorectal cancer.

To develop a clinical-radiomics nomogram based on spectral CT multi-parameter images for predicting lymph node metastasis in colorectal cancer. A total of 76 patients with colorectal cancer and 156 lymph nodes were included. The clinical data of the patients were collected, including gender, age, tumor location and size, preoperative tumor markers, etc. Three sets of conventional images in the arterial, venous, and delayed phases were obtained, and six sets of spectral images were reconstructed using the arterial phase spectral data, including virtual monoenergetic images (40 keV, 70 keV, 100 keV), iodine density maps, iodine no water maps, and virtual non-contrast images. Radiomics features of lymph nodes were extracted from the above images, respectively. Univariate analysis and least absolute shrinkage and selection operator (LASSO) regression were used to select features. A clinical model was constructed based on age and carcinoembryonic antigen (CEA) levels. The radiomics features selected were used to generate a composed radiomics signature (Com-RS). A nomogram was developed using age, CEA, and the Com-RS. The models' prediction efficiency, calibration, and clinical application value were evaluated by the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis, respectively. The nomogram outperforms the clinical model and the Com-RS (AUC = 0.879, 0.824). It is well calibrated and has great clinical application value. This study developed a clinical-radiomics nomogram based on spectral CT multi-parameter images, which can be used as an effective tool for preoperative personalized prediction of lymph node metastasis in colorectal cancer.

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
CiteScore
7.80
自引率
5.00%
发文量
55
审稿时长
12 months
期刊介绍: The Journal''s scope encompasses all aspects of metastasis research, whether laboratory-based, experimental or clinical and therapeutic. It covers such areas as molecular biology, pharmacology, tumor biology, and clinical cancer treatment (with all its subdivisions of surgery, chemotherapy and radio-therapy as well as pathology and epidemiology) insofar as these disciplines are concerned with the Journal''s core subject of metastasis formation, prevention and treatment.
×
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