使用基于 18F-FDG 正电子发射断层成像/计算机断层扫描的放射组学对胃癌中 HER2 表达状态进行无创评估:一项试点研究。

IF 2.4 4区 医学 Q3 MEDICINE, RESEARCH & EXPERIMENTAL
Cancer Biotherapy and Radiopharmaceuticals Pub Date : 2024-04-01 Epub Date: 2024-01-09 DOI:10.1089/cbr.2023.0162
Xiaojing Jiang, Tianyue Li, Jianfang Wang, Zhaoqi Zhang, Xiaolin Chen, Jingmian Zhang, Xinming Zhao
{"title":"使用基于 18F-FDG 正电子发射断层成像/计算机断层扫描的放射组学对胃癌中 HER2 表达状态进行无创评估:一项试点研究。","authors":"Xiaojing Jiang, Tianyue Li, Jianfang Wang, Zhaoqi Zhang, Xiaolin Chen, Jingmian Zhang, Xinming Zhao","doi":"10.1089/cbr.2023.0162","DOIUrl":null,"url":null,"abstract":"<p><p><b><i>Purpose:</i></b> Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on <sup>18</sup>F-fuorodeoxyglucose (<sup>18</sup>F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). <b><i>Patients and Methods:</i></b> A total of 118 patients with GC were enrolled in this study. <sup>18</sup>F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. <b><i>Results:</i></b> In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. <b><i>Conclusions:</i></b> <sup>18</sup>F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy.</p>","PeriodicalId":55277,"journal":{"name":"Cancer Biotherapy and Radiopharmaceuticals","volume":" ","pages":"169-177"},"PeriodicalIF":2.4000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Noninvasive Assessment of HER2 Expression Status in Gastric Cancer Using <sup>18</sup>F-FDG Positron Emission Tomography/Computed Tomography-Based Radiomics: A Pilot Study.\",\"authors\":\"Xiaojing Jiang, Tianyue Li, Jianfang Wang, Zhaoqi Zhang, Xiaolin Chen, Jingmian Zhang, Xinming Zhao\",\"doi\":\"10.1089/cbr.2023.0162\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b><i>Purpose:</i></b> Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on <sup>18</sup>F-fuorodeoxyglucose (<sup>18</sup>F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). <b><i>Patients and Methods:</i></b> A total of 118 patients with GC were enrolled in this study. <sup>18</sup>F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. <b><i>Results:</i></b> In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. <b><i>Conclusions:</i></b> <sup>18</sup>F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy.</p>\",\"PeriodicalId\":55277,\"journal\":{\"name\":\"Cancer Biotherapy and Radiopharmaceuticals\",\"volume\":\" \",\"pages\":\"169-177\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cancer Biotherapy and Radiopharmaceuticals\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1089/cbr.2023.0162\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/9 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"MEDICINE, RESEARCH & EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Biotherapy and Radiopharmaceuticals","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1089/cbr.2023.0162","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/9 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

摘要

目的:免疫组化(IHC)是检测人类表皮生长因子受体 2(HER2)表达水平的主要方法。然而,IHC 具有侵袭性,不能实时反映 HER2 的表达状态。本研究旨在构建和验证三种基于 18F- 福尔脱氧葡萄糖(18F-FDG)正电子发射断层扫描/计算机断层扫描(PET/CT)成像的放射组学模型,并评估放射组学模型对胃癌(GC)患者 HER2 表达状态的预测能力。患者和方法:本研究共纳入 118 例胃癌患者。手术前进行 18F-FDG PET/CT 检查。应用 LIFEx 软件包提取 PET 和 CT 放射组学特征。使用最小绝对收缩和选择算子(least absolute shrinkage and selection operator [LASSO])算法选择最佳放射组学特征。构建并验证了三种机器学习方法,即逻辑回归(LR)、支持向量机(SVM)和随机森林(RF)模型。合成少数群体过度采样技术(SMOTE)用于解决数据不平衡问题。结果在训练集和测试集中,LR、SVM 和 RF 模型的曲线下面积(AUC)值分别为 0.809、0.761、0.861 和 0.628、0.993、0.717,Brier 分数分别为 0.118、0.214 和 0.143。在这三个模型中,LR 和 RF 模型的预测性能极佳。在 SMOTE 平衡数据后,三个模型的 AUC 值都有明显提高。结论基于18F-FDG PET/CT的放射组学模型,尤其是LR和RF模型,在预测GC患者的HER2表达状态方面表现良好,可用于预选可能从HER2靶向治疗中获益的患者。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Noninvasive Assessment of HER2 Expression Status in Gastric Cancer Using 18F-FDG Positron Emission Tomography/Computed Tomography-Based Radiomics: A Pilot Study.

Purpose: Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on 18F-fuorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). Patients and Methods: A total of 118 patients with GC were enrolled in this study. 18F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. Results: In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. Conclusions: 18F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy.

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
2.90%
发文量
87
审稿时长
3 months
期刊介绍: Cancer Biotherapy and Radiopharmaceuticals is the established peer-reviewed journal, with over 25 years of cutting-edge content on innovative therapeutic investigations to ultimately improve cancer management. It is the only journal with the specific focus of cancer biotherapy and is inclusive of monoclonal antibodies, cytokine therapy, cancer gene therapy, cell-based therapies, and other forms of immunotherapies. The Journal includes extensive reporting on advancements in radioimmunotherapy, and the use of radiopharmaceuticals and radiolabeled peptides for the development of new cancer treatments.
×
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