CT和MRI双峰放射组学预测NSCLC脑转移患者EGFR状态：一项多中心研究。

IF 3.2 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Pub Date : 2025-02-01 DOI:10.1016/j.ejrad.2024.111853

Zhiqiang Ouyang , Guodong Zhang , Shaonan He , Qiubo Huang , Liren Zhang , Xirui Duan , Xuerong Zhang , Yifan Liu , Tengfei Ke , Jun Yang , Conghui Ai , Yi Lu , Chengde Liao

{"title":"CT和MRI双峰放射组学预测NSCLC脑转移患者EGFR状态：一项多中心研究。","authors":"Zhiqiang Ouyang , Guodong Zhang , Shaonan He , Qiubo Huang , Liren Zhang , Xirui Duan , Xuerong Zhang , Yifan Liu , Tengfei Ke , Jun Yang , Conghui Ai , Yi Lu , Chengde Liao","doi":"10.1016/j.ejrad.2024.111853","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Leveraging the radiomics information from non-small cell lung cancer (NSCLC) primary lesion and brain metastasis (BM) to develop and validate a bimodal radiomics nomogram that can accurately predict epidermal growth factor receptor (EGFR) status.</div></div><div><h3>Methods</h3><div>A total of 309 NSCLC patients with BM from three independent centers were recruited. Among them, the patients of Center I were randomly allocated into the training and internal test cohorts in a 7:3 ratio. Meanwhile, the patients from Center Ⅱ and Center Ⅲ collectively constitute the external test cohort. All chest CT and brain MRI images of each patient were obtained for image registration and sequence combination within a single modality. After image preprocessing, 1037 radiomics features were extracted from each single sequence. Six machine learning algorithms were used to construct radiomics signatures for CT and MRI respectively. The best CT and MRI radiomics signatures were fitted to establish the bimodal radiomics nomogram for predicting the EGFR status.</div></div><div><h3>Results</h3><div>The contrast-enhanced (CE) eXtreme gradient boosting (XG Boost) and T2-weighted imaging (T2WI) + T1-weighted contrast-enhanced imaging (T1CE) random forest models were chosen as the radiomics signature representing primary lesion and BM. Both models were found to be independent predictors of EGFR mutation. The bimodal radiomics nomogram, which incorporated CT radiomics signature and MRI radiomics signature, demonstrated a good calibration and discrimination in the internal test cohort [area under curve (AUC), 0.866; 95 % confidence intervals (CI), 0.778–0.950) and the external test cohort (AUC, 0.818; 95 % CI, 0.691–0.938).</div></div><div><h3>Conclusions</h3><div>Our CT and MRI bimodal radiomics nomogram could timely and accurately evaluate the likelihood of EGFR mutation in patients with limited access to necessary materials, thus making up for the shortcoming of plasma sequencing and promoting the advancement of precision medicine.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"183 ","pages":"Article 111853"},"PeriodicalIF":3.2000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CT and MRI bimodal radiomics for predicting EGFR status in NSCLC patients with brain metastases: A multicenter study\",\"authors\":\"Zhiqiang Ouyang , Guodong Zhang , Shaonan He , Qiubo Huang , Liren Zhang , Xirui Duan , Xuerong Zhang , Yifan Liu , Tengfei Ke , Jun Yang , Conghui Ai , Yi Lu , Chengde Liao\",\"doi\":\"10.1016/j.ejrad.2024.111853\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Leveraging the radiomics information from non-small cell lung cancer (NSCLC) primary lesion and brain metastasis (BM) to develop and validate a bimodal radiomics nomogram that can accurately predict epidermal growth factor receptor (EGFR) status.</div></div><div><h3>Methods</h3><div>A total of 309 NSCLC patients with BM from three independent centers were recruited. Among them, the patients of Center I were randomly allocated into the training and internal test cohorts in a 7:3 ratio. Meanwhile, the patients from Center Ⅱ and Center Ⅲ collectively constitute the external test cohort. All chest CT and brain MRI images of each patient were obtained for image registration and sequence combination within a single modality. After image preprocessing, 1037 radiomics features were extracted from each single sequence. Six machine learning algorithms were used to construct radiomics signatures for CT and MRI respectively. The best CT and MRI radiomics signatures were fitted to establish the bimodal radiomics nomogram for predicting the EGFR status.</div></div><div><h3>Results</h3><div>The contrast-enhanced (CE) eXtreme gradient boosting (XG Boost) and T2-weighted imaging (T2WI) + T1-weighted contrast-enhanced imaging (T1CE) random forest models were chosen as the radiomics signature representing primary lesion and BM. Both models were found to be independent predictors of EGFR mutation. The bimodal radiomics nomogram, which incorporated CT radiomics signature and MRI radiomics signature, demonstrated a good calibration and discrimination in the internal test cohort [area under curve (AUC), 0.866; 95 % confidence intervals (CI), 0.778–0.950) and the external test cohort (AUC, 0.818; 95 % CI, 0.691–0.938).</div></div><div><h3>Conclusions</h3><div>Our CT and MRI bimodal radiomics nomogram could timely and accurately evaluate the likelihood of EGFR mutation in patients with limited access to necessary materials, thus making up for the shortcoming of plasma sequencing and promoting the advancement of precision medicine.</div></div>\",\"PeriodicalId\":12063,\"journal\":{\"name\":\"European Journal of Radiology\",\"volume\":\"183 \",\"pages\":\"Article 111853\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Radiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0720048X24005692\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0720048X24005692","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

摘要

背景：利用非小细胞肺癌（NSCLC）原发病变和脑转移（BM）的放射组学信息，开发并验证了一种能够准确预测表皮生长因子受体（EGFR）状态的双峰放射组学模式图。方法：共招募来自三个独立中心的309例非小细胞肺癌合并脑转移患者。其中，I中心的患者按7:3的比例随机分为训练组和内测组。同时，中心Ⅱ和中心Ⅲ的患者共同构成外部检测队列。获得每位患者的所有胸部CT和脑部MRI图像，在单一模式下进行图像配准和序列组合。图像预处理后，从每个序列中提取1037个放射组学特征。使用六种机器学习算法分别构建CT和MRI的放射组学特征。拟合最佳CT和MRI放射组学特征，建立预测EGFR状态的双峰放射组学图。结果：选择对比增强（CE）极端梯度增强（XG Boost）和t2加权成像(T2WI) + t1加权对比增强成像（T1CE）随机森林模型作为代表原发病变和BM的放射组学特征。发现这两种模型都是EGFR突变的独立预测因子。结合CT放射组学特征和MRI放射组学特征的双峰放射组学图在内部测试队列中具有良好的校准和辨别能力[曲线下面积（AUC）， 0.866；95%置信区间（CI）， 0.778-0.950)和外部测试队列(AUC, 0.818；95% ci, 0.691-0.938)。结论：我们的CT和MRI双峰放射组学图能够及时、准确地评估患者在获得必要材料有限的情况下发生EGFR突变的可能性，弥补血浆测序的不足，促进精准医学的进步。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

CT and MRI bimodal radiomics for predicting EGFR status in NSCLC patients with brain metastases: A multicenter study

Background

Leveraging the radiomics information from non-small cell lung cancer (NSCLC) primary lesion and brain metastasis (BM) to develop and validate a bimodal radiomics nomogram that can accurately predict epidermal growth factor receptor (EGFR) status.

Methods

A total of 309 NSCLC patients with BM from three independent centers were recruited. Among them, the patients of Center I were randomly allocated into the training and internal test cohorts in a 7:3 ratio. Meanwhile, the patients from Center Ⅱ and Center Ⅲ collectively constitute the external test cohort. All chest CT and brain MRI images of each patient were obtained for image registration and sequence combination within a single modality. After image preprocessing, 1037 radiomics features were extracted from each single sequence. Six machine learning algorithms were used to construct radiomics signatures for CT and MRI respectively. The best CT and MRI radiomics signatures were fitted to establish the bimodal radiomics nomogram for predicting the EGFR status.

Results

The contrast-enhanced (CE) eXtreme gradient boosting (XG Boost) and T2-weighted imaging (T2WI) + T1-weighted contrast-enhanced imaging (T1CE) random forest models were chosen as the radiomics signature representing primary lesion and BM. Both models were found to be independent predictors of EGFR mutation. The bimodal radiomics nomogram, which incorporated CT radiomics signature and MRI radiomics signature, demonstrated a good calibration and discrimination in the internal test cohort [area under curve (AUC), 0.866; 95 % confidence intervals (CI), 0.778–0.950) and the external test cohort (AUC, 0.818; 95 % CI, 0.691–0.938).

Conclusions

Our CT and MRI bimodal radiomics nomogram could timely and accurately evaluate the likelihood of EGFR mutation in patients with limited access to necessary materials, thus making up for the shortcoming of plasma sequencing and promoting the advancement of precision medicine.

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

European Journal of Radiology 医学-核医学

CiteScore

6.70

自引率

3.00%

发文量

398

审稿时长

42 days

期刊介绍： European Journal of Radiology is an international journal which aims to communicate to its readers, state-of-the-art information on imaging developments in the form of high quality original research articles and timely reviews on current developments in the field. Its audience includes clinicians at all levels of training including radiology trainees, newly qualified imaging specialists and the experienced radiologist. Its aim is to inform efficient, appropriate and evidence-based imaging practice to the benefit of patients worldwide.