全脑静息状态fMRI特征的机器学习用于额叶胶质瘤的个体化分级。

IF 3.5 2区 医学 Q2 ONCOLOGY
Yue Hu, Xin Cao, Hongyi Chen, Daoying Geng, Kun Lv
{"title":"全脑静息状态fMRI特征的机器学习用于额叶胶质瘤的个体化分级。","authors":"Yue Hu, Xin Cao, Hongyi Chen, Daoying Geng, Kun Lv","doi":"10.1186/s40644-025-00920-x","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Accurate preoperative grading of gliomas is critical for therapeutic planning and prognostic evaluation. We developed a noninvasive machine learning model leveraging whole-brain resting-state functional magnetic resonance imaging (rs-fMRI) biomarkers to discriminate high-grade (HGGs) and low-grade gliomas (LGGs) in the frontal lobe.</p><p><strong>Methods: </strong>This retrospective study included 138 patients (78 LGGs, 60 HGGs) with left frontal gliomas. A total of 7134 features were extracted from the mean amplitude of low-frequency fluctuation (mALFF), mean fractional ALFF, mean percentage amplitude of fluctuation (mPerAF), mean regional homogeneity (mReHo) maps and resting-state functional connectivity (RSFC) matrix. Twelve predictive features were selected through Mann-Whitney U test, correlation analysis and least absolute shrinkage and selection operator method. The patients were stratified and randomized into the training and testing datasets with a 7:3 ratio. The logical regression, random forest, support vector machine (SVM) and adaptive boosting algorithms were used to establish models. The model performance was evaluated using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.</p><p><strong>Results: </strong>The selected 12 features included 7 RSFC features, 4 mPerAF features, and 1 mReHo feature. Based on these features, the model was established using the SVM had an optimal performance. The accuracy in the training and testing datasets was 0.957 and 0.727, respectively. The area under the receiver operating characteristic curves was 0.972 and 0.799, respectively.</p><p><strong>Conclusions: </strong>Our whole-brain rs-fMRI radiomics approach provides an objective tool for preoperative glioma stratification. The biological interpretability of selected features reflects distinct neuroplasticity patterns between LGGs and HGGs, advancing understanding of glioma-network interactions.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"25 1","pages":"97"},"PeriodicalIF":3.5000,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12323070/pdf/","citationCount":"0","resultStr":"{\"title\":\"Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas.\",\"authors\":\"Yue Hu, Xin Cao, Hongyi Chen, Daoying Geng, Kun Lv\",\"doi\":\"10.1186/s40644-025-00920-x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Accurate preoperative grading of gliomas is critical for therapeutic planning and prognostic evaluation. We developed a noninvasive machine learning model leveraging whole-brain resting-state functional magnetic resonance imaging (rs-fMRI) biomarkers to discriminate high-grade (HGGs) and low-grade gliomas (LGGs) in the frontal lobe.</p><p><strong>Methods: </strong>This retrospective study included 138 patients (78 LGGs, 60 HGGs) with left frontal gliomas. A total of 7134 features were extracted from the mean amplitude of low-frequency fluctuation (mALFF), mean fractional ALFF, mean percentage amplitude of fluctuation (mPerAF), mean regional homogeneity (mReHo) maps and resting-state functional connectivity (RSFC) matrix. Twelve predictive features were selected through Mann-Whitney U test, correlation analysis and least absolute shrinkage and selection operator method. The patients were stratified and randomized into the training and testing datasets with a 7:3 ratio. The logical regression, random forest, support vector machine (SVM) and adaptive boosting algorithms were used to establish models. The model performance was evaluated using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.</p><p><strong>Results: </strong>The selected 12 features included 7 RSFC features, 4 mPerAF features, and 1 mReHo feature. Based on these features, the model was established using the SVM had an optimal performance. The accuracy in the training and testing datasets was 0.957 and 0.727, respectively. The area under the receiver operating characteristic curves was 0.972 and 0.799, respectively.</p><p><strong>Conclusions: </strong>Our whole-brain rs-fMRI radiomics approach provides an objective tool for preoperative glioma stratification. The biological interpretability of selected features reflects distinct neuroplasticity patterns between LGGs and HGGs, advancing understanding of glioma-network interactions.</p>\",\"PeriodicalId\":9548,\"journal\":{\"name\":\"Cancer Imaging\",\"volume\":\"25 1\",\"pages\":\"97\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2025-08-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12323070/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cancer Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s40644-025-00920-x\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40644-025-00920-x","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:准确的胶质瘤术前分级对治疗计划和预后评估至关重要。我们开发了一种无创机器学习模型,利用全脑静息状态功能磁共振成像(rs-fMRI)生物标志物来区分额叶中的高级别(HGGs)和低级别胶质瘤(LGGs)。方法:本研究纳入138例左额叶胶质瘤患者(78例LGGs, 60例HGGs)。从平均低频波动幅度(mALFF)、平均分数ALFF、平均波动百分比幅度(mPerAF)、平均区域均匀性(mReHo)图和静息状态功能连通性(RSFC)矩阵中提取了7134个特征。通过Mann-Whitney U检验、相关分析、最小绝对收缩和选择算子法选出12个预测特征。将患者按7:3的比例分层并随机分为训练和测试数据集。采用逻辑回归、随机森林、支持向量机(SVM)和自适应增强算法建立模型。使用受试者工作特征曲线下的面积、准确性、灵敏度和特异性来评估模型的性能。结果:选取的12个特征包括7个RSFC特征、4个mPerAF特征和1个mReHo特征。基于这些特征,利用支持向量机建立的模型具有最优的性能。训练集和测试集的准确率分别为0.957和0.727。受试者工作特征曲线下面积分别为0.972和0.799。结论:我们的全脑磁共振成像放射组学方法为术前胶质瘤分层提供了客观的工具。所选特征的生物学可解释性反映了LGGs和HGGs之间不同的神经可塑性模式,促进了对胶质瘤网络相互作用的理解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas.

Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas.

Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas.

Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas.

Purpose: Accurate preoperative grading of gliomas is critical for therapeutic planning and prognostic evaluation. We developed a noninvasive machine learning model leveraging whole-brain resting-state functional magnetic resonance imaging (rs-fMRI) biomarkers to discriminate high-grade (HGGs) and low-grade gliomas (LGGs) in the frontal lobe.

Methods: This retrospective study included 138 patients (78 LGGs, 60 HGGs) with left frontal gliomas. A total of 7134 features were extracted from the mean amplitude of low-frequency fluctuation (mALFF), mean fractional ALFF, mean percentage amplitude of fluctuation (mPerAF), mean regional homogeneity (mReHo) maps and resting-state functional connectivity (RSFC) matrix. Twelve predictive features were selected through Mann-Whitney U test, correlation analysis and least absolute shrinkage and selection operator method. The patients were stratified and randomized into the training and testing datasets with a 7:3 ratio. The logical regression, random forest, support vector machine (SVM) and adaptive boosting algorithms were used to establish models. The model performance was evaluated using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.

Results: The selected 12 features included 7 RSFC features, 4 mPerAF features, and 1 mReHo feature. Based on these features, the model was established using the SVM had an optimal performance. The accuracy in the training and testing datasets was 0.957 and 0.727, respectively. The area under the receiver operating characteristic curves was 0.972 and 0.799, respectively.

Conclusions: Our whole-brain rs-fMRI radiomics approach provides an objective tool for preoperative glioma stratification. The biological interpretability of selected features reflects distinct neuroplasticity patterns between LGGs and HGGs, advancing understanding of glioma-network interactions.

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
Cancer Imaging
Cancer Imaging ONCOLOGY-RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
CiteScore
7.00
自引率
0.00%
发文量
66
审稿时长
>12 weeks
期刊介绍: Cancer Imaging is an open access, peer-reviewed journal publishing original articles, reviews and editorials written by expert international radiologists working in oncology. The journal encompasses CT, MR, PET, ultrasound, radionuclide and multimodal imaging in all kinds of malignant tumours, plus new developments, techniques and innovations. Topics of interest include: Breast Imaging Chest Complications of treatment Ear, Nose & Throat Gastrointestinal Hepatobiliary & Pancreatic Imaging biomarkers Interventional Lymphoma Measurement of tumour response Molecular functional imaging Musculoskeletal Neuro oncology Nuclear Medicine Paediatric.
×
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:604180095
Book学术官方微信