通过核磁共振成像和深度学习预测具有放射学低级别特征的胶质瘤术中5-ALA诱导的肿瘤荧光。

IF 3.2 2区 医学 Q2 CLINICAL NEUROLOGY Journal of Neuro-Oncology Pub Date : 2024-11-19 DOI:10.1007/s11060-024-04875-0
Eric Suero Molina, Ghasem Azemi, Zeynep Özdemir, Carlo Russo, Hermann Krähling, Alexandra Valls Chavarria, Sidong Liu, Walter Stummer, Antonio Di Ieva
{"title":"通过核磁共振成像和深度学习预测具有放射学低级别特征的胶质瘤术中5-ALA诱导的肿瘤荧光。","authors":"Eric Suero Molina, Ghasem Azemi, Zeynep Özdemir, Carlo Russo, Hermann Krähling, Alexandra Valls Chavarria, Sidong Liu, Walter Stummer, Antonio Di Ieva","doi":"10.1007/s11060-024-04875-0","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI).</p><p><strong>Methods: </strong>We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure.</p><p><strong>Results: </strong>Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively.</p><p><strong>Conclusions: </strong>Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.</p>","PeriodicalId":16425,"journal":{"name":"Journal of Neuro-Oncology","volume":" ","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.\",\"authors\":\"Eric Suero Molina, Ghasem Azemi, Zeynep Özdemir, Carlo Russo, Hermann Krähling, Alexandra Valls Chavarria, Sidong Liu, Walter Stummer, Antonio Di Ieva\",\"doi\":\"10.1007/s11060-024-04875-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI).</p><p><strong>Methods: </strong>We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure.</p><p><strong>Results: </strong>Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively.</p><p><strong>Conclusions: </strong>Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.</p>\",\"PeriodicalId\":16425,\"journal\":{\"name\":\"Journal of Neuro-Oncology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-11-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Neuro-Oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s11060-024-04875-0\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Neuro-Oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11060-024-04875-0","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:低级别胶质瘤通常只有20%-30%的病例表现出5-氨基乙酰丙酸(5-ALA)诱导的荧光,将5-ALA的给药剂量增加一倍可提高荧光率。荧光可描绘出无细胞灶,可对其进行精确采样,以避免评级过低。我们旨在分析深度学习模型能否根据术前磁共振成像(MRI)预测术中荧光:我们评估了一组 163 例术中被分为荧光(83 例)和非荧光(80 例)的胶质瘤患者。缺乏高级别特征(如坏死或不规则环形对比增强)的胶质瘤的术前磁共振图像包括T1、T1-钆后和FLAIR序列。经过预处理的核磁共振成像被输入一个编码器-解码器卷积神经网络(U-Net),该网络经过预先训练,可使用这三种核磁共振成像序列进行肿瘤分割。我们使用变异自动编码器(VAE)中 U-Net 瓶颈层的输出作为分类特征。我们使用主成分分析(PCA)和偏最小平方判别分析(PLS-DA)算法在随机森林分类器中识别并使用了最有效的特征。我们使用十倍交叉验证程序评估了分类器的性能:结果:我们使用平均平衡准确度、平均灵敏度和平均特异度评估了我们提出的方法的性能。通过使用 PCA 挑选出的表现最佳的特征获得了最佳结果,平均平衡准确率达到 80%,平均灵敏度和特异性分别达到 84% 和 76%:我们的研究结果凸显了 U-Net 模型与随机森林分类器相结合用于术前预测术中荧光的潜力。我们利用针对脑肿瘤分割预先训练的 U-Net 模型提取的特征获得了较高的准确率。虽然该模型仍有待改进,但它有潜力用于评估何时对缺乏典型高级别放射学特征的胶质瘤施用 5-ALA。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.

Purpose: Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI).

Methods: We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure.

Results: Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively.

Conclusions: Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

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
Journal of Neuro-Oncology
Journal of Neuro-Oncology 医学-临床神经学
CiteScore
6.60
自引率
7.70%
发文量
277
审稿时长
3.3 months
期刊介绍: The Journal of Neuro-Oncology is a multi-disciplinary journal encompassing basic, applied, and clinical investigations in all research areas as they relate to cancer and the central nervous system. It provides a single forum for communication among neurologists, neurosurgeons, radiotherapists, medical oncologists, neuropathologists, neurodiagnosticians, and laboratory-based oncologists conducting relevant research. The Journal of Neuro-Oncology does not seek to isolate the field, but rather to focus the efforts of many disciplines in one publication through a format which pulls together these diverse interests. More than any other field of oncology, cancer of the central nervous system requires multi-disciplinary approaches. To alleviate having to scan dozens of journals of cell biology, pathology, laboratory and clinical endeavours, JNO is a periodical in which current, high-quality, relevant research in all aspects of neuro-oncology may be found.
期刊最新文献
Immune checkpoint inhibitors for glioblastoma: emerging science, clinical advances, and future directions. Congress of Neurological Surgeons systematic review and evidence-based guidelines for the role of chemotherapy in newly diagnosed WHO Grade II diffuse glioma in adults: update. Multimodal treatment of glioblastoma with multiple lesions - a multi-center retrospective analysis. Optimal treatment regimen for very elderly patients with atypical meningioma: an analysis of survival outcomes using the National Cancer Database (NCDB). Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1