Deep Learning Segmentation of Infiltrative and Enhancing Cellular Tumor at Pre- and Posttreatment Multishell Diffusion MRI of Glioblastoma.
IF 8.1
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Louis Gagnon, Diviya Gupta, George Mastorakos, Nathan White, Vanessa Goodwill, Carrie R McDonald, Thomas Beaumont, Christopher Conlin, Tyler M Seibert, Uyen Nguyen, Jona Hattangadi-Gluth, Santosh Kesari, Jessica D Schulte, David Piccioni, Kathleen M Schmainda, Nikdokht Farid, Anders M Dale, Jeffrey D Rudie
下载PDF
{"title":"Deep Learning Segmentation of Infiltrative and Enhancing Cellular Tumor at Pre- and Posttreatment Multishell Diffusion MRI of Glioblastoma.","authors":"Louis Gagnon, Diviya Gupta, George Mastorakos, Nathan White, Vanessa Goodwill, Carrie R McDonald, Thomas Beaumont, Christopher Conlin, Tyler M Seibert, Uyen Nguyen, Jona Hattangadi-Gluth, Santosh Kesari, Jessica D Schulte, David Piccioni, Kathleen M Schmainda, Nikdokht Farid, Anders M Dale, Jeffrey D Rudie","doi":"10.1148/ryai.230489","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To develop and validate a deep learning (DL) method to detect and segment enhancing and nonenhancing cellular tumor on pre- and posttreatment MRI scans in patients with glioblastoma and to predict overall survival (OS) and progression-free survival (PFS). Materials and Methods This retrospective study included 1397 MRI scans in 1297 patients with glioblastoma, including an internal set of 243 MRI scans (January 2010 to June 2022) for model training and cross-validation and four external test cohorts. Cellular tumor maps were segmented by two radiologists on the basis of imaging, clinical history, and pathologic findings. Multimodal MRI data with perfusion and multishell diffusion imaging were inputted into a nnU-Net DL model to segment cellular tumor. Segmentation performance (Dice score) and performance in distinguishing recurrent tumor from posttreatment changes (area under the receiver operating characteristic curve [AUC]) were quantified. Model performance in predicting OS and PFS was assessed using Cox multivariable analysis. Results A cohort of 178 patients (mean age, 56 years ± 13 [SD]; 116 male, 62 female) with 243 MRI timepoints, as well as four external datasets with 55, 70, 610, and 419 MRI timepoints, respectively, were evaluated. The median Dice score was 0.79 (IQR, 0.53-0.89), and the AUC for detecting residual or recurrent tumor was 0.84 (95% CI: 0.79, 0.89). In the internal test set, estimated cellular tumor volume was significantly associated with OS (hazard ratio [HR] = 1.04 per milliliter; <i>P</i> < .001) and PFS (HR = 1.04 per milliliter; <i>P</i> < .001) after adjustment for age, sex, and gross total resection (GTR) status. In the external test sets, estimated cellular tumor volume was significantly associated with OS (HR = 1.01 per milliliter; <i>P</i> < .001) after adjustment for age, sex, and GTR status. Conclusion A DL model incorporating advanced imaging could accurately segment enhancing and nonenhancing cellular tumor, distinguish recurrent or residual tumor from posttreatment changes, and predict OS and PFS in patients with glioblastoma. <b>Keywords:</b> Segmentation, Glioblastoma, Multishell Diffusion MRI <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e230489"},"PeriodicalIF":8.1000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11427928/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology-Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryai.230489","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
引用
批量引用
Abstract
Purpose To develop and validate a deep learning (DL) method to detect and segment enhancing and nonenhancing cellular tumor on pre- and posttreatment MRI scans in patients with glioblastoma and to predict overall survival (OS) and progression-free survival (PFS). Materials and Methods This retrospective study included 1397 MRI scans in 1297 patients with glioblastoma, including an internal set of 243 MRI scans (January 2010 to June 2022) for model training and cross-validation and four external test cohorts. Cellular tumor maps were segmented by two radiologists on the basis of imaging, clinical history, and pathologic findings. Multimodal MRI data with perfusion and multishell diffusion imaging were inputted into a nnU-Net DL model to segment cellular tumor. Segmentation performance (Dice score) and performance in distinguishing recurrent tumor from posttreatment changes (area under the receiver operating characteristic curve [AUC]) were quantified. Model performance in predicting OS and PFS was assessed using Cox multivariable analysis. Results A cohort of 178 patients (mean age, 56 years ± 13 [SD]; 116 male, 62 female) with 243 MRI timepoints, as well as four external datasets with 55, 70, 610, and 419 MRI timepoints, respectively, were evaluated. The median Dice score was 0.79 (IQR, 0.53-0.89), and the AUC for detecting residual or recurrent tumor was 0.84 (95% CI: 0.79, 0.89). In the internal test set, estimated cellular tumor volume was significantly associated with OS (hazard ratio [HR] = 1.04 per milliliter; P < .001) and PFS (HR = 1.04 per milliliter; P < .001) after adjustment for age, sex, and gross total resection (GTR) status. In the external test sets, estimated cellular tumor volume was significantly associated with OS (HR = 1.01 per milliliter; P < .001) after adjustment for age, sex, and GTR status. Conclusion A DL model incorporating advanced imaging could accurately segment enhancing and nonenhancing cellular tumor, distinguish recurrent or residual tumor from posttreatment changes, and predict OS and PFS in patients with glioblastoma. Keywords: Segmentation, Glioblastoma, Multishell Diffusion MRI Supplemental material is available for this article. © RSNA, 2024.
胶质母细胞瘤治疗前和治疗后多壳体弥散 MRI 上浸润性和增强型细胞肿瘤的深度学习分割
"刚刚接受 "的论文经过同行评审,已被接受在《放射学》上发表:人工智能》上发表。这篇文章在以最终版本发表之前,还将经过校对、排版和校对审核。请注意,在制作最终校对稿的过程中,可能会发现一些可能影响内容的错误。目的 开发并验证一种深度学习(DL)方法,用于检测和分割胶质母细胞瘤患者治疗前和治疗后 MRI 扫描中的增强和非增强细胞肿瘤,并预测总生存期(OS)和无进展生存期(PFS)。材料与方法 这项回顾性研究包括 1297 名胶质母细胞瘤患者的 1397 次核磁共振成像,其中包括用于模型训练和交叉验证的 243 次核磁共振成像内部队列(2010 年 1 月至 2022 年 6 月)和四个外部测试队列。细胞肿瘤图由两名放射科医生根据成像、临床病史和病理学进行分割。多模态 MRI 灌注和多壳体扩散成像被输入 nnU-Net DL 模型,以分割细胞肿瘤。对分割性能(Dice评分)和从治疗后变化中检测复发肿瘤的性能(接收器操作特征曲线下面积[AUC])进行了量化。使用 Cox 多变量分析评估了模型预测 OS 和 PFS 的性能。结果 评估了一组 178 例患者(平均年龄 56 岁 ± [SD]13;男性 121 例,女性 57 例),共 243 个 MRI 时间点,以及四个外部数据集,分别有 55、70、610 和 419 个 MRI 时间点。Dice 评分的中位数为 0.79(IQR:0.53-0.89),检测残留/复发肿瘤的 AUC 为 0.84(95% CI:0.79-0.89)。在内部测试组中,当调整年龄、性别和总切除状态时,估计的细胞肿瘤体积与OS(危险比[HR] = 1.04/mL,P < .001)和PFS(HR = 1.04/mL,P < .001)显著相关。在外部测试集中,当调整年龄、性别和大体全切除状态时,估计的细胞肿瘤体积与 OS 显著相关(HR = 1.01/mL,P < .001)。结论 结合先进成像技术的 DL 模型可准确分割增强和非增强细胞肿瘤,根据治疗后的变化对复发/残留肿瘤进行分类,并预测胶质母细胞瘤患者的 OS 和 PFS。©RSNA,2024。
本文章由计算机程序翻译,如有差异,请以英文原文为准。