NS-HGlio：一种可推广且可重复的高级别胶质瘤分割与体积测量人工智能算法，用于纵向磁共振成像评估，为试验和临床中的RANO标准提供依据。
NS-HGlio: A generalizable and repeatable HGG segmentation and volumetric measurement AI algorithm for the longitudinal MRI assessment to inform RANO in trials and clinics.
作者信息
Abayazeed Aly H, Abbassy Ahmed, Müeller Michael, Hill Michael, Qayati Mohamed, Mohamed Shady, Mekhaimar Mahmoud, Raymond Catalina, Dubey Prachi, Nael Kambiz, Rohatgi Saurabh, Kapare Vaishali, Kulkarni Ashwini, Shiang Tina, Kumar Atul, Andratschke Nicolaus, Willmann Jonas, Brawanski Alexander, De Jesus Reordan, Tuna Ibrahim, Fung Steve H, Landolfi Joseph C, Ellingson Benjamin M, Reyes Mauricio
机构信息
Biomedical Engineering group, Neosoma Inc., Groton, Massachusetts, USA (Originating Institution address:44 Farmers Row, Groton, Massachusetts, 01450), USA.
ARTORG Biomedical Engineering group, University of Bern, Switzerland.
出版信息
Neurooncol Adv. 2022 Dec 20;5(1):vdac184. doi: 10.1093/noajnl/vdac184. eCollection 2023 Jan-Dec.
BACKGROUND
Accurate and repeatable measurement of high-grade glioma (HGG) enhancing (Enh.) and T2/FLAIR hyperintensity/edema (Ed.) is required for monitoring treatment response. 3D measurements can be used to inform the modified Response Assessment in Neuro-oncology criteria. We aim to develop an HGG volumetric measurement and visualization AI algorithm that is generalizable and repeatable.
METHODS
A single 3D-Convoluted Neural Network, NS-HGlio, to analyze HGG on MRIs using 5-fold cross validation was developed using retrospective (557 MRIs), multicentre (38 sites) and multivendor (32 scanners) dataset divided into training (70%), validation (20%), and testing (10%). Six neuroradiologists created the ground truth (GT). Additional Internal validation (IV, three institutions) using 70 MRIs, and External validation (EV, single institution) using 40 MRIs through measuring the Dice Similarity Coefficient (DSC) of Enh., Ed. ,and Enh. + Ed. (WholeLesion/WL) tumor tissue and repeatability testing on 14 subjects from the TCIA MGH-QIN-GBM dataset using volume correlations between timepoints were performed.
RESULTS
IV Preoperative median DSC Enh. 0.89 (SD 0.11), Ed. 0.88 (0.28), WL 0.88 (0.11). EV Preoperative median DSC Enh. 0.82 (0.09), Ed. 0.83 (0.11), WL 0.86 (0.06). IV Postoperative median DSC Enh. 0.77 (SD 0.20), Ed 0.78. (SD 0.09), WL 0.78 (SD 0.11). EV Postoperative median DSC Enh. 0.75 (0.21), Ed 0.74 (0.12), WL 0.79 (0.07). Repeatability testing; Intraclass Correlation Coefficient of 0.95 Enh. and 0.92 Ed.
CONCLUSION
NS-HGlio is accurate, repeatable, and generalizable. The output can be used for visualization, documentation, treatment response monitoring, radiation planning, intra-operative targeting, and estimation of Residual Tumor Volume among others.
背景
监测高级别胶质瘤（HGG）的治疗反应需要准确且可重复地测量其强化（Enh.）以及T2/FLAIR高信号/水肿（Ed.）情况。三维测量可用于指导神经肿瘤学改良反应评估标准。我们旨在开发一种可推广且可重复的HGG体积测量与可视化人工智能算法。
方法
使用回顾性（557例磁共振成像）、多中心（38个站点）和多厂商（32台扫描仪）数据集，通过5折交叉验证开发了一个单一的三维卷积神经网络NS-HGlio，用于分析磁共振成像上的HGG，该数据集分为训练集（70%）、验证集（20%）和测试集（10%）。六名神经放射科医生创建了真实标准（GT）。通过测量强化、水肿以及强化 + 水肿（全瘤/WL）肿瘤组织的骰子相似系数（DSC），使用70例磁共振成像进行了额外的内部验证（IV，三个机构），并使用40例磁共振成像通过测量TCIA MGH-QIN-GBM数据集中14名受试者不同时间点之间的体积相关性进行了外部验证（EV，单个机构）。
结果
内部验证术前强化DSC中位数为0.89（标准差0.11），水肿为0.88（0.28），全瘤为0.88（0.11）。外部验证术前强化DSC中位数为0.82（0.09），水肿为0.83（0.11），全瘤为0.86（0.06）。内部验证术后强化DSC中位数为0.77（标准差0.20），水肿为0.78（标准差0.09），全瘤为0.78（标准差0.11）。外部验证术后强化DSC中位数为0.75（0.21），水肿为0.74（0.12），全瘤为0.79（0.07）。重复性测试；强化的组内相关系数为0.95，水肿的为0.92。
结论
NS-HGlio准确、可重复且可推广。其输出可用于可视化、记录、治疗反应监测、放射治疗计划、术中靶向以及残余肿瘤体积估计等。
Zotero 插件