Yang Zi, Zamarud Aroosa, Marianayagam Neelan J, Park David J, Yener Ulas, Soltys Scott G, Chang Steven D, Meola Antonio, Jiang Hao, Lu Weiguo, Gu Xuejun
Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA; Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
Department of Neurosurgery, Stanford University School of Medicine, Stanford, CA, USA.
Comput Biol Med. 2025 Feb;185:109436. doi: 10.1016/j.compbiomed.2024.109436. Epub 2024 Dec 4.
Accurate and automated early survival prediction is critical for patients with glioblastoma (GBM) as their poor prognosis requires timely treatment decision-making. To address this need, we developed a deep learning (DL)-based end-to-end workflow for GBM overall survival (OS) prediction using pre-resection basic structural multiparametric magnetic resonance images (Bas-mpMRI) with a multi-institutional public dataset and evaluated it with an independent dataset of patients on a prospective institutional clinical trial.
The proposed end-to-end workflow includes a skull-stripping model, a GBM sub-region segmentation model and an ensemble learning-based OS prediction model. The segmentation model utilizes skull-stripped Bas-mpMRIs to segment three GBM sub-regions. The segmented GBM is fed into the contrastive learning-based OS prediction model to classify the patients into different survival groups. Our datasets include both a multi-institutional public dataset from Medical Image Computing and Computer Assisted Intervention (MICCAI) Brain Tumor Segmentation (BraTS) challenge 2020 with 235 patients, and an institutional dataset from a 5-fraction SRS clinical trial with 19 GBM patients. Each data entry consists of pre-operative Bas-mpMRIs, survival days and patient ages. Basic clinical characteristics are also available for SRS clinical trial data. The multi-institutional public dataset was used for workflow establishing (90% of data) and initial validation (10% of data). The validated workflow was then evaluated on the institutional clinical trial data.
Our proposed OS prediction workflow achieved an area under the curve (AUC) of 0.86 on the public dataset and 0.72 on the institutional clinical trial dataset to classify patients into 2 OS classes as long-survivors (>12 months) and short-survivors (<12 months), despite the large variation in Bas-mpMRI protocols. In addition, as part of the intermediate results, the proposed workflow can also provide detailed GBM sub-regions auto-segmentation with a whole tumor Dice score of 0.91.
Our study demonstrates the feasibility of employing this DL-based end-to-end workflow to predict the OS of patients with GBM using only the pre-resection Bas-mpMRIs. This DL-based workflow can be potentially applied to assist timely clinical decision-making.
准确且自动化的早期生存预测对于胶质母细胞瘤（GBM）患者至关重要，因为其预后较差，需要及时做出治疗决策。为满足这一需求，我们使用多机构公共数据集，开发了一种基于深度学习（DL）的端到端工作流程，用于使用切除前的基本结构多参数磁共振图像（Bas-mpMRI）预测GBM患者的总生存期（OS），并在前瞻性机构临床试验中使用独立患者数据集对其进行评估。
所提出的端到端工作流程包括一个颅骨剥离模型、一个GBM子区域分割模型和一个基于集成学习的OS预测模型。分割模型利用去除颅骨后的Bas-mpMRI对三个GBM子区域进行分割。分割后的GBM被输入到基于对比学习的OS预测模型中，将患者分类到不同的生存组。我们的数据集包括来自医学图像计算和计算机辅助干预（MICCAI）脑肿瘤分割（BraTS）2020挑战赛的多机构公共数据集（235例患者）以及来自一项5分次立体定向放射外科（SRS）临床试验的机构数据集（19例GBM患者）。每个数据条目包括术前Bas-mpMRI、生存天数和患者年龄。SRS临床试验数据还提供基本临床特征。多机构公共数据集用于工作流程建立（90%的数据）和初始验证（10%的数据）。然后在机构临床试验数据上评估经过验证的工作流程。
我们提出的OS预测工作流程在公共数据集上实现了曲线下面积（AUC）为0.86，在机构临床试验数据集上为0.72，可将患者分为两个OS类别，即长期存活者（>12个月）和短期存活者（<12个月），尽管Bas-mpMRI协议存在很大差异。此外，作为中间结果的一部分，所提出的工作流程还可以提供详细的GBM子区域自动分割，全肿瘤Dice评分为0.91。
我们的研究证明了采用这种基于DL的端到端工作流程仅使用切除前的Bas-mpMRI预测GBM患者OS的可行性。这种基于DL的工作流程有可能应用于协助及时的临床决策。
