Clinical and surgical decisions for glioblastoma patients depend on a tumor imaging-based evaluation. Artificial Intelligence (AI) can be applied to magnetic resonance imaging (MRI) assessment to support clinical practice, surgery planning and prognostic predictions. In a real-world context, the current obstacles for AI are low-quality imaging and postoperative reliability. The aim of this study is to train an automatic algorithm for glioblastoma segmentation on a clinical MRI dataset and to obtain reliable results both pre- and post-operatively. The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by a histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to perform the segmentation task on postoperative MRIs. The training was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdorff 95% (H95). In preoperative scenario, overall DS is 91.09 (± 0.60) and H95 is 8.35 (± 1.12), considering tumor core, enhancing tumor and whole tumor (ET and edema). In postoperative context, overall DS is 72.31 (± 2.88) and H95 is 23.43 (± 7.24), considering resection cavity (RC), gross tumor volume (GTV) and whole tumor (WT). Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs. The performances achieved by the algorithm are consistent with previous literature for both pre-operative and post-operative glioblastoma’s MRI evaluation. Through the proposed algorithm, it is possible to reduce the impact of low-quality images and missing sequences.

中文翻译：

---

基于深度学习的术后胶质母细胞瘤 MRI 分割算法：一种有前途的肿瘤负荷评估新工具

胶质母细胞瘤患者的临床和手术决策取决于基于肿瘤成像的评估。人工智能（AI）可应用于磁共振成像（MRI）评估，以支持临床实践、手术计划和预后预测。在现实世界中，人工智能当前的障碍是低质量的成像和术后可靠性。本研究的目的是在临床 MRI 数据集上训练胶质母细胞瘤分割的自动算法，并在术前和术后获得可靠的结果。本研究使用的数据集包含来自 71 名经组织学证实的 IV 级胶质瘤患者的 237 幅 MRI（71 幅术前和 166 幅术后）MRI。实现的 U-Net 架构通过迁移学习进行训练，以在术后 MRI 上执行分割任务。首先在 BraTS2021 数据集上进行训练，用于术前分割。使用 DICE 评分 (DS) 和 Hausdorff 95% (H95) 评估绩效。术前情况下，考虑肿瘤核心、增强肿瘤和整个肿瘤（ET 和水肿），总体 DS 为 91.09（± 0.60），H95 为 8.35（± 1.12）。在术后情况下，考虑到切除腔 (RC)、肿瘤大体体积 (GTV) 和整个肿瘤 (WT)，总体 DS 为 72.31 (± 2.88)，H95 为 23.43 (± 7.24)。值得注意的是，RC 分割在术后 MRI 中获得的平均 DS 为 63.52 (± 8.90)。该算法实现的性能与之前文献中术前和术后胶质母细胞瘤 MRI 评估的结果一致。通过所提出的算法，可以减少低质量图像和丢失序列的影响。