Deep learning based algorithm for postoperative glioblastoma MRI segmentation: a promising new tool for tumor burden assessment

This is the authors' abstract. We don't add key points for this paper.

Objective: 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. In a real-world context, the current obstacles for AI are low-quality imaging and post-operative 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. Methods: The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by an histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to segment the resection cavity (RC), the enhancing tumor volume (ET) and the whole tumor volume (WT) in post-operative images. The learning phase was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdroff 95%. Results: The overall mean DS are 91.09 (± 0.60) and 72.31 (± 2.88), respectively obtained in pre-operative and post-operative scenarios. The overall mean Hausdroff 95% is 8.35 (± 1.12) for preoperative segmentation and 23.43 (± 7.24) for the postoperative assessment. Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs. Conclusions: 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.