ABSTRACT
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, 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. METHODS: 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). RESULTS: 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. 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.
ABSTRACT
BACKGROUND: Fluorescence-guided surgery has been increasingly used to support glioma surgery with the purpose of obtaining a maximal safe resection, in particular in high-grade gliomas, while its role is less definitely assessed in low-grade gliomas. METHODS: A systematic review was conducted. 5-aminolevulinic acid, sodium fluorescein, indocyanine green and tozuleristide were taken into account. The main considered outcome was the fluorescence rate, defined as the number of patients in whom positive fluorescence was detected out of the total number of patients. Only low-grade gliomas were considered, and data were grouped according to single fluorophores. RESULTS: 16 papers about 5-aminolevulinic acid, 4 about sodium fluorescein, 2 about indocyanine green and 1 about tozuleristide were included in the systematic review. Regarding 5-aminolevulinic acid, a total of 467 low-grade glioma patients were included, and fluorescence positivity was detected in 34 out of 451 Grade II tumors (7.3%); while in Grade I tumors, fluorescence positivity was detected in 9 out of 16 cases. In 16 sodium fluorescein patients, seven positive fluorescent cases were detected. As far as indocyanine is concerned, two studies accounting for six patients (three positive) were included, while for tozuleristide, a single clinical trial with eight patients (two positive) was retrieved. CONCLUSIONS: The current evidence does not support the routine use of 5-aminolevulinic acid or sodium fluorescein with a standard operating microscope because of the low fluorescence rates. New molecules, including tozuleristide, and new techniques for fluorescence detection have shown promising results; however, their use still needs to be clinically validated on a large scale.
