Improved Prediction of Surgical Resectability in Patients with Glioblastoma using an Artificial Neural Network

Abstract

In managing a patient with glioblastoma (GBM), a surgeon must carefully consider whether sufficient tumour can be removed so that the patient can enjoy the benefits of decompression and cytoreduction, without impacting on the patient's neurological status. In a previous study we identified the five most important anatomical features on a pre-operative MRi that are predictive of surgical resectability and used them to develop a simple, objective, and reproducible grading system. The objective of this study was to apply an artificial neural network (ANN) to improve the prediction of surgical resectability in patients with GBM. prospectively maintained databases were searched to identify adult patients with supratentorial GBM that underwent craniotomy and resection. performance of the Ann was evaluated against logistic regression and the standard grading system by analysing their Receiver operator characteristic (Roc) curves; Area Under curve (AUc) and accuracy were calculated and compared using Wilcoxon signed rank test with a value of p < 0.05 considered statistically significant. In all, 135 patients were included, of which 33 (24.4%) were found to have complete excision of all contrast-enhancing tumour. The AUC and accuracy were significantly greater using the ANN compared to the standard grading system (0.87 vs. 0.79 and 83% vs. 80% respectively; p < 0.01 in both cases). In conclusion, an Ann allows for the improved prediction of surgical resectability in patients with GBM.

Improved prediction of postoperative pediatric cerebellar mutism syndrome using an artificial neural network

“…Indeed, given the high reported accuracy of our ANN as a neurosurgical predictive model when trained on a dataset of 135 patients, training on this large subset should not negatively impact the performance of the ANN. 15 …”

“…We implement a previously reported ANN with proven accuracy within neurosurgery. 15 A complete description of our computational approach is presented in Supplementary Material .…”

“…Indeed, the efficacy of this learning framework on relatively small datasets within neurosurgery has recently been shown. 14 , 15 …”

Second surgery for progressive glioblastoma: a multi‐centre questionnaire and cohort‐based review of clinical decision‐making and patient outcomes in current practice

“…This was a retrospective analysis of a selected study cohort, so the findings may not be generalisable. Moreover, predicted extent of tumour resection based on an individual patient's imaging is contentious and can vary between surgeons, although scoring systems, artificial intelligence analysis and cloud-based systems for consensus gathering may help [21,22]. Importantly, subtotal resection may still improve patient symptoms, and patients could potentially benefit from relatively modest debulking where recent tumour tissue for molecular analysis is required for entry into a clinical trial.…”

Second Surgery for Progressive Glioblastoma: A Multi-Centre Questionnaire and Cohort-Based Review of Clinical Decision-Making and Patient Outcomes in Current Practice

“…Moreover, predicted extent of tumour resection based on an individual patient's imaging is contentious and can vary between surgeons, although scoring systems, arti cial intelligence analysis and cloud-based systems for consensus gathering may help. [14,15] Importantly, subtotal resection may still improve patient symptoms, and patients could potentially bene t from relatively modest debulking where recent tumour tissue for molecular analysis is required for entry into a clinical trial. Whatever the surgical goals, maintenance or improving of quality of life are paramount; 90% of our questionnaire respondents agreed.…”