# Drawing the Line: From U-Net-Based Glioblastoma Segmentation to Machine Learning-Driven Survival Prediction

## TL;DR

This study uses AI to segment brain tumors and predict patient survival, showing that tumor size and features correlate with outcomes.

## Contribution

The integration of AI-based segmentation with multi-model machine learning for glioblastoma survival prediction is novel.

## Key findings

- Larger glioblastoma tumors correlate with shorter post-treatment survival.
- Necrotic tumor patterns affect survival rates and therapy response.
- Neural Networks and Random Forest models effectively predict patient outcomes using imaging biomarkers.

## Abstract

Background/Objectives: Glioblastoma (GB) remains the most prevalent primary malignant brain tumor in adults, characterized by its aggressive nature and poor prognosis. The present study endeavored to contribute to the development of advanced computational tools for neuro-oncology by integrating artificial intelligence (AI)-based segmentation and multi-model machine learning (ML) approaches. Methods: A retrospective analysis was conducted on patients with GB. AI-driven algorithms were utilized to perform volumetric segmentation of GB. These quantitative metrics were subsequently integrated into a multi-model ML framework to analyze correlations with patient survival and evaluate the predictive accuracy of the resulting models. Results: A total of 79 patients were ultimately included in the study after meeting all eligibility criteria. The results showed that larger GB tumors were associated with shorter post-treatment survival. Necrotic patterns within GB tumors impacted patient survival rates and response to therapy. Quantitative volumetric analysis of tumor enhancement, shape features, and morphological metrics were associated with patient outcomes. The Neural Network remained the top ML model performer overall for discrimination, but the Random Forest model also showed strong practical performance. Conclusions: As a summary, our study contributes to the development of advanced computational tools for neuro-oncology by integrating AI-based segmentation and multi-model ML approaches, and the results highlight the importance of imaging biomarkers in understanding GB prognosis.