Drawing the Line: From U-Net-Based Glioblastoma Segmentation to Machine Learning-Driven Survival Prediction
Medical Sciences · 03.03.2026 · 14 (1) · 119
DOI: 10.3390/medsci14010119 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Sciences, online erschienen am 03.03.2026. Verfasst von Costin Chirica und 12 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Medicine, Grigore T. Popa University of Medicine and Pharmacy, 16 Universității Str., 700115 Iasi, Romania. Hauptthemen laut MEDLINE: Glioblastoma, Machine Learning, Brain Neoplasms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Medicine, Grigore T. Popa University of Medicine and Pharmacy, 16 Universității Str., 700115 Iasi, Romania.
- Faculty of Dental Medicine, Grigore T. Popa University of Medicine and Pharmacy, 16 Universității Str., 700115 Iasi, Romania.
- Faculty of Computer Science, Alexandru Ioan Cuza University, 700506 Iasi, Romania.
ORCID-Profile: Costin Chirica, Bogdan-Ionuț Dobrovăț, Laura-Elena Cucu, Daniela Pomohaci, Mihaela-Roxana Popescu, Alexandra Maștaleru, Maria Magdalena Leon
Zitieren
APA
Chirica, C., Dobrovăț, B. I., Chirica, S. I., Onicescu, O. M., Rotundu, A., Marciuc, E. A., Cucu, L. E., Pomohaci, D., Anghel, R. C., Popescu, M. R., Maștaleru, A., Haba, D., & Leon, M. M. (2026). Drawing the Line: From U-Net-Based Glioblastoma Segmentation to Machine Learning-Driven Survival Prediction. Medical Sciences, 14(1), 119. https://doi.org/10.3390/medsci14010119
Vancouver
Chirica C, Dobrovăț BI, Chirica SI, Onicescu OM, Rotundu A, Marciuc EA, et al. Drawing the Line: From U-Net-Based Glioblastoma Segmentation to Machine Learning-Driven Survival Prediction. Medical Sciences. 2026;14(1):119. doi:10.3390/medsci14010119
BibTeX
@article{Chirica2026,
author = {Chirica, Costin and Dobrovăț, Bogdan-Ionuț and Chirica, Sabina-Ioana and Onicescu, Oriana-Maria and Rotundu, Andreea and Marciuc, Emilia-Adriana and Cucu, Laura-Elena and Pomohaci, Daniela and Anghel, Răzvan-Constantin and Popescu, Mihaela-Roxana and Maștaleru, Alexandra and Haba, Danisia and Leon, Maria Magdalena},
title = {Drawing the Line: From U-Net-Based Glioblastoma Segmentation to Machine Learning-Driven Survival Prediction},
journal = {Medical Sciences},
year = {2026},
volume = {14},
number = {1},
pages = {119},
doi = {10.3390/medsci14010119}
}
EUVIMED