A deep learning–based model for postoperative resection assessment in glioblastoma: A comparative study
Neurosurgical Review · 13.04.2026 · 49 (1)
DOI: 10.1007/s10143-026-04255-4 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Neurosurgical Review, online erschienen am 13.04.2026. Verfasst von Joon-Seok Kim und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine, The Catholic University of Korea, Seoul, South Korea. Hauptthemen laut MEDLINE: Glioblastoma, Brain Neoplasms, Deep Learning. Die Arbeit nennt 30 Literaturangaben.
Abstract (Originalsprache)
Background
Post-operative imaging of glioblastoma presents unique challenges for tumor segmentation due to surgical cavities, hemorrhage, and treatment-related changes. Although multiple open-source artificial intelligence (AI) tools have demonstrated strong performance in pre-operative settings, their utility in post-operative assessment has been insufficiently validated. Thus, we sought to develop an AI-based model for segmentation of postoperative images and to evaluate its performance.
Method
Our newly developed subtraction-based AI-based segmentation model (Dynapex BT) was tested on the LUMIERE and RHUH-GBM dataset, publicly available cohorts. Its performance was evaluated in three domains: (1) extent of resection (EOR) classification by experts, (2) segmentation performance for residual tumors with non-gross total resection, and (3) correlation between EOR classification and measured residual tumor volume. Performance of our model was compared with that of DeepBraTumIA, a widely used commercially available U-Net-based brain tumor segmentation tool.
Results
In the LUMIERE cohort, Dynapex BT demonstrated higher GTR classification accuracy compared to DeepBraTumIA (0.80 vs. 0.58). Dynapex BT also achieved significantly better segmentation performance compared to DeepBraTumIA (DSC: 0.815 vs. 0.406, p = 0.002; precision: 0.771 vs. 0.366, p < 0.001; recall: 0.888 vs. 0.583, p = 0.019). Dynapex BT maintained GTR classification accuracy in expert-annotated validation cohort (RHUH-GBM) of 0.8161.
Conclusion
Our automated postoperative segmentation model outperformed a widely used commercial U-Net-based model not only in segmentation accuracy but also in clinically relevant endpoints. Future studies in larger, multi-institutional cohorts are warranted to evaluate its clinical utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medicine, The Catholic University of Korea, Seoul, South Korea.
- Department of Radiology and Research Institute of Radiology, College of Medicine, University of Ulsan, Asan Medical Center, Seoul, South Korea.
- Dynapex Co., Ltd, Seoul, Republic of Korea.
- Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 222 Banpo-daero Seocho-gu, Seoul, 06591, Republic of Korea.
- Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 222 Banpo-daero Seocho-gu, Seoul, 06591, Republic of Korea. ilahshin@gmail.com.
- Department of Neurosurgery, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 222 Banpo-daero Seocho-gu, Seoul, 06591, Republic of Korea. nsstp@catholic.ac.kr.
Zitieren
APA
Kim, J. S., Ahn, J., Park, J. E., Kim, H. S., Kim, N., Ahn, K. J., Shin, I., & Ahn, S. (2026). A deep learning–based model for postoperative resection assessment in glioblastoma: A comparative study. Neurosurgical Review, 49(1). https://doi.org/10.1007/s10143-026-04255-4
Vancouver
Kim JS, Ahn J, Park JE, Kim HS, Kim N, Ahn KJ, et al. A deep learning–based model for postoperative resection assessment in glioblastoma: A comparative study. Neurosurgical Review. 2026;49(1). doi:10.1007/s10143-026-04255-4
BibTeX
@article{Kim2026,
author = {Kim, Joon-Seok and Ahn, Jaehyun and Park, Ji Eun and Kim, Ho Sung and Kim, NakYoung and Ahn, Kook-Jin and Shin, Ilah and Ahn, Stephen},
title = {A deep learning–based model for postoperative resection assessment in glioblastoma: A comparative study},
journal = {Neurosurgical Review},
year = {2026},
volume = {49},
number = {1},
doi = {10.1007/s10143-026-04255-4}
}
EUVIMED