Deep Learning Pipeline for Automatic Segmentation, Classification, and Molecular Subtyping of Three Pediatric Posterior Fossa Tumors Using T2 ‐Weighted MRI
Journal of Magnetic Resonance Imaging · 07.09.2026
DOI: 10.1002/jmri.70532 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 07.09.2026. Verfasst von Ying Jin und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Beijing Outstanding Young Scientist Program, Youth Program of Beijing Natural Science Foundation, General Program of Beijing Natural Science Foundation.
Abstract (Originalsprache)
Background
Pediatric posterior fossa tumors vary in malignancy, treatment, and prognosis across tumor types and molecular subtypes, yet noninvasive preoperative differentiation remains challenging.
Purpose
To develop a deep learning (DL) pipeline using T2‐weighted (T2w) MR images to automatically segment pediatric posterior fossa tumors, differentiate tumor types (medulloblastoma [MB], ependymoma [EP], pilocytic astrocytoma [PA]), and classify molecular subtypes of MB and EP. Study Type Retrospective and prospective. Population 1305 patients (M/F: 828/477; 490 MB, 327 EP, and 488 PA) from three centers. For tumor segmentation and classification, PF‐nnU‐Net was developed on the training set ( n = 880) and validated on a validation set ( n = 220), an internal prospective test set ( n = 90), and two external independent test sets ( n = 68, n = 47). MB‐nnU‐Net was trained on 338 patients and tested on 63 patients for MB subtyping; a prior developed EP‐nnU‐Net was tested on 38 patients for EP subtyping. Field Strength/Sequence 1.5 T or 3 T MRI, axial T2w images (turbo spin echo). Assessment Three nnU‐Net‐based models: PF‐nnU‐Net and MB‐nnU‐Net for development, EP‐nnU‐Net for validation. Five‐fold cross‐validation was performed on training sets, followed by testing on independent test sets. Statistical Tests Dice similarity coefficient for segmentation. Accuracy, sensitivity, specificity, the area under the receiver operating characteristic curve (AUC), and Cohen's kappa for classification. A two‐sided p < 0.05 was considered significant.
Results
PF‐nnU‐Net achieved Dice scores of 0.94–0.96 and overall classification accuracy of 0.824–0.918 (multiclass Cohen's kappa: 0.722–0.873). MB‐nnU‐Net attained an overall accuracy of 0.794 (multiclass Cohen's kappa: 0.605), and EP‐nnU‐Net achieved an accuracy of 0.789 (Cohen's kappa: 0.538). Data Conclusion A fully automated DL pipeline was developed and validated to accurately segment pediatric posterior fossa tumors, differentiate tumor types (MB, EP, PA), and classify MB and EP molecular subtypes. Evidence Level 3. Technical Efficacy Stage 2.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Institute of Research and Clinical Innovations, Neusoft Medical Systerns co., Ltd., Beijing, China.
- Philips Healthcare, Shanghai, China.
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Department of Pathology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Department of Radiology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
ORCID-Profile: Ying Jin, Renlong Zhang, Jinyuan Weng, Xing Liu, Jun Qiu, Qiang Yue, Yaou Liu
Förderung
- Beijing Outstanding Young Scientist Program
- Youth Program of Beijing Natural Science Foundation
- General Program of Beijing Natural Science Foundation
Zitieren
APA
Jin, Y., Li, Y., Zhang, R., Zhuo, Z., Cheng, D., Weng, J., Mao, Y., Liu, Y., Dong, J., Wang, J., Ren, S., Liu, X., Du, J., Qiu, J., Yue, Q., Tian, Y., & Liu, Y. (2026). Deep Learning Pipeline for Automatic Segmentation, Classification, and Molecular Subtyping of Three Pediatric Posterior Fossa Tumors Using T2 ‐Weighted MRI. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.70532
Vancouver
Jin Y, Li Y, Zhang R, Zhuo Z, Cheng D, Weng J, et al. Deep Learning Pipeline for Automatic Segmentation, Classification, and Molecular Subtyping of Three Pediatric Posterior Fossa Tumors Using T2 ‐Weighted MRI. Journal of Magnetic Resonance Imaging. 2026. doi:10.1002/jmri.70532
BibTeX
@article{Jin2026,
author = {Jin, Ying and Li, Yangyang and Zhang, Renlong and Zhuo, Zhizheng and Cheng, Dan and Weng, Jinyuan and Mao, Yu and Liu, Yuwei and Dong, Jian and Wang, Jingxuan and Ren, Sikang and Liu, Xing and Du, Jiang and Qiu, Jun and Yue, Qiang and Tian, Yongji and Liu, Yaou},
title = {Deep Learning Pipeline for Automatic Segmentation, Classification, and Molecular Subtyping of Three Pediatric Posterior Fossa Tumors Using T2 ‐Weighted MRI},
journal = {Journal of Magnetic Resonance Imaging},
year = {2026},
doi = {10.1002/jmri.70532}
}
EUVIMED