Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI
PLOS One · 08.06.2026 · 21 (6) · e0350335
DOI: 10.1371/journal.pone.0350335 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 08.06.2026. Verfasst von Klara Mogensen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostics and Intervention, Biomedical Engineering and Radiation Physics, Umeå University, Umeå, Sweden. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Hydrocephalus, Normal Pressure, Cerebrospinal Fluid Shunts. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stiftelsen för Strategisk Forskning, Vetenskapsrådet, Future Artificial Intelligence Research Foundation.
Abstract (Originalsprache)
Objective
Idiopathic normal pressure hydrocephalus (INPH) is a treatable neurological condition, yet predicting which patients will benefit from a cerebrospinal fluid shunt remains challenging. Structural brain MRI is a core part of the diagnostic workup, but traditional radiological measures show limited predictive accuracy. This study aimed to assess whether deep learning and radiomics-based machine learning approaches can provide clinically useful predictions of shunt outcome based on preoperative MRI.
Methods
We investigated 149 shunted INPH patients with available preoperative T1-weighted, T2-weighted, and FLAIR images. Patients were classified as responders (n = 113) or non-responders (n = 36) based on postoperative gait speed improvement. For INPH, this is a large sample with typical outcome distribution. Three artificial intelligence approaches were tested: a late-fusion ensemble of multiple 3D convolutional neural networks; a multimodal intermediate fusion model; and radiomics-based machine learning models trained on features extracted from whole-brain masks. Models were assessed using 10-fold cross-validation. The best performing model on the validation set was selected from each approach. Performance metrics included the area under the receiving operating characteristic curve (AUROC), sensitivity, and specificity.
Results
Performance was considered poor in all models, and none reached an area under the receiving operating characteristic curve above 70%. Of the three methodologies, the best performance was achieved with a radiomics-based model (Linear Discriminant Analysis classifier on T1-weighted images) which achieved an AUROC of 63.7%. In a reduced subset of clearly separated responders and non-responders (n = 72), the best model (late fusion ensemble of 5 convolutional neural networks) reached an AUROC of 69.2%.
Conclusions
Despite the use of advanced artificial intelligence techniques, structural MRI alone were insufficient for reliably predicting gait outcome after surgery in idiopathic normal pressure hydrocephalus. To capture the complexity of the condition and enable clinically meaningful predictions, our findings indicate the need for research investigating multimodal input and using large multi-center datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Diagnostics and Intervention, Biomedical Engineering and Radiation Physics, Umeå University, Umeå, Sweden.
- Unit of Artificial Intelligence and Computer Systems, Department of Engineering, Università Campus Bio-Medico di Roma, Rome, Italy.
- Department of Diagnostics and Intervention, Diagnostic Radiology, Umeå University, Umeå, Sweden.
- Department of Clinical Sciences, Neurosciences, Umeå University, Umeå, Sweden.
- Umeå Center for Functional Brain Imaging, Umeå University, Umeå, Sweden.
ORCID-Profile: Klara Mogensen, Valerio Guarrasi, Anders Eklund, Sara Qvarlander
Förderung
- Stiftelsen för Strategisk Forskning
- Vetenskapsrådet
- Future Artificial Intelligence Research Foundation
- Regional agreement between Umeå University and Region Västerbotten
Zitieren
APA
Mogensen, K., Guarrasi, V., Behndig, S., Eriksson De Ryst, J., Soda, P., Eklund, A., Malm, J., & Qvarlander, S. (2026). Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI. PLOS One, 21(6), e0350335. https://doi.org/10.1371/journal.pone.0350335
Vancouver
Mogensen K, Guarrasi V, Behndig S, Eriksson De Ryst J, Soda P, Eklund A, et al. Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI. PLOS One. 2026;21(6):e0350335. doi:10.1371/journal.pone.0350335
BibTeX
@article{Mogensen2026,
author = {Mogensen, Klara and Guarrasi, Valerio and Behndig, Sofia and Eriksson De Ryst, Johan and Soda, Paolo and Eklund, Anders and Malm, Jan and Qvarlander, Sara},
title = {Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0350335},
doi = {10.1371/journal.pone.0350335}
}
EUVIMED