Deep learning from head CT scans to predict elevated intracranial pressure
Journal of Neuroimaging · 2024
DOI: 10.1111/jon.13241 ↗At a glance
Journal article in Journal of Neuroimaging, 2024. Written by Ryota Sato and 9 co-authors. Institution: Department of Neurosurgery, Sapporo Medical University, Sapporo, Japan. Major MEDLINE topics: Deep Learning, Tomography, X-Ray Computed, Intracranial Hypertension. Cited 3 times so far (Crossref); 35 references. Funded by: None.
Abstract (original language)
Background and Purpose Elevated intracranial pressure (ICP) resulting from severe head injury or stroke poses a risk of secondary brain injury that requires neurosurgical intervention. However, currently available noninvasive monitoring techniques for predicting ICP are not sufficiently advanced. We aimed to develop a minimally invasive ICP prediction model using simple CT images to prevent secondary brain injury caused by elevated ICP.
Methods
We used the following three methods to determine the presence or absence of elevated ICP using midbrain‐level CT images: (1) a deep learning model created using the Python (PY) programming language; (2) a model based on cistern narrowing and scaling of brainstem deformities and presence of hydrocephalus, analyzed using the statistical tool Prediction One (PO); and (3) identification of ICP by senior residents (SRs). We compared the accuracy of the validation and test data using fivefold cross‐validation and visualized or quantified the areas of interest in the models.
Results
The accuracy of the validation data for the PY, PO, and SR methods was 83.68% (83.42%‐85.13%), 85.71% (73.81%‐88.10%), and 66.67% (55.96%‐72.62%), respectively. Significant differences in accuracy were observed between the PY and SR methods. Test data accuracy was 77.27% (70.45%‐77.2%), 84.09% (75.00%‐85.23%), and 61.36% (56.82%‐68.18%), respectively.
Conclusions
Overall, the outcomes suggest that these newly developed models may be valuable tools for the rapid and accurate detection of elevated ICP in clinical practice. These models can easily be applied to other sites, as a single CT image at the midbrain level can provide a highly accurate diagnosis.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Neurosurgery, Sapporo Medical University, Sapporo, Japan.
ORCID profiles: Yukinori Akiyama
Funding
- None
Cite
APA
Sato, R., Akiyama, Y., Mikami, T., Yamaoka, A., Kamada, C., Sakashita, K., Takahashi, Y., Kimura, Y., Komatsu, K., & Mikuni, N. (2024). Deep learning from head CT scans to predict elevated intracranial pressure. Journal of Neuroimaging. https://doi.org/10.1111/jon.13241
Vancouver
Sato R, Akiyama Y, Mikami T, Yamaoka A, Kamada C, Sakashita K, et al. Deep learning from head CT scans to predict elevated intracranial pressure. Journal of Neuroimaging. 2024. doi:10.1111/jon.13241
BibTeX
@article{Sato2024,
author = {Sato, Ryota and Akiyama, Yukinori and Mikami, Takeshi and Yamaoka, Ayumu and Kamada, Chie and Sakashita, Kyoya and Takahashi, Yasuhiro and Kimura, Yusuke and Komatsu, Katsuya and Mikuni, Nobuhiro},
title = {Deep learning from head CT scans to predict elevated intracranial pressure},
journal = {Journal of Neuroimaging},
year = {2024},
doi = {10.1111/jon.13241}
}
EUVIMED