Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury
CNS Neuroscience & Therapeutics · 2024
DOI: 10.1111/cns.70119 ↗Kurz gefasst
Fachartikel in der Zeitschrift CNS Neuroscience & Therapeutics, 2024. Verfasst von Yang Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Disaster and Emergency Medicine, Tianjin University, Tianjin, China. Hauptthemen laut MEDLINE: Brain Injuries, Traumatic, Hematoma, Tomography, X-Ray Computed. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Purpose
To develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.
Methods
This study presents a cascade framework for two‐stage segmentation and multi‐label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14‐day in‐hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.
Results
The proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5‐fold cross‐validation.
Conclusions
The proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Disaster and Emergency Medicine, Tianjin University, Tianjin, China.
- Georgia Tech Shenzhen Institute, Tianjin University, Tianjin, China.
- College of Intelligence and Computing, Tianjin University, Tianjin, China.
Förderung
- National Key R&D Program of China
- National Key Research and Development Program of China
Zitieren
APA
Xu, Y., Fu, Q., Qu, M., Chen, J., Fan, J., Hou, S., & Lu, L. (2024). Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury. CNS Neuroscience & Therapeutics. https://doi.org/10.1111/cns.70119
Vancouver
Xu Y, Fu Q, Qu M, Chen J, Fan J, Hou S, et al. Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury. CNS Neuroscience & Therapeutics. 2024. doi:10.1111/cns.70119
BibTeX
@article{Xu2024,
author = {Xu, Yang and Fu, Qiuyu and Qu, Mengqi and Chen, Junyao and Fan, Jianqi and Hou, Shike and Lu, Lu},
title = {Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury},
journal = {CNS Neuroscience & Therapeutics},
year = {2024},
doi = {10.1111/cns.70119}
}
EUVIMED