Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach
Diagnostic and Interventional Radiology · 2024
DOI: 10.4274/dir.2024.222088 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostic and Interventional Radiology, 2024. Verfasst von Mengtian Lu und 3 weiteren Autor:innen. Beteiligte Einrichtung: The First Affiliated Hospital of Hubei University of Science and Technology, Xianning Central Hospital, Department of Radiology, Xianning, China. Hauptthemen laut MEDLINE: Deep Learning, Cerebral Hemorrhage, Hematoma, Tomography, X-Ray Computed. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 1 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
PURPOSE: Spontaneous intracerebral hemorrhage (ICH) is the most severe form of stroke. The timely assessment of early hematoma enlargement and its proper treatment are of great significance in curbing the deterioration and improving the prognosis of patients with ICH. This study aimed to develop an automated hybrid approach to predict hematoma expansion in ICH. METHODS: The transfer learning method was applied to build a hybrid model based on a convolutional neural network (CNN) to predict the expansion of hematoma. The model integrated (1) a CNN for automated hematoma segmentation and (2) a CNN-based classifier for hematoma expansion prediction that incorporated both 2-dimensional images and the radiomics features of the 3-dimensional hematoma shape. RESULTS: The radiomics feature module had the highest area under the receiver operating characteristic curve (AUC) of 0.58, a precision of 0, a recall of 0, and an average precision (AP) of 0.26. The ResNet50 and Inception_v3 modules had AUCs of 0.79 and 0.93, a precision of 0.56 and 0.86, a recall of 0.42 and 0.75, and an AP of 0.51 and 0.85, respectively. Radiomic with Inception_v3 and Radiomic with ResNet50 had AUCs of 0.95 and 0.81, a precision of 0.90 and 0.57, a recall of 0.79 and 0.17, and an AP of 0.87 and 0.69, respectively. CONCLUSION: A model using deep learning and radiomics was successfully developed. This model can reliably predict the hematoma expansion of ICH with a fully automated process based on non-contrast computed tomography imaging. Furthermore, the radiomics fusion with the Inception_v3 model had the highest accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The First Affiliated Hospital of Hubei University of Science and Technology, Xianning Central Hospital, Department of Radiology, Xianning, China
- The Second Affiliated Hospital of Hubei University of Science and Technology, Department of Radiology, Xianning, China
- The First Affiliated Hospital of Hubei University of Science and Technology, Xianning Central Hospital, Department of Ultrasound, Xianning, China
ORCID-Profile: Mengtian Lu, Yaqi Wang, Jiaqiang Tian, Haifeng Feng
Zitieren
APA
Lu, M., Wang, Y., Tian, J., & Feng, H. (2024). Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach. Diagnostic and Interventional Radiology. https://doi.org/10.4274/dir.2024.222088
Vancouver
Lu M, Wang Y, Tian J, Feng H. Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach. Diagnostic and Interventional Radiology. 2024. doi:10.4274/dir.2024.222088
BibTeX
@article{Lu2024,
author = {Lu, Mengtian and Wang, Yaqi and Tian, Jiaqiang and Feng, Haifeng},
title = {Application of deep learning and radiomics in the prediction of hematoma expansion in intracerebral hemorrhage: a fully automated hybrid approach},
journal = {Diagnostic and Interventional Radiology},
year = {2024},
doi = {10.4274/dir.2024.222088}
}
EUVIMED