A non-contrast CT-based multi-task learning framework for co-segmenting hematoma and edema and predicting hematoma expansion in spontaneous intracerebral hemorrhage
British Journal of Radiology · 2026
DOI: 10.1093/bjr/tqag179 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift British Journal of Radiology, 2026. Verfasst von Lu Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The Third Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China. Hauptthemen laut MEDLINE: Cerebral Hemorrhage, Hematoma, Tomography, X-Ray Computed, Brain Edema. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Natural Science Foundation of Chongqing, China, Chongqing medical scientific research project.
Abstract (Originalsprache)
Objectives
To develop a multi-task learning (MTL) framework for the simultaneous segmentation of spontaneous intracerebral hemorrhage (sICH) and perihematomal edema (PHE), along with the prediction of hematoma expansion (HE).
Methods
This multicenter retrospective study collected baseline noncontrast CT (NCCT) images of 981 patients with sICH from 4 centers, with 429 cases for training, 183 cases for internal validation, and 369 cases for external testing. A multi-task sICH model (MTsICHM) was designed to simultaneously segment hematoma and PHE and predict HE, which employs a hard parameter-sharing architecture based on a 3D U-Net backbone. The model processes dual-window NCCT inputs and generates 3 outputs: a binary hematoma mask, a binary PHE mask, and a binary HE label. For comparative evaluation and ablation studies, 4 control models were constructed: a multi-task segmentation comparative model, a multi-task classification comparative model, a single-task segmentation comparative model, and a single-task classification comparative model.
Results
For hematoma segmentation, MTsICHM achieved mean Dice of 0.909 and Intersection over Union of 0.872; for PHE segmentation, it attained 0.686 and 0.644, respectively, consistently outperforming the comparative models. For HE prediction, it yielded an AUC of 0.888, with corresponding accuracy, sensitivity, and specificity of 0.765, 0.949, and 0.710.
Conclusions
The MTsICHM accurately segments hematoma and PHE while effectively predicting HE, demonstrating substantial potential for clinical application. Advances in knowledge MTsICHM simultaneously quantifies hematoma and PHE and predicts HE from a single NCCT, with high consistency with manual segmentation and clinical utility for risk identification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, The Third Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China.
- Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing 400010, China.
- Department of Radiology, The Nanchong Central Hospital, Sichuan 637000, China.
- The Second Clinical College of Chongqing Medical University, Chongqing 400010, China.
- Key Laboratory of Intelligent Processing and Applications for Medical Imaging Big Data, Chongqing 400010, China.
ORCID-Profile: Lu Zhou, Zhiming Zhou
Förderung
- Natural Science Foundation of Chongqing, China
- Chongqing medical scientific research project
Zitieren
APA
Zhou, L., Zhou, J., Zhou, H., Xu, H., & Zhou, Z. (2026). A non-contrast CT-based multi-task learning framework for co-segmenting hematoma and edema and predicting hematoma expansion in spontaneous intracerebral hemorrhage. British Journal of Radiology. https://doi.org/10.1093/bjr/tqag179
Vancouver
Zhou L, Zhou J, Zhou H, Xu H, Zhou Z. A non-contrast CT-based multi-task learning framework for co-segmenting hematoma and edema and predicting hematoma expansion in spontaneous intracerebral hemorrhage. British Journal of Radiology. 2026. doi:10.1093/bjr/tqag179
BibTeX
@article{Zhou2026,
author = {Zhou, Lu and Zhou, Jinhua and Zhou, Hongli and Xu, Hong and Zhou, Zhiming},
title = {A non-contrast CT-based multi-task learning framework for co-segmenting hematoma and edema and predicting hematoma expansion in spontaneous intracerebral hemorrhage},
journal = {British Journal of Radiology},
year = {2026},
doi = {10.1093/bjr/tqag179}
}
EUVIMED