An end-to-end deep learning pipeline for hematoma expansion prediction in spontaneous intracerebral hemorrhage based on non-contrast computed tomography.
Authors
Affiliations (13)
Affiliations (13)
- Department of Radiology and Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, China.
- Sichuan Provincial Engineering Research Center of Intelligent Medical Imaging, West China Hospital, Sichuan University, Chengdu, China.
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
- Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, China.
- Department of Neurosurgery, The Fourth Affiliated Hospital of Guangxi Medical University, Liuzhou, China.
- Hunan Diantou Education Technology Co. Ltd., Changsha, China.
- Department of Radiology, Xiangya Hospital, Central South University, Changsha, China.
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China. [email protected].
- Department of Radiology, The First Affiliated Hospital of Army Medical University, Chongqing, China. [email protected].
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China. [email protected].
- Department of Radiology and Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, China. [email protected].
- Sichuan Provincial Engineering Research Center of Intelligent Medical Imaging, West China Hospital, Sichuan University, Chengdu, China. [email protected].
Abstract
Hematoma expansion (HE) is a critical therapeutic target in spontaneous intracerebral hemorrhage (sICH), yet its reliable early identification remains challenging. We developed an automated pipeline for HE prediction using non-contrast computed tomography from 2020 patients across five centers. The modular framework comprised automated segmentation, synthetic data augmentation, and Vision Transformer (ViT)-based classification. High-quality hematoma masks were generated by the full-scale U-Mamba model, identified as the optimal architecture through comprehensive benchmarking. Two augmented training sets were constructed using synthetic HE images from the Diffusion-UKAN model: UKAN-Balanced (HE: NHE = 1:1) and UKAN-Semibalanced (HE: NHE = 1:2). The ViT-1:2 classifier, trained on the UKAN-Semibalanced dataset, achieved a training set AUC of 0.815 and demonstrated robust cross-institutional generalization with external validation AUCs of 0.793 and 0.781 on two independent datasets. These findings suggest that the proposed modular approach provides a promising front-line tool for rapid HE risk stratification in acute care settings, with potentially improving clinical decision-making in sICH management.