Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans
IEEE Transactions on Medical Imaging · 2024-06 · 43 (6) · 2303-2316
DOI: 10.1109/tmi.2024.3362879 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024-06. Verfasst von Hulin Kuang und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Ischemic Stroke, Neural Networks, Computer, Tomography, X-Ray Computed. Die Arbeit wurde bisher 90-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Science and Technology Innovation Program of Hunan Province.
Themen: Schlaganfall
Abstract (Originalsprache)
Lesion segmentation is a fundamental step for the diagnosis of acute ischemic stroke (AIS). Non-contrast CT (NCCT) is still a mainstream imaging modality for AIS lesion measurement. However, AIS lesion segmentation on NCCT is challenging due to low contrast, noise and artifacts. To achieve accurate AIS lesion segmentation on NCCT, this study proposes a hybrid convolutional neural network (CNN) and Transformer network with circular feature interaction and bilateral difference learning. It consists of parallel CNN and Transformer encoders, a circular feature interaction module, and a shared CNN decoder with a bilateral difference learning module. A new Transformer block is particularly designed to solve the weak inductive bias problem of the traditional Transformer. To effectively combine features from CNN and Transformer encoders, we first design a multi-level feature aggregation module to combine multi-scale features in each encoder and then propose a novel feature interaction module containing circular CNN-to-Transformer and Transformer-to-CNN interaction blocks. Besides, a bilateral difference learning module is proposed at the bottom level of the decoder to learn the different information between the ischemic and contralateral sides of the brain. The proposed method is evaluated on three AIS datasets: the public AISD, a private dataset and an external dataset. Experimental results show that the proposed method achieves Dices of 61.39% and 46.74% on the AISD and the private dataset, respectively, outperforming 17 state-of-the-art segmentation methods. Besides, volumetric analysis on segmented lesions and external validation results imply that the proposed method is potential to provide support information for AIS diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Science and Technology Innovation Program of Hunan Province
- Hubei Provincial Key Research and Development Program
- Fundamental Research Funds for the Central Universities of Central South University
- High Performance Computing Center of Central South University
- High Performance Computing Platformof the Huazhong University of Science and Technology
Zitieren
APA
Kuang, H., Wang, Y., Liu, J., Wang, J., Cao, Q., Hu, B., Qiu, W., & Wang, J. (2024). Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans. IEEE Transactions on Medical Imaging, 43(6), 2303-2316. https://doi.org/10.1109/tmi.2024.3362879
Vancouver
Kuang H, Wang Y, Liu J, Wang J, Cao Q, Hu B, et al. Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans. IEEE Transactions on Medical Imaging. 2024;43(6):2303-2316. doi:10.1109/tmi.2024.3362879
BibTeX
@article{Kuang2024,
author = {Kuang, Hulin and Wang, Yahui and Liu, Jin and Wang, Jie and Cao, Quanliang and Hu, Bo and Qiu, Wu and Wang, Jianxin},
title = {Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans},
journal = {IEEE Transactions on Medical Imaging},
year = {2024},
volume = {43},
number = {6},
pages = {2303--2316},
doi = {10.1109/tmi.2024.3362879}
}
EUVIMED