Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion
Journal of Applied Clinical Medical Physics · 2024-11 · 25 (11)
DOI: 10.1002/acm2.14527 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 16.09.2024. Verfasst von Yuheng Pan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Computer and Information Engineering Department, Tianjin Chengjian University, Tianjin, China. Hauptthemen laut MEDLINE: Brain Neoplasms, Magnetic Resonance Imaging, Wavelet Analysis, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Tianjin Municipal Science and Technology Program, Science Research Program of Tianjin Education Committee.
Abstract (Originalsprache)
Background and objective Accurate segmentation of brain tumors from multimodal magnetic resonance imaging (MRI) holds significant importance in clinical diagnosis and surgical intervention, while current deep learning methods cope with situations of multimodal MRI by an early fusion strategy that implicitly assumes that the modal relationships are linear, which tends to ignore the complementary information between modalities, negatively impacting the model's performance. Meanwhile, long‐range relationships between voxels cannot be captured due to the localized character of the convolution procedure.
Method
Aiming at this problem, we propose a multimodal segmentation network based on a late fusion strategy that employs multiple encoders and a decoder for the segmentation of brain tumors. Each encoder is specialized for processing distinct modalities. Notably, our framework includes a feature fusion module based on a 3D discrete wavelet transform aimed at extracting complementary features among the encoders. Additionally, a 3D global context‐aware module was introduced to capture the long‐range dependencies of tumor voxels at a high level of features. The decoder combines fused and global features to enhance the network's segmentation performance.
Result
Our proposed model is experimented on the publicly available BraTS2018 and BraTS2021 datasets. The experimental results show competitiveness with state‐of‐the‐art methods.
Conclusion
The results demonstrate that our approach applies a novel concept for multimodal fusion within deep neural networks and delivers more accurate and promising brain tumor segmentation, with the potential to assist physicians in diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer and Information Engineering Department, Tianjin Chengjian University, Tianjin, China.
ORCID-Profile: Weijia Lu
Förderung
- National Natural Science Foundation of China
- Tianjin Municipal Science and Technology Program
- Science Research Program of Tianjin Education Committee
- Tianjin Research Innovation Project for Postgraduate Students
Zitieren
APA
Pan, Y., Yong, H., Lu, W., Li, G., & Cong, J. (2024). Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion. Journal of Applied Clinical Medical Physics, 25(11). https://doi.org/10.1002/acm2.14527
Vancouver
Pan Y, Yong H, Lu W, Li G, Cong J. Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion. Journal of Applied Clinical Medical Physics. 2024;25(11). doi:10.1002/acm2.14527
BibTeX
@article{Pan2024,
author = {Pan, Yuheng and Yong, Haohan and Lu, Weijia and Li, Guoyan and Cong, Jia},
title = {Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion},
journal = {Journal of Applied Clinical Medical Physics},
year = {2024},
volume = {25},
number = {11},
doi = {10.1002/acm2.14527}
}
EUVIMED