Multi-resolution visual Mamba with multi-directional selective mechanism for retinal disease detection
Frontiers in Cell and Developmental Biology · 11.10.2024 · 12
DOI: 10.3389/fcell.2024.1484880 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Cell and Developmental Biology, online erschienen am 11.10.2024. Verfasst von Qiankun Zuo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province.
Abstract (Originalsprache)
Introduction
Retinal diseases significantly impact patients’ quality of life and increase social medical costs. Optical coherence tomography (OCT) offers high-resolution imaging for precise detection and monitoring of these conditions. While deep learning techniques have been employed to extract features from OCT images for classification, convolutional neural networks (CNNs) often fail to capture global context due to their focus on local receptive fields. Transformer-based methods, on the other hand, suffer from quadratic complexity when handling long-range dependencies.
Methods
To overcome these limitations, we introduce the Multi-Resolution Visual Mamba (MRVM) model, which addresses long-range dependencies with linear computational complexity for OCT image classification. The MRVM model initially employs convolution to extract local features and subsequently utilizes the retinal Mamba to capture global dependencies. By integrating multi-scale global features, the MRVM enhances classification accuracy and overall performance. Additionally, the multi-directional selection mechanism (MSM) within the retinal Mamba improves feature extraction by concentrating on various directions, thereby better capturing complex, orientation-specific retinal patterns.
Results
Experimental results demonstrate that the MRVM model excels in differentiating retinal images with various lesions, achieving superior detection accuracy compared to traditional methods, with overall accuracies of 98.98\% and 96.21\% on two public datasets, respectively.
Discussion
This approach offers a novel perspective for accurately identifying retinal diseases and could contribute to the development of more robust artificial intelligence algorithms and recognition systems for medical image-assisted diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan, China.
- School of Information Engineering, Hubei University of Economics, Wuhan, China.
- Hubei Internet Finance Information Engineering Technology Research Center, Hubei University of Economics, Wuhan, China.
- School of Mathematics and Computer Science, Nanchang University, Nanchang, China.
- School of Mechanical Engineering, Beijing Institute of Petrochemical Technology, Beijing, China.
- School of Information Engineering, Nanchang University, Nanchang, China.
Förderung
- Natural Science Foundation of Hubei Province
Zitieren
APA
Zuo, Q., Shi, Z., Liu, B., Ping, N., Wang, J., Cheng, X., Zhang, K., Guo, J., Wu, Y., & Hong, J. (2024). Multi-resolution visual Mamba with multi-directional selective mechanism for retinal disease detection. Frontiers in Cell and Developmental Biology, 12. https://doi.org/10.3389/fcell.2024.1484880
Vancouver
Zuo Q, Shi Z, Liu B, Ping N, Wang J, Cheng X, et al. Multi-resolution visual Mamba with multi-directional selective mechanism for retinal disease detection. Frontiers in Cell and Developmental Biology. 2024;12. doi:10.3389/fcell.2024.1484880
BibTeX
@article{Zuo2024,
author = {Zuo, Qiankun and Shi, Zhengkun and Liu, Bo and Ping, Na and Wang, Jiangtao and Cheng, Xi and Zhang, Kexin and Guo, Jia and Wu, Yixian and Hong, Jin},
title = {Multi-resolution visual Mamba with multi-directional selective mechanism for retinal disease detection},
journal = {Frontiers in Cell and Developmental Biology},
year = {2024},
volume = {12},
doi = {10.3389/fcell.2024.1484880}
}
EUVIMED