Skip to main content

ORIGINAL RESEARCH article

Front. Cell Dev. Biol.
Sec. Molecular and Cellular Pathology
Volume 12 - 2024 | doi: 10.3389/fcell.2024.1484880
This article is part of the Research Topic Artificial Intelligence Applications in Chronic Ocular Diseases, Volume II View all 5 articles

Multi-resolution Visual Mamba with Multi-directional Selective Mechanism for Retinal Disease Detection

Provisionally accepted
Qiankun Zuo Qiankun Zuo 1Zhengkun Shi Zhengkun Shi 1Bo Liu Bo Liu 2Na Ping Na Ping 1Jiangtao Wang Jiangtao Wang 1Xi Cheng Xi Cheng 1Kexin Zhang Kexin Zhang 1Jia Guo Jia Guo 1*Yixian Wu Yixian Wu 3Jin Hong Jin Hong 2*
  • 1 Hubei University of Economics, Wuhan, Hubei Province, China
  • 2 Nanchang University, Nanchang, Jiangxi Province, China
  • 3 Beijing Institute of Petrochemical Technology, Beijing, Beijing Municipality, China

The final, formatted version of the article will be published soon.

    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. 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 multiscale 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. 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. 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.

    Keywords: Retinal disease detection, State space model, global-local feature, Multi-scale fusion, multi-directional selective learning

    Received: 22 Aug 2024; Accepted: 20 Sep 2024.

    Copyright: © 2024 Zuo, Shi, Liu, Ping, Wang, Cheng, Zhang, Guo, Wu and Hong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Jia Guo, Hubei University of Economics, Wuhan, Hubei Province, China
    Jin Hong, Nanchang University, Nanchang, 330031, Jiangxi Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.