Skip to main navigation Skip to search Skip to main content

MAMAF-Net: Motion-aware and multi-attention fusion network for stroke diagnosis

    • University of Eastern Finland
    • Lapland University of Applied Sciences

    Research output: Contribution to journal › Article › Scientific › peer-review

    89 Downloads (Pure)

    Abstract

    Stroke is a major cause of mortality and disability worldwide from which one in four people are in danger of incurring in their lifetime. The pre-hospital stroke assessment plays a vital role in identifying stroke patients accurately to accelerate further examination and treatment in hospitals. Accordingly, the National Institutes of Health Stroke Scale (NIHSS), Cincinnati Pre-hospital Stroke Scale (CPSS) and Face Arm Speed Time (F.A.S.T.) are globally known tests for stroke assessment. However, the validity of these tests is skeptical in the absence of neurologists and access to healthcare may be limited. Therefore, in this study, we propose a motion-aware and multi-attention fusion network (MAMAF-Net) that can detect stroke from multiple examination videos. Contrary to other studies on stroke detection from video analysis, our study for the first time collected a dataset encapsulating transient ischemic attack (TIA), stroke, and healthy controls, and proposes an end-to-end solution using multiple video recordings of each subject. The proposed MAMAF-Net consists of motion-aware modules to sense the mobility of patients, attention modules to fuse the multi-input video data, and 3D convolutional layers to perform diagnosis from the attention-based extracted features. Experimental results over the collected Stroke-data dataset show that the proposed MAMAF-Net achieves a successful detection of stroke with the highest levels of 93.62% sensitivity, 91.19% F1-Score, and 0.7472 Kappa measure in addition to 3.92% increase in the AUC score compared to state-of-the-art deep learning models.

    Original languageEnglish
    Article number106381
    Number of pages11
    JournalBiomedical Signal Processing and Control
    Volume95
    DOIs
    Publication statusPublished - Sept 2024
    MoE publication typeA1 Journal article-refereed

    Funding

    This study was supported by Stroke-data project under Business Finland Grant 3617/31/2019. Authors would like to thank the study nurses Riitta Laitala, Saara Haatanen, Matti Pasanen, and Tanja Kumpulainen, research assistant Jari Paunonen, and senior scientist Timo Urhemaa for their contributions to data collection.

    UN SDGs

    This output contributes to the following UN Sustainable Development Goals (SDGs)

    1. SDG 3 - Good Health and Well-being
      SDG 3 Good Health and Well-being
    2. SDG 4 - Quality Education
      SDG 4 Quality Education
    3. SDG 10 - Reduced Inequalities
      SDG 10 Reduced Inequalities

    Keywords

    • Deep learning
    • NIHSS
    • Self-attention
    • Stroke
    • Transient ischemic attack

    Fingerprint

    Dive into the research topics of 'MAMAF-Net: Motion-aware and multi-attention fusion network for stroke diagnosis'. Together they form a unique fingerprint.

    Cite this