LEVERAGING CONCEPT TECHNOLOGY IN MEDICAL APPLICATIONS FOR ALZHEIMER'S DISEASE
Abstract
The number of Alzheimer's disease (AD) cases is expected to double every two decades, and the need for effective diagnostic tools has become increasingly urgent to address this growing healthcare challenge. The hippocampus and magnetic resonance imaging (MRI) play a pivotal role in diagnosing AD. It could demonstrate utility in differentiating AD. Deep learning-based approaches to produce digital health technologies may offer valuable advantages to dementia researchers and clinicians as screening tools and diagnostic aids. The study aims to design a user interface (UI) for medical imaging apps to present the complexity of medical data and the critical nature of accurate interpretation. We found that our proposed model showed the best performance with more than 0.90 accuracy. From three views, axial view showed the highest performance, but coronal in MCI class showed the lower performance. However, the concept of interface design needs to consider the consistency, layout, and color of the design. We conclude that the detection performance is understandable to interpret the medical complexity region of MRI images. These result could be benefit for the medical apps, in order to create the interface design leveraging the deep learning models.
Downloads
References
Carrillo, M. C., Bain, L. J., Frisoni, G. B., & Weiner, M. W. (2012). Worldwide Alzheimer’s disease neuroimaging initiative. Alzheimer's & Dementia, 8(4), 337-342.
Forloni, G. (2020). Alzheimer’s disease: from basic science to precision medicine approach. BMJ Neurology Open, 2(2), e000079.
Horvat, M., Jelečević, L., & Gledec, G. (2022). A comparative study of YOLOv5 models performance for image localization and classification. Paper presented at the Central European Conference on Information and Intelligent Systems.
Khatri, U., & Kwon, G.-R. (2022). Alzheimer’s disease diagnosis and biomarker analysis using resting-state functional MRI functional brain network with multi-measures features and hippocampal subfield and amygdala volume of structural MRI. Frontiers in aging neuroscience, 14, 818871.
Kumar, M., Pilania, U., Thakur, S., & Bhayana, T. (2024). YOLOv5x-based Brain Tumor Detection for Healthcare Applications. Procedia Computer Science, 233, 950-959. Retrieved from https://www.sciencedirect.com/science/article/pii/S1877050924006446. doi:https://doi.org/10.1016/j.procs.2024.03.284
Lott, S. A., Streel, E., Bachman, S. L., Bode, K., Dyer, J., Fitzer-Attas, C., . . . Fromy, P. (2024). Digital Health Technologies for Alzheimer's Disease and Related Dementias: Initial Results from a Landscape Analysis and Community Collaborative Effort. The Journal of Prevention of Alzheimer's Disease, 11(5), 1480-1489. Retrieved from https://www.sciencedirect.com/science/article/pii/S2274580724006794. doi:https://doi.org/10.14283/jpad.2024.103
Pusparani, Y., Lin, C.-Y., Jan, Y.-K., Lin, F.-Y., Liau, B.-Y., Ardhianto, P., . . . Lung, C.-W. (2024). Deep Learning Applications in MRI-Based Detection of the Hippocampal Region for Alzheimer’s Diagnosis. IEEE Access.
Sarasua, I., Pölsterl, S., & Wachinger, C. (2022). Hippocampal representations for deep learning on Alzheimer's disease. Sci Rep, 12(1), 8619. doi:10.1038/s41598-022-12533-6
