Modern Challenges and Limitations in Medical Science Using Capsule Networks: A Comprehensive Review

Abstract

Capsule networks (CapsNet), an emerging neural network architecture, is now used in medical science to develop potential tools and applications. Particularly, in the domain of medical image analysis, CapsNet outperforms the existing CNN models in terms of disease detection and classification tasks, such as identifying abnormalities in retinal images for diabetic retinopathy and tumor detection. Moreover, capsule networks are now used in analyzing the electronic health records (EHRs) such as hospital readmissions and mortality rates. However, the implementation of capsule networks in medical science is still in the nascent stage facing several challenges due to the limited availability of high-quality medical data, lack of interpretability, and ethical considerations. In order to overcome these challenges, more research and collaboration works should be encouraged between medical professionals and artificial intelligence (AI) experts. This research study discusses about the modern challenges faced by medical science and how the challenges can be solved by using capsule networks and algorithms.