Prediction of Alzheimer's Disease Progression Using Longitudinal Brain MRI Data and GANs
- Resource Type
- Conference
- Authors
- Singh, Kamred Udham; More, Ajit; Verma, Rajeshwar; Jain, Dhananjay kumar; Somasekar, J.; Pandey, Saroj Kumar
- Source
- 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), 2023 International Conference on. 1:1-6 Dec, 2023
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
General Topics for Engineers
Geoscience
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Industries
Technological innovation
Ethics
Magnetic resonance imaging
Transforms
Medical services
Predictive models
Alzheimer's Disease
Generative Adversarial Networks
Longitudinal Brain MRI
Predictive Model
Disease Progression
- Language
This research introduces a new method for predicting the course of Alzheimer's disease by combining longitudinal brain MRI data with Generative Adversarial Networks (GANs). Using additional information from reputable repositories, we carried out a descriptive study by applying a deductive technique and an interpretivist mindset. The GAN exhibited remarkable efficacy in producing lifelike MRI pictures by accurately identifying minute structural alterations that signify the advancement of the disease. The predictive model outperformed previous techniques with its high sensitivity and specificity. Comparison with well-established methods demonstrated our GAN-based approach's greater accuracy. Clinical validation, ethical issues, and multi-modal data integration should be the main areas of future research. This novel approach has the potential to completely transform Alzheimer's disease early detection and treatment programs.