Optimized Hybrid Deep Learning Framework for Early Detection of Alzheimer’s Disease
Author Information
Author(s): Gasmi Karim, Alyami Abdulrahman, Hamid Omer, Altaieb Mohamed O., Shahin Osama Rezk, Ben Ammar Lassaad, Chouaib Hassen, Shehab Abdulaziz
Primary Institution: Jouf University
Hypothesis
Can a hybrid deep learning framework improve the early detection of Alzheimer’s disease using neuroimaging data?
Conclusion
The proposed framework shows significant potential for accurately identifying early-stage Alzheimer’s disease, outperforming conventional diagnostic techniques.
Supporting Evidence
- The framework achieved a Scott’s Pi agreement score of 0.9907, indicating exceptional diagnostic accuracy.
- The method effectively mitigates the shortcomings of conventional diagnostic techniques.
- Utilizing an optimized weight selection mechanism enhances the model's performance.
- The study demonstrates the framework's scalability and adaptability for various neuroimaging datasets.
Takeaway
This study created a smart computer program that helps doctors find Alzheimer’s disease early by looking at brain scans.
Methodology
The study used a hybrid deep learning framework combining EfficientNetV2B3 and Inception-ResNetV2 models, optimized with a Cuckoo Search algorithm for weight selection.
Potential Biases
Potential biases may arise from the reliance on specific datasets and the generalizability of the model across diverse populations.
Limitations
The study may face challenges related to class imbalance in the dataset and the need for large labeled datasets for training.
Participant Demographics
The dataset included neuroimaging data from 461 participants, primarily older adults.
Statistical Information
P-Value
0.9907
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website