Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AlzhiNet: Traversing from 2DCNN to 3DCNN, Towards Early Detection and Diagnosis of Alzheimer's Disease

Romoke Grace Akindele, Samuel Adebayo, Paul Shekonya Kanda, Ming Yu

TL;DR

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the aging population, necessitating early and accurate diagnosis for effective disease management, and this approach represents a promising advancement in the early diagnosis and treatment planning for Alzheimer's disease.

Abstract

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the aging population, necessitating early and accurate diagnosis for effective disease management. In this study, we present a novel hybrid deep learning framework that integrates both 2D Convolutional Neural Networks (2D-CNN) and 3D Convolutional Neural Networks (3D-CNN), along with a custom loss function and volumetric data augmentation, to enhance feature extraction and improve classification performance in AD diagnosis. According to extensive experiments, AlzhiNet outperforms standalone 2D and 3D models, highlighting the importance of combining these complementary representations of data. The depth and quality of 3D volumes derived from the augmented 2D slices also significantly influence the model's performance. The results indicate that carefully selecting weighting factors in hybrid predictions is imperative for achieving optimal results. Our framework has been validated on the Magnetic Resonance Imaging (MRI) from Kaggle and MIRIAD datasets, obtaining accuracies of 98.9% and 99.99%, respectively, with an AUC of 100%. Furthermore, AlzhiNet was studied under a variety of perturbation scenarios on the Alzheimer's Kaggle dataset, including Gaussian noise, brightness, contrast, salt and pepper noise, color jitter, and occlusion. The results obtained show that AlzhiNet is more robust to perturbations than ResNet-18, making it an excellent choice for real-world applications. This approach represents a promising advancement in the early diagnosis and treatment planning for Alzheimer's disease.

AlzhiNet: Traversing from 2DCNN to 3DCNN, Towards Early Detection and Diagnosis of Alzheimer's Disease

TL;DR

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the aging population, necessitating early and accurate diagnosis for effective disease management, and this approach represents a promising advancement in the early diagnosis and treatment planning for Alzheimer's disease.

Abstract

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the aging population, necessitating early and accurate diagnosis for effective disease management. In this study, we present a novel hybrid deep learning framework that integrates both 2D Convolutional Neural Networks (2D-CNN) and 3D Convolutional Neural Networks (3D-CNN), along with a custom loss function and volumetric data augmentation, to enhance feature extraction and improve classification performance in AD diagnosis. According to extensive experiments, AlzhiNet outperforms standalone 2D and 3D models, highlighting the importance of combining these complementary representations of data. The depth and quality of 3D volumes derived from the augmented 2D slices also significantly influence the model's performance. The results indicate that carefully selecting weighting factors in hybrid predictions is imperative for achieving optimal results. Our framework has been validated on the Magnetic Resonance Imaging (MRI) from Kaggle and MIRIAD datasets, obtaining accuracies of 98.9% and 99.99%, respectively, with an AUC of 100%. Furthermore, AlzhiNet was studied under a variety of perturbation scenarios on the Alzheimer's Kaggle dataset, including Gaussian noise, brightness, contrast, salt and pepper noise, color jitter, and occlusion. The results obtained show that AlzhiNet is more robust to perturbations than ResNet-18, making it an excellent choice for real-world applications. This approach represents a promising advancement in the early diagnosis and treatment planning for Alzheimer's disease.
Paper Structure (33 sections, 5 equations, 9 figures, 8 tables)

This paper contains 33 sections, 5 equations, 9 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Pre-trained CNNs for feature extraction based on ResNet-18
  4. 2D-CNN Models
  5. 3D-CNN Models
  6. Contributions
  7. Methodology
  8. Model Architecture
  9. 2D Module
  10. 3D Module
  11. Hybrid Model Integration and Custom Loss Function
  12. Custom Loss Function
  13. Experimental and system Setup
  14. Setup of the Experiment
  15. Datasets
  16. ...and 18 more sections

Figures (9)

  • Figure 1: High-level overview of AlzhiNet Architecture. The framework processes input data through 2D and 3D modules, integrating their outputs via a custom loss function to produce the final output classes.
  • Figure 2: Detailed architecture of AlzhiNet hybrid model. The framework processes both 2D images through ResNet-18 and 3D volumes through 3D encoder layers, integrating their outputs via a custom loss function to produce the final classification output.
  • Figure 3: Visual depiction of standard brain MRI samples from Kaggle.
  • Figure 4: Visualization of Brain MRI Samples: (a) Different Views of MIRIAD MRI Images (b) Normal Control-CN (c) Alzheimer’s Disease (AD) brain imaging.
  • Figure 5: Generation of Augmented 3D volumes from 2D Brain Imaging Slices using diverse data Augmentation Techniques
  • ...and 4 more figures