Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AD-Lite Net: A Lightweight and Concatenated CNN Model for Alzheimer's Detection from MRI Images

Santanu Roy, Archit Gupta, Shubhi Tiwari, Palak Sahu

TL;DR

This research has proposed a novel AD-Lite Net model (trained from scratch), that has outperformed all the existing CNN models, and one recent trend Vision Transformer (ViT) model by a significant margin.

Abstract

Alzheimer's Disease (AD) is a non-curable progressive neurodegenerative disorder that affects the human brain, leading to a decline in memory, cognitive abilities, and eventually, the ability to carry out daily tasks. Manual diagnosis of Alzheimer's disease from MRI images is fraught with less sensitivity and it is a very tedious process for neurologists. Therefore, there is a need for an automatic Computer Assisted Diagnosis (CAD) system, which can detect AD at early stages with higher accuracy. In this research, we have proposed a novel AD-Lite Net model (trained from scratch), that could alleviate the aforementioned problem. The novelties we bring here in this research are, (I) We have proposed a very lightweight CNN model by incorporating Depth Wise Separable Convolutional (DWSC) layers and Global Average Pooling (GAP) layers. (II) We have leveraged a ``parallel concatenation block'' (pcb), in the proposed AD-Lite Net model. This pcb consists of a Transformation layer (Tx-layer), followed by two convolutional layers, which are thereby concatenated with the original base model. This Tx-layer converts the features into very distinct kind of features, which are imperative for the Alzheimer's disease. As a consequence, the proposed AD-Lite Net model with ``parallel concatenation'' converges faster and automatically mitigates the class imbalance problem from the MRI datasets in a very generalized way. For the validity of our proposed model, we have implemented it on three different MRI datasets. Furthermore, we have combined the ADNI and AD datasets and subsequently performed a 10-fold cross-validation experiment to verify the model's generalization ability. Extensive experimental results showed that our proposed model has outperformed all the existing CNN models, and one recent trend Vision Transformer (ViT) model by a significant margin.

AD-Lite Net: A Lightweight and Concatenated CNN Model for Alzheimer's Detection from MRI Images

TL;DR

This research has proposed a novel AD-Lite Net model (trained from scratch), that has outperformed all the existing CNN models, and one recent trend Vision Transformer (ViT) model by a significant margin.

Abstract

Alzheimer's Disease (AD) is a non-curable progressive neurodegenerative disorder that affects the human brain, leading to a decline in memory, cognitive abilities, and eventually, the ability to carry out daily tasks. Manual diagnosis of Alzheimer's disease from MRI images is fraught with less sensitivity and it is a very tedious process for neurologists. Therefore, there is a need for an automatic Computer Assisted Diagnosis (CAD) system, which can detect AD at early stages with higher accuracy. In this research, we have proposed a novel AD-Lite Net model (trained from scratch), that could alleviate the aforementioned problem. The novelties we bring here in this research are, (I) We have proposed a very lightweight CNN model by incorporating Depth Wise Separable Convolutional (DWSC) layers and Global Average Pooling (GAP) layers. (II) We have leveraged a ``parallel concatenation block'' (pcb), in the proposed AD-Lite Net model. This pcb consists of a Transformation layer (Tx-layer), followed by two convolutional layers, which are thereby concatenated with the original base model. This Tx-layer converts the features into very distinct kind of features, which are imperative for the Alzheimer's disease. As a consequence, the proposed AD-Lite Net model with ``parallel concatenation'' converges faster and automatically mitigates the class imbalance problem from the MRI datasets in a very generalized way. For the validity of our proposed model, we have implemented it on three different MRI datasets. Furthermore, we have combined the ADNI and AD datasets and subsequently performed a 10-fold cross-validation experiment to verify the model's generalization ability. Extensive experimental results showed that our proposed model has outperformed all the existing CNN models, and one recent trend Vision Transformer (ViT) model by a significant margin.
Paper Structure (10 sections, 5 equations, 3 figures, 3 tables)

This paper contains 10 sections, 5 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. MRI Images Dataset and Its Challenges
  3. Contributions
  4. Methodology
  5. Alzheimer's Detection-Lite Network (AD-Lite Net)
  6. Mathematical Analysis of AD Lite-Net
  7. Results and Analysis
  8. Training Specifications
  9. Experimental results comparisons and analysis
  10. Conclusion and Future Work

Figures (3)

  • Figure 1: Block diagram of the proposed model AD-Lite Net
  • Figure 2: First row represents the original MRI images, 2nd row represents the images after passing it through Tx-layer
  • Figure 3: Validation graph comparison of proposed AD-Lite Net with vs AD-Lite Net without pcb, blue line indicates performance of AD-Lite without pcb and green line indicates performance of AD-Lite with pcb; (a) Accuracy vs epochs, (b) Recall vs epochs, (c) Precision vs epochs, (d) Loss vs Epochs