Development and validation of a deep-broad ensemble model for early detection of Alzheimer's disease

Peixian Ma, Jing Wang, Zhiguo Zhou, C. L. Philip Chen, Junwei DuanFrontiers in Neuroscience 2023 · DOI

Abstract

Alzheimer’s disease (AD) remains a significant global health challenge, requiring early and accurate diagnosis to improve patient outcomes. While deep learning has advanced medical imaging analysis, traditional 3D models are often computationally expensive and slow to train. This paper presents a novel broad-deep ensemble model that combines 3D residual convolution for feature extraction with a Broad Learning System (BLS) for efficient classification. Utilizing the ADNI dataset, the model achieved over 92% accuracy in AD detection while reducing training time from nearly an hour to under two seconds.

Introduction

The diagnosis of Alzheimer's disease is often hindered by a shortage of specialized clinicians and the subtle nature of early brain changes. Artificial intelligence, particularly deep learning, has emerged as a vital tool for assisting clinicians. However, standard 3D Convolutional Neural Networks (CNNs) require significant hardware resources and long training cycles. To address these limitations, we propose a hybrid architecture that leverages the spatial feature extraction capabilities of 3D ResNet and the rapid learning speed of the Broad Learning System (BLS).

Methods: The Deep-Broad Architecture

The proposed model splits the diagnostic task into two phases: deep feature extraction and broad classification.

1. Deep Feature Extraction

The model utilizes a 3D Residual Convolution module based on the ResNet architecture. Unlike 2D models that process individual slices, this 3D module analyzes the entire MRI volume, preserving critical spatial relationships between brain structures. This ensures that the complex, three-dimensional atrophy patterns characteristic of AD are captured effectively.

2. Broad Learning System (BLS)

Instead of a traditional deep classifier, features are fed into a BLS. The BLS is a "flat" network that uses feature mapping and enhancement layers. A key advantage of BLS is its weight calculation method; rather than using iterative gradient descent, it employs ridge regression and pseudo-inverse coordinates to determine weights in a single step. This drastically reduces computational overhead and hardware dependency.

Datasets and Preprocessing

The study used data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), specifically the ADNI1 Complete 2Yr 3T standardized dataset. The cohort included 434 subjects (77 AD, 206 MCI, and 151 NC).

Sagittal MRI view used for 3D feature extraction.

Images were preprocessed by resampling to 1.5-mm isotropic voxels and cropping to a 224×224×128 grid. This focused the model's attention on the brain tissue while removing background noise.

Coronal MRI view showing structural features such as ventricle size.

Results

The ensemble model was benchmarked against several state-of-the-art architectures, including 3D-ResNet and VoxCNN.

  • Accuracy: The model achieved 92.65% accuracy for AD vs. Normal Control and 93.58% for AD vs. MCI. Even the challenging MCI vs. Normal Control task reached 84.68% accuracy.
  • Efficiency: While traditional models like VoxCNN required approximately 2,800 seconds to train, the proposed model completed training in just 1.3 to 1.6 seconds.
  • Clinical Validation: In a head-to-head comparison with a board-certified nuclear medicine physician, the model significantly outperformed human diagnosis (92% vs. 68.57% accuracy on the same test set), particularly in sensitivity.

Discussion and Conclusion

The deep-broad ensemble model demonstrates that high-performance medical AI does not always require "deeper" architectures. By combining 3D feature extraction with a broad classification layer, we achieve clinical-grade accuracy with unprecedented speed. This efficiency lowers the barrier for real-world clinical deployment, especially in resource-constrained environments. Future work will focus on expanding the dataset size and integrating explainable AI (XAI) to help clinicians interpret the model's findings.

Summary updated

Abstract

Introduction Alzheimer's disease (AD) is a chronic neurodegenerative disease of the brain that has attracted wide attention in the world. The diagnosis of Alzheimer's disease is faced with the difficulties of insufficient manpower and great difficulty. With the intervention of artificial intelligence, deep learning methods are widely used to assist clinicians in the early recognition of Alzheimer's disease. And a series of methods based on data input with different dimensions have been proposed. However, traditional deep learning models rely on expensive hardware resources and consume a lot of training time, and may fall into the dilemma of local optima. Methods In recent years, broad learning system (BLS) has provided researchers with new research ideas. Based on the three-dimensional residual convolution module and BLS, a novel broad-deep ensemble model based on BLS is proposed for the early detection of Alzheimer's disease. The Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI image dataset is used to train the model and then we compare the performance of proposed model with previous work and clinicians' diagnosis. Results The result of experiments demonstrate that the broad-deep ensemble model is superior to previously proposed related works, including 3D-ResNet and VoxCNN, in accuracy, sensitivity, specificity and F1. Discussion The proposed broad-deep ensemble model is effective for early detection of Alzheimer's disease. In addition, the proposed model does not need the pre-training process of its depth module, which greatly reduces the training time and hardware dependence.
BibTeX
@inproceedings{ma2023development,
  author = {Peixian Ma and Jing Wang and Zhiguo Zhou and C. L. Philip Chen and Junwei Duan and Junwei Duan},
  title = {{Development and validation of a deep-broad ensemble model for early detection of Alzheimer's disease}},
  booktitle = {Frontiers in Neuroscience},
  year = {2023},
  doi = {10.3389/fnins.2023.1137557},
}
Figure