article · Alexandria Engineering Journal
Early identification of Alzheimer's disease progression before symptoms appear is vital for timely treatment, yet analysing full three-dimensional brain scans demands considerable computational resources. To address this, an approximate rank pooling technique compresses three-dimensional magnetic resonance imaging volumes into dynamic two-dimensional image slices. These dynamic representations are integrated with cognitive features within a hybrid deep learning model combining convolutional neural networks and bidirectional long short-term memory networks. An explainable artificial intelligence method then generates visual explanations by tracking changes across brain regions over time. Tested on 1,692 subjects from the Alzheimer's Disease Neuroimaging Initiative dataset, the model achieved an area under the receiver operating characteristics curve of 94 percent using longitudinal three-time-step dynamic images, which improved by 2 percent when combined with cognitive data. The tool highlights specific structures such as the hippocampus in initial stages, expanding to other temporal regions as disease progresses.
Alzheimer's disease requires early intervention, but standard three-dimensional brain imaging is computationally intensive and difficult to interpret. By transforming scans into lighter formats and pairing them with visual explanations, this approach offers clearer insight into disease progression. Clinicians can see exactly which brain regions undergo structural changes over time, supporting safer, more transparent, and less error-prone medical decision-making for cognitive health monitoring.
This research could support clinical decision-support software for neurologists and healthcare providers monitoring dementia progression. By reducing the computational demands of MRI processing, it may facilitate more accessible diagnostic tools in smart healthcare systems. However, the framework represents applied and tested research validated on an existing retrospective dataset, meaning further prospective testing in real-world clinical environments is necessary before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Artificial intelligence (AI)-based diagnostic systems provide less error-prone and safer support to clinicians, enhancing the medical decision-making process. This study presents a smart and reliable healthcare framework for detecting Alzheimer's disease (AD) progression. Early detection of AD before the onset of clinical symptoms is the most crucial step in starting timely treatment. To predict the conversion of cognitively normal patients to those with AD, three-dimensional 3D magnetic resonance imaging (MRI) whole-brain neuroimaging methods have been extensively studied. However, depending on the 3D volume, this method is computationally expensive. To solve this problem, we used an approximate rank pooling method originally designed for video action recognition with a 3D MRI volume to obtain a compressed representation of multiple two-dimensional (2D) MRI slices. This study proposes a hybrid multimodal CNN-BiLSTM deep model for AD progression detection, in which the resulting dynamic 2D images are fused with cognitive features. Moreover, a novel explainable AI approach is proposed to provide visual explanations using the resulting longitudinal 2D dynamic images. Temporal explanations were provided by visualizing the affected brain regions captured using longitudinal 2D MRIs. By utilizing a sample of 1,692 subjects with multimodal data from the Alzheimer’s Disease Neuroimaging Initiative dataset, our method was assessed using a 10-fold cross-validation process. The model achieved an area under the receiver operating characteristics curve (AUC) of 94% using longitudinal 2D three-time-step dynamic image data. The fusion of 2D dynamic images with cognitive features enhanced the performance by 2% in terms of the AUC. Patients who gradually develop AD, show changes in various brain regions. For such patients, our system highlights the critical role of the hippocampus, medial amygdala, caudal hippocampus, and lateral amygdala at the initial time steps. In the late stages of AD, the system detects abnormalities in extra brain regions such as the medial temporal gyrus, superior temporal gyrus, fusiform gyrus, and caudal hippocampus; indicating that patients have completely progressed to AD.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.aej.2023.09.050
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
