S 3Net: a Synthesis-Segmentation-Spiking Network for Alzheimer's disease detection and segmentation.
Gandham Dhanush Varmaa1, Aravindkumar Sekar1, Vemisetty Anshul1
1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India.
Frontiers in Artificial Intelligence
|June 30, 2026
Summary
A new AI model, S3Net, accurately detects Alzheimer's disease (AD) from MRI scans by synthesizing images, segmenting lesions, and classifying with spiking networks. This approach shows high accuracy for early AD diagnosis.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Neurological Disorder Diagnosis
- Machine Learning for Healthcare
Background:
- Early and accurate detection of Alzheimer's disease (AD) is critical for effective clinical intervention.
- Magnetic Resonance Imaging (MRI) is a key modality for visualizing brain changes associated with AD.
- Current diagnostic methods can be limited in speed and accuracy, necessitating advanced computational approaches.
Purpose of the Study:
- To introduce a novel deep learning framework, S3Net (Synthesis-Segmentation-Spiking Network), for automated AD detection from MRI.
- To integrate synthetic MRI generation, pathology-aware segmentation, and spike-based classification within a unified model.
- To enhance the precision of lesion detection and classification for improved diagnostic performance.
Main Methods:
- A Synthesis Network, using a generative adversarial network (GAN), fuses original MRIs with lesion-only patches to preserve pathological details.
- A Segmentation Network employs an encoder-decoder architecture with skip connections and hybrid loss functions for precise lesion delineation.
- A Spiking Neural Network (SNN) classifies AD using fused features, leveraging Leaky Integrate-and-Fire neurons for event-driven computation.
Main Results:
- S3Net achieved high performance on the OASIS dataset, with an Accuracy of 95.1%, F1-score of 93.0%, and Intersection over Union (IoU) of 82.6%.
- The model demonstrated superior performance compared to existing state-of-the-art methods for AD detection.
- The integrated approach effectively preserved high-frequency pathological structures and enabled precise segmentation.
Conclusions:
- The S3Net model offers a robust and effective solution for automated Alzheimer's disease diagnosis using MRI data.
- The combination of synthesis, segmentation, and spiking neural networks shows significant clinical viability.
- This approach has the potential to improve early detection rates and facilitate timely patient management.
Related Concept Videos
01:29Alzheimer Disease l: Introduction
Alzheimer disease is a chronic, progressive, and irreversible neurodegenerative disorder and the most common cause of dementia in older adults. It leads to gradual neuronal loss, causing cognitive decline, behavioral changes, and loss of functional independence.Risk Factors and EtiologyThe disease is multifactorial. Age is the strongest risk factor, with prevalence doubling every 5 years after age 65. Genetic factors include mutations in genes such as APP, PSEN1, and PSEN2, which are associated...
01:26Alzheimer's Disease: Overview
Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
01:23Alzheimer Disease ll: Pathophysiology
Alzheimer disease involves structural changes in the brain that begin long before symptoms appear. The most distinctive features are extracellular neuritic plaques and intracellular neurofibrillary tangles.Neuritic plaques form in the cerebral cortex and around blood vessels. These plaques contain a dense core of beta-amyloid (Aβ)—a toxic protein fragment that clumps outside neurons. The core is surrounded by damaged neuronal extensions, as well as reactive astrocytes and microglia. Abnormal...
01:22Alzheimer's Disease: Treatment
Alzheimer's Disease (AD), a neurodegenerative disorder, is pathologically identified by amyloid plaques and neurofibrillary tangles composed of tau protein. AD pharmacotherapy aims to manage cognitive symptoms, delay disease progression, and treat behavioral symptoms. The treatment is primarily symptomatic and palliative, with no definitive disease-modifying therapy available. Cholinesterase inhibitors, including donepezil (Aricept), rivastigmine (Exelon), and galantamine (Razadyne), are...