analiza aiqbench
Delta2Gamma introduces a self-supervised framework that leverages band-wise contrastive learning on EEG data to address the scarcity of labeled clinical datasets in dementia screening. By adaptively balancing temperature parameters across distinct neural rhythms, this approach achieves high accuracy without relying on expensive imaging modalities or extensive supervised training. The method represents a significant step toward scalable, low-cost diagnostic tools for Alzheimer's disease using accessible hardware.
Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection
arXiv:2608.17231v1 Announce Type: new Abstract: Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4\% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.
Abstract:Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4\% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2608.17231 [cs.LG]
(or arXiv:2608.17231v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.17231 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 240 cuvinte
Subiecte conexe
GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
arXiv · 16 iun. 2026
GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
arXiv · 15 iun. 2026
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
arXiv · 15 oct. 2026
Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
arXiv · 16 sept. 2026