Alzheimer's disease recognition via long-range state space model using multi-modal brain images

As a persistent neurodegenerative abnormality, Alzheimer's disease (AD) is affecting an increasing number of elderly people. The early identification of AD is critical for halting the disease progression at an early stage. However, the extraction and fusion of multi-modal features at different...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyin Ren, Meng Zhou, Sadia Shakil, Raymond Kai-Yu Tong
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2025.1576931/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849744865971142656
author Ziyin Ren
Meng Zhou
Sadia Shakil
Raymond Kai-Yu Tong
author_facet Ziyin Ren
Meng Zhou
Sadia Shakil
Raymond Kai-Yu Tong
author_sort Ziyin Ren
collection DOAJ
description As a persistent neurodegenerative abnormality, Alzheimer's disease (AD) is affecting an increasing number of elderly people. The early identification of AD is critical for halting the disease progression at an early stage. However, the extraction and fusion of multi-modal features at different scales from brain images remains a challenge for effective AD recognition. In this work, a novel feature fusion long-range state space model (FF-LSSM) model is suggested for effective extraction and fusion of multi-level characteristics from scannings of MRI and PET. The FF-LSSM can extract whole-volume features at every scale and effectively decide their global dependencies via adopted 3D Mamba encoders. Moreover, a feature fusion block is employed to consolidate features of different levels extracted by each encoder to generate fused feature maps. A classifier is cascaded at the end, using the fused features to produce the predicted labels. The FF-LSSM model is optimized and evaluated using brain images of subjects from the ADNI dataset. The inference result on the testing set reveals the FF-LSSM accomplishes a classification ACC of 93.59% in CN vs. AD and 79.31% in sMCI vs. pMCI task, proving its effectiveness in disease classification. Finally, the introduction of the Grad-CAM method illustrates that the implied FF-LSSM can detect AD- and MCI-related brain regions effectively.
format Article
id doaj-art-4bace00171374653abc611fc5f73f2c3
institution DOAJ
issn 1662-453X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-4bace00171374653abc611fc5f73f2c32025-08-20T03:07:04ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-05-011910.3389/fnins.2025.15769311576931Alzheimer's disease recognition via long-range state space model using multi-modal brain imagesZiyin RenMeng ZhouSadia ShakilRaymond Kai-Yu TongAs a persistent neurodegenerative abnormality, Alzheimer's disease (AD) is affecting an increasing number of elderly people. The early identification of AD is critical for halting the disease progression at an early stage. However, the extraction and fusion of multi-modal features at different scales from brain images remains a challenge for effective AD recognition. In this work, a novel feature fusion long-range state space model (FF-LSSM) model is suggested for effective extraction and fusion of multi-level characteristics from scannings of MRI and PET. The FF-LSSM can extract whole-volume features at every scale and effectively decide their global dependencies via adopted 3D Mamba encoders. Moreover, a feature fusion block is employed to consolidate features of different levels extracted by each encoder to generate fused feature maps. A classifier is cascaded at the end, using the fused features to produce the predicted labels. The FF-LSSM model is optimized and evaluated using brain images of subjects from the ADNI dataset. The inference result on the testing set reveals the FF-LSSM accomplishes a classification ACC of 93.59% in CN vs. AD and 79.31% in sMCI vs. pMCI task, proving its effectiveness in disease classification. Finally, the introduction of the Grad-CAM method illustrates that the implied FF-LSSM can detect AD- and MCI-related brain regions effectively.https://www.frontiersin.org/articles/10.3389/fnins.2025.1576931/fullAlzheimer's diseaselong-range sequential modelingmild cognitive impairmentmulti-modal brain imagesmulti-modality integration
spellingShingle Ziyin Ren
Meng Zhou
Sadia Shakil
Raymond Kai-Yu Tong
Alzheimer's disease recognition via long-range state space model using multi-modal brain images
Frontiers in Neuroscience
Alzheimer's disease
long-range sequential modeling
mild cognitive impairment
multi-modal brain images
multi-modality integration
title Alzheimer's disease recognition via long-range state space model using multi-modal brain images
title_full Alzheimer's disease recognition via long-range state space model using multi-modal brain images
title_fullStr Alzheimer's disease recognition via long-range state space model using multi-modal brain images
title_full_unstemmed Alzheimer's disease recognition via long-range state space model using multi-modal brain images
title_short Alzheimer's disease recognition via long-range state space model using multi-modal brain images
title_sort alzheimer s disease recognition via long range state space model using multi modal brain images
topic Alzheimer's disease
long-range sequential modeling
mild cognitive impairment
multi-modal brain images
multi-modality integration
url https://www.frontiersin.org/articles/10.3389/fnins.2025.1576931/full
work_keys_str_mv AT ziyinren alzheimersdiseaserecognitionvialongrangestatespacemodelusingmultimodalbrainimages
AT mengzhou alzheimersdiseaserecognitionvialongrangestatespacemodelusingmultimodalbrainimages
AT sadiashakil alzheimersdiseaserecognitionvialongrangestatespacemodelusingmultimodalbrainimages
AT raymondkaiyutong alzheimersdiseaserecognitionvialongrangestatespacemodelusingmultimodalbrainimages