TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment

Abstract Early diagnosis of Alzheimer’s disease (AD) and its precursor, mild cognitive impairment (MCI), is critical for effective prevention and treatment. Computer-aided diagnosis using magnetic resonance imaging (MRI) provides a cost-effective and objective approach. However, existing methods oft...

Full description

Saved in:
Bibliographic Details
Main Authors: Sichen Bao, Fengbo Zheng, Lifen Jiang, Qiuyuan Wang, Yong Lyu
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01836-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738585140363264
author Sichen Bao
Fengbo Zheng
Lifen Jiang
Qiuyuan Wang
Yong Lyu
author_facet Sichen Bao
Fengbo Zheng
Lifen Jiang
Qiuyuan Wang
Yong Lyu
author_sort Sichen Bao
collection DOAJ
description Abstract Early diagnosis of Alzheimer’s disease (AD) and its precursor, mild cognitive impairment (MCI), is critical for effective prevention and treatment. Computer-aided diagnosis using magnetic resonance imaging (MRI) provides a cost-effective and objective approach. However, existing methods often segment 3D MRI images into 2D slices, leading to spatial information loss and reduced diagnostic accuracy. To overcome this limitation, we propose TA-SSM Net, a deep learning model that leverages tri-directional attention and structured state-space model (SSM) for improved MRI-based diagnosis of AD and MCI. The tri-directional attention mechanism captures spatial and contextual information from forward, backward, and vertical directions in 3D MRI images, enabling effective feature fusion. Additionally, gradient checkpointing is applied within the SSM to enhance processing efficiency, allowing the model to handle whole-brain scans while preserving spatial correlations. To evaluate our method, we construct a dataset from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), consisting of 300 AD patients, 400 MCI patients, and 400 normal controls. TA-SSM Net achieved an accuracy of 90.24% for MCI detection and 95.83% for AD detection. The results demonstrate that our approach not only improves classification accuracy but also enhances processing efficiency and maintains spatial correlations, offering a promising solution for the diagnosis of Alzheimer’s disease.
format Article
id doaj-art-b90afc2fb7c0466da9a8bcd192ef43b4
institution DOAJ
issn 1471-2342
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-b90afc2fb7c0466da9a8bcd192ef43b42025-08-20T03:06:31ZengBMCBMC Medical Imaging1471-23422025-07-0125111310.1186/s12880-025-01836-5TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairmentSichen Bao0Fengbo Zheng1Lifen Jiang2Qiuyuan Wang3Yong Lyu4College of Computer and Information Engineering, Tianjin Normal UniversityCollege of Computer and Information Engineering, Tianjin Normal UniversityCollege of Computer and Information Engineering, Tianjin Normal UniversityDepartment of Pain Medicine, Peking University People’s HospitalDepartment of Otolaryngology-Head and Neck Surgery, China-Japan Friendship HospitalAbstract Early diagnosis of Alzheimer’s disease (AD) and its precursor, mild cognitive impairment (MCI), is critical for effective prevention and treatment. Computer-aided diagnosis using magnetic resonance imaging (MRI) provides a cost-effective and objective approach. However, existing methods often segment 3D MRI images into 2D slices, leading to spatial information loss and reduced diagnostic accuracy. To overcome this limitation, we propose TA-SSM Net, a deep learning model that leverages tri-directional attention and structured state-space model (SSM) for improved MRI-based diagnosis of AD and MCI. The tri-directional attention mechanism captures spatial and contextual information from forward, backward, and vertical directions in 3D MRI images, enabling effective feature fusion. Additionally, gradient checkpointing is applied within the SSM to enhance processing efficiency, allowing the model to handle whole-brain scans while preserving spatial correlations. To evaluate our method, we construct a dataset from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), consisting of 300 AD patients, 400 MCI patients, and 400 normal controls. TA-SSM Net achieved an accuracy of 90.24% for MCI detection and 95.83% for AD detection. The results demonstrate that our approach not only improves classification accuracy but also enhances processing efficiency and maintains spatial correlations, offering a promising solution for the diagnosis of Alzheimer’s disease.https://doi.org/10.1186/s12880-025-01836-5Alzheimer’s diseaseMagnetic resonance imagingAttention mechanismState space models
spellingShingle Sichen Bao
Fengbo Zheng
Lifen Jiang
Qiuyuan Wang
Yong Lyu
TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
BMC Medical Imaging
Alzheimer’s disease
Magnetic resonance imaging
Attention mechanism
State space models
title TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
title_full TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
title_fullStr TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
title_full_unstemmed TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
title_short TA-SSM net: tri-directional attention and structured state-space model for enhanced MRI-Based diagnosis of Alzheimer’s disease and mild cognitive impairment
title_sort ta ssm net tri directional attention and structured state space model for enhanced mri based diagnosis of alzheimer s disease and mild cognitive impairment
topic Alzheimer’s disease
Magnetic resonance imaging
Attention mechanism
State space models
url https://doi.org/10.1186/s12880-025-01836-5
work_keys_str_mv AT sichenbao tassmnettridirectionalattentionandstructuredstatespacemodelforenhancedmribaseddiagnosisofalzheimersdiseaseandmildcognitiveimpairment
AT fengbozheng tassmnettridirectionalattentionandstructuredstatespacemodelforenhancedmribaseddiagnosisofalzheimersdiseaseandmildcognitiveimpairment
AT lifenjiang tassmnettridirectionalattentionandstructuredstatespacemodelforenhancedmribaseddiagnosisofalzheimersdiseaseandmildcognitiveimpairment
AT qiuyuanwang tassmnettridirectionalattentionandstructuredstatespacemodelforenhancedmribaseddiagnosisofalzheimersdiseaseandmildcognitiveimpairment
AT yonglyu tassmnettridirectionalattentionandstructuredstatespacemodelforenhancedmribaseddiagnosisofalzheimersdiseaseandmildcognitiveimpairment