Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease

BackgroundThis study aimed to quantitatively evaluate brain glymphatic imaging features in patients with Alzheimer’s disease (AD), amnestic mild cognitive impairment (aMCI), and normal controls (NC) by applying a deep learning-based method for the automated segmentation of enlarged perivascular spac...

Full description

Saved in:
Bibliographic Details
Main Authors: Fenyang Chen, Tiantian Heng, Qi Feng, Rui Hua, Jiaojiao Wu, Feng Shi, Zhengluan Liao, Keyin Qiao, Zhiliang Zhang, Jianliang Miao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Aging Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnagi.2025.1621106/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850099284184137728
author Fenyang Chen
Tiantian Heng
Qi Feng
Rui Hua
Jiaojiao Wu
Feng Shi
Zhengluan Liao
Keyin Qiao
Zhiliang Zhang
Jianliang Miao
author_facet Fenyang Chen
Tiantian Heng
Qi Feng
Rui Hua
Jiaojiao Wu
Feng Shi
Zhengluan Liao
Keyin Qiao
Zhiliang Zhang
Jianliang Miao
author_sort Fenyang Chen
collection DOAJ
description BackgroundThis study aimed to quantitatively evaluate brain glymphatic imaging features in patients with Alzheimer’s disease (AD), amnestic mild cognitive impairment (aMCI), and normal controls (NC) by applying a deep learning-based method for the automated segmentation of enlarged perivascular space (EPVS) and diffusion tensor imaging analysis along perivascular spaces (DTI-ALPS) indices.MethodsA total of 89 patients with AD, 24 aMCI, and 32 NCs were included. EPVS were automatically segmented from T1WI and T2WI images using a VB-Net-based model. Quantitative metrics, including total EPVS volume, number, and regional volume fractions were extracted, and segmentation performance was evaluated using the Dice similarity coefficient. Bilateral ALPS indices were also calculated. Group comparisons were conducted for all imaging metrics, and correlations with cognitive scores were analyzed.ResultsVB-Net segmentation model demonstrated high accuracy, with mean Dice coefficients exceeding 0.90. Compared to the NC group, both AD and aMCI groups exhibited significantly increased EPVS volume, number, along with reduced ALPS indices (all P < 0.05). Partial correlation analysis revealed strong associations between ALPS and EPVS metrics and cognitive performance. The combined imaging features showed good discriminative performance among diagnostic groups.ConclusionThe integration of deep learning-based EPVS segmentation and DTI-ALPS analysis enables multidimensional assessment of glymphatic system alterations, offering potential value for early diagnosis and translation in neurodegenerative diseases.
format Article
id doaj-art-aa209224f90c4a0c9590cfec3bc82e37
institution DOAJ
issn 1663-4365
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Aging Neuroscience
spelling doaj-art-aa209224f90c4a0c9590cfec3bc82e372025-08-20T02:40:30ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652025-07-011710.3389/fnagi.2025.16211061621106Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s diseaseFenyang Chen0Tiantian Heng1Qi Feng2Rui Hua3Jiaojiao Wu4Feng Shi5Zhengluan Liao6Keyin Qiao7Zhiliang Zhang8Jianliang Miao9Department of Medical Imaging, Section One of Air Force Hangzhou Special Crew Sanatorium of PLA AIR Force, Hangzhou, ChinaAir Force Healthcare Center for Special Services, Hangzhou, ChinaDepartment of Radiology, Hangzhou First People’s Hospital Affiliated of Westlake University School of Medicine, Hangzhou, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Mental Health, Zhejiang Provincial People’s Hospital, Hangzhou, ChinaDepartment of Medical Imaging, Section One of Air Force Hangzhou Special Crew Sanatorium of PLA AIR Force, Hangzhou, ChinaDepartment of Radiology, Zhejiang Hospital, Hangzhou, ChinaDepartment of Medical Imaging, Section One of Air Force Hangzhou Special Crew Sanatorium of PLA AIR Force, Hangzhou, ChinaBackgroundThis study aimed to quantitatively evaluate brain glymphatic imaging features in patients with Alzheimer’s disease (AD), amnestic mild cognitive impairment (aMCI), and normal controls (NC) by applying a deep learning-based method for the automated segmentation of enlarged perivascular space (EPVS) and diffusion tensor imaging analysis along perivascular spaces (DTI-ALPS) indices.MethodsA total of 89 patients with AD, 24 aMCI, and 32 NCs were included. EPVS were automatically segmented from T1WI and T2WI images using a VB-Net-based model. Quantitative metrics, including total EPVS volume, number, and regional volume fractions were extracted, and segmentation performance was evaluated using the Dice similarity coefficient. Bilateral ALPS indices were also calculated. Group comparisons were conducted for all imaging metrics, and correlations with cognitive scores were analyzed.ResultsVB-Net segmentation model demonstrated high accuracy, with mean Dice coefficients exceeding 0.90. Compared to the NC group, both AD and aMCI groups exhibited significantly increased EPVS volume, number, along with reduced ALPS indices (all P < 0.05). Partial correlation analysis revealed strong associations between ALPS and EPVS metrics and cognitive performance. The combined imaging features showed good discriminative performance among diagnostic groups.ConclusionThe integration of deep learning-based EPVS segmentation and DTI-ALPS analysis enables multidimensional assessment of glymphatic system alterations, offering potential value for early diagnosis and translation in neurodegenerative diseases.https://www.frontiersin.org/articles/10.3389/fnagi.2025.1621106/fullAlzheimer’s diseaseamnestic mild cognitive impairmentglymphatic systemV-shape bottleneck networkenlarged perivascular spacediffusion tensor imaging along perivascular spaces
spellingShingle Fenyang Chen
Tiantian Heng
Qi Feng
Rui Hua
Jiaojiao Wu
Feng Shi
Zhengluan Liao
Keyin Qiao
Zhiliang Zhang
Jianliang Miao
Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
Frontiers in Aging Neuroscience
Alzheimer’s disease
amnestic mild cognitive impairment
glymphatic system
V-shape bottleneck network
enlarged perivascular space
diffusion tensor imaging along perivascular spaces
title Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
title_full Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
title_fullStr Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
title_full_unstemmed Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
title_short Quantitative assessment of brain glymphatic imaging features using deep learning-based EPVS segmentation and DTI-ALPS analysis in Alzheimer’s disease
title_sort quantitative assessment of brain glymphatic imaging features using deep learning based epvs segmentation and dti alps analysis in alzheimer s disease
topic Alzheimer’s disease
amnestic mild cognitive impairment
glymphatic system
V-shape bottleneck network
enlarged perivascular space
diffusion tensor imaging along perivascular spaces
url https://www.frontiersin.org/articles/10.3389/fnagi.2025.1621106/full
work_keys_str_mv AT fenyangchen quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT tiantianheng quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT qifeng quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT ruihua quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT jiaojiaowu quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT fengshi quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT zhengluanliao quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT keyinqiao quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT zhiliangzhang quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease
AT jianliangmiao quantitativeassessmentofbrainglymphaticimagingfeaturesusingdeeplearningbasedepvssegmentationanddtialpsanalysisinalzheimersdisease