Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation

Objective quantification of brain arteriolosclerosis remains an area of ongoing refinement in neuropathology, with current methods primarily utilizing semi-quantitative scales completed through manual histological examination. These approaches offer modest inter-rater reliability and do not provide...

Full description

Saved in:
Bibliographic Details
Main Authors: Jerry J. Lou, Peter Chang, Kiana D. Nava, Chanon Chantaduly, Hsin-Pei Wang, William H. Yong, Viharkumar Patel, Ajinkya J. Chaudhari, La Rissa Vasquez, Edwin Monuki, Elizabeth Head, Harry V. Vinters, Shino Magaki, Danielle J. Harvey, Chen-Nee Chuah, Charles S. DeCarli, Christopher K. Williams, Michael Keiser, Brittany N. Dugger
Format: Article
Language:English
Published: University of Münster / Open Journals System 2025-06-01
Series:Free Neuropathology
Subjects:
Online Access:https://www.uni-muenster.de/Ejournals/index.php/fnp/article/view/6387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138550144598016
author Jerry J. Lou
Peter Chang
Kiana D. Nava
Chanon Chantaduly
Hsin-Pei Wang
William H. Yong
Viharkumar Patel
Ajinkya J. Chaudhari
La Rissa Vasquez
Edwin Monuki
Elizabeth Head
Harry V. Vinters
Shino Magaki
Danielle J. Harvey
Chen-Nee Chuah
Charles S. DeCarli
Christopher K. Williams
Michael Keiser
Brittany N. Dugger
author_facet Jerry J. Lou
Peter Chang
Kiana D. Nava
Chanon Chantaduly
Hsin-Pei Wang
William H. Yong
Viharkumar Patel
Ajinkya J. Chaudhari
La Rissa Vasquez
Edwin Monuki
Elizabeth Head
Harry V. Vinters
Shino Magaki
Danielle J. Harvey
Chen-Nee Chuah
Charles S. DeCarli
Christopher K. Williams
Michael Keiser
Brittany N. Dugger
author_sort Jerry J. Lou
collection DOAJ
description Objective quantification of brain arteriolosclerosis remains an area of ongoing refinement in neuropathology, with current methods primarily utilizing semi-quantitative scales completed through manual histological examination. These approaches offer modest inter-rater reliability and do not provide precise quantitative metrics. To address this gap, we present a prototype end-to-end machine learning (ML)-based algorithm, Arteriolosclerosis Segmentation (ArtSeg), followed by Vascular Morphometry (VasMorph) – to assist persons in the morphometric analysis of arteriolosclerotic vessels on whole slide images (WSIs). We digitized hematoxylin and eosin-stained glass slides (13 participants, total 42 WSIs) of human brain frontal or occipital lobe cortical and/or periventricular white matter collected from three brain banks (University of California, Davis, Irvine, and Los Angeles Alzheimer’s Disease Research Centers). ArtSeg comprises three ML models for blood vessel detection, arteriolosclerosis classification, and segmentation of arteriolosclerotic vessel walls and lumens. For blood vessel detection, ArtSeg achieved area under the receiver operating characteristic curve (AUC-ROC) values of 0.79 (internal hold-out testing) and 0.77 (external testing), Dice scores of 0.56 (internal hold-out) and 0.74 (external), and Hausdorff distances of 2.53 (internal hold-out) and 2.15 (external). Arteriolosclerosis classification demonstrated accuracies of 0.94 (mean, 3-fold cross-validation), 0.86 (internal hold-out), and 0.77 (external), alongside AUC-ROC values of 0.69 (mean, 3-fold cross-validation), 0.87 (internal hold-out), and 0.83 (external). For arteriolosclerotic vessel segmentation, ArtSeg yielded Dice scores of 0.68 (mean, 3-fold cross-validation), 0.73 (internal hold-out), and 0.71 (external); Hausdorff distances of 7.63 (mean, 3-fold cross-validation), 6.93 (internal hold-out), and 7.80 (external); and AUC-ROC values of 0.90 (mean, 3-fold cross-validation), 0.92 (internal hold-out), and 0.87 (external). VasMorph successfully derived sclerotic indices, vessel wall thicknesses, and vessel wall to lumen area ratios from ArtSeg-segmented vessels, producing results comparable to expert assessment. This integrated approach shows promise as an assistive tool to enhance current neuropathological evaluation of brain arteriolosclerosis, offering potential for improved inter-rater reliability and quantification.
format Article
id doaj-art-0e31e203068d445aaaa7bb1834e13b3a
institution OA Journals
issn 2699-4445
language English
publishDate 2025-06-01
publisher University of Münster / Open Journals System
record_format Article
series Free Neuropathology
spelling doaj-art-0e31e203068d445aaaa7bb1834e13b3a2025-08-20T02:30:34ZengUniversity of Münster / Open Journals SystemFree Neuropathology2699-44452025-06-01610.17879/freeneuropathology-2025-6387Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automationJerry J. Lou0Peter Chang1Kiana D. Nava2Chanon Chantaduly3Hsin-Pei Wang4William H. Yong5Viharkumar Patel6Ajinkya J. Chaudhari7La Rissa Vasquez8Edwin Monuki9Elizabeth Head10Harry V. Vinters11Shino Magaki12Danielle J. Harvey13Chen-Nee Chuah14Charles S. DeCarli15Christopher K. Williams16Michael Keiser17Brittany N. Dugger18Department of Pathology and Laboratory Medicine, School of Medicine, University of California Irvine, Irvine, USADepartment of Radiological Sciences, Center for Artificial Intelligence in Diagnostic Medicine, School of Medicine, University of California Irvine, Orange, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Davis, Sacramento, USADepartment of Radiological Sciences, Center for Artificial Intelligence in Diagnostic Medicine, School of Medicine, University of California Irvine, Orange, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Davis, Sacramento, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Irvine, Irvine, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Davis, Sacramento, USADepartment of Electrical and Computer Engineering, University of California, Davis, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Davis, Sacramento, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Irvine, Irvine, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Irvine, Irvine, USADepartment of Pathology and Laboratory Medicine and Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USADepartment of Pathology and Laboratory Medicine, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USADepartment of Public Health Sciences, School of Medicine, University of California Davis, Davis, USADepartment of Electrical and Computer Engineering, University of California Davis, Davis, USADepartment of Neurology, School of Medicine, University of California Davis, Sacramento, USADepartment of Pathology and Laboratory Medicine, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, USADepartment of Pharmaceutical Chemistry, Department of Bioengineering and Therapeutic Sciences, Institute for Neurodegenerative Diseases; Bakar Computational Health Sciences Institute, University of California San Francisco, San Francisco, USADepartment of Pathology and Laboratory Medicine, School of Medicine, University of California Davis, Sacramento, USA Objective quantification of brain arteriolosclerosis remains an area of ongoing refinement in neuropathology, with current methods primarily utilizing semi-quantitative scales completed through manual histological examination. These approaches offer modest inter-rater reliability and do not provide precise quantitative metrics. To address this gap, we present a prototype end-to-end machine learning (ML)-based algorithm, Arteriolosclerosis Segmentation (ArtSeg), followed by Vascular Morphometry (VasMorph) – to assist persons in the morphometric analysis of arteriolosclerotic vessels on whole slide images (WSIs). We digitized hematoxylin and eosin-stained glass slides (13 participants, total 42 WSIs) of human brain frontal or occipital lobe cortical and/or periventricular white matter collected from three brain banks (University of California, Davis, Irvine, and Los Angeles Alzheimer’s Disease Research Centers). ArtSeg comprises three ML models for blood vessel detection, arteriolosclerosis classification, and segmentation of arteriolosclerotic vessel walls and lumens. For blood vessel detection, ArtSeg achieved area under the receiver operating characteristic curve (AUC-ROC) values of 0.79 (internal hold-out testing) and 0.77 (external testing), Dice scores of 0.56 (internal hold-out) and 0.74 (external), and Hausdorff distances of 2.53 (internal hold-out) and 2.15 (external). Arteriolosclerosis classification demonstrated accuracies of 0.94 (mean, 3-fold cross-validation), 0.86 (internal hold-out), and 0.77 (external), alongside AUC-ROC values of 0.69 (mean, 3-fold cross-validation), 0.87 (internal hold-out), and 0.83 (external). For arteriolosclerotic vessel segmentation, ArtSeg yielded Dice scores of 0.68 (mean, 3-fold cross-validation), 0.73 (internal hold-out), and 0.71 (external); Hausdorff distances of 7.63 (mean, 3-fold cross-validation), 6.93 (internal hold-out), and 7.80 (external); and AUC-ROC values of 0.90 (mean, 3-fold cross-validation), 0.92 (internal hold-out), and 0.87 (external). VasMorph successfully derived sclerotic indices, vessel wall thicknesses, and vessel wall to lumen area ratios from ArtSeg-segmented vessels, producing results comparable to expert assessment. This integrated approach shows promise as an assistive tool to enhance current neuropathological evaluation of brain arteriolosclerosis, offering potential for improved inter-rater reliability and quantification. https://www.uni-muenster.de/Ejournals/index.php/fnp/article/view/6387Machine learningArtificial intelligenceNeuropathologyArteriolosclerosisBlood vesselMorphometry
spellingShingle Jerry J. Lou
Peter Chang
Kiana D. Nava
Chanon Chantaduly
Hsin-Pei Wang
William H. Yong
Viharkumar Patel
Ajinkya J. Chaudhari
La Rissa Vasquez
Edwin Monuki
Elizabeth Head
Harry V. Vinters
Shino Magaki
Danielle J. Harvey
Chen-Nee Chuah
Charles S. DeCarli
Christopher K. Williams
Michael Keiser
Brittany N. Dugger
Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
Free Neuropathology
Machine learning
Artificial intelligence
Neuropathology
Arteriolosclerosis
Blood vessel
Morphometry
title Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
title_full Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
title_fullStr Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
title_full_unstemmed Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
title_short Applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
title_sort applying machine learning to assist in the morphometric assessment of brain arteriolosclerosis through automation
topic Machine learning
Artificial intelligence
Neuropathology
Arteriolosclerosis
Blood vessel
Morphometry
url https://www.uni-muenster.de/Ejournals/index.php/fnp/article/view/6387
work_keys_str_mv AT jerryjlou applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT peterchang applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT kianadnava applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT chanonchantaduly applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT hsinpeiwang applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT williamhyong applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT viharkumarpatel applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT ajinkyajchaudhari applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT larissavasquez applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT edwinmonuki applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT elizabethhead applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT harryvvinters applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT shinomagaki applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT daniellejharvey applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT chenneechuah applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT charlessdecarli applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT christopherkwilliams applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT michaelkeiser applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation
AT brittanyndugger applyingmachinelearningtoassistinthemorphometricassessmentofbrainarteriolosclerosisthroughautomation