Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI
Perivascular spaces (PVS) are believed to be involved in brain waste disposal. PVS are associated with cerebral small vessel disease. At higher field strengths more PVS can be observed, challenging manual assessment. We developed a method to automatically detect and quantify PVS.A machine learning a...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-01-01
|
Series: | Cerebral Circulation - Cognition and Behavior |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666245022001076 |
_version_ | 1811197589616328704 |
---|---|
author | J.M. Spijkerman J.J.M. Zwanenburg W.H. Bouvy M.I. Geerlings G.J. Biessels J. Hendrikse P.R. Luijten H.J. Kuijf |
author_facet | J.M. Spijkerman J.J.M. Zwanenburg W.H. Bouvy M.I. Geerlings G.J. Biessels J. Hendrikse P.R. Luijten H.J. Kuijf |
author_sort | J.M. Spijkerman |
collection | DOAJ |
description | Perivascular spaces (PVS) are believed to be involved in brain waste disposal. PVS are associated with cerebral small vessel disease. At higher field strengths more PVS can be observed, challenging manual assessment. We developed a method to automatically detect and quantify PVS.A machine learning approach identified PVS in an automatically positioned ROI in the centrum semiovale (CSO), based on -resolution T2-weighted TSE scans. Next, 3D PVS tracking was performed in 50 subjects (mean age 62.9 years (range 27–78), 19 male), and quantitative measures were extracted. Maps of PVS density, length, and tortuosity were created. Manual PVS annotations were available to train and validate the automatic method.Good correlation was found between the automatic and manual PVS count: ICC (absolute/consistency) is 0.64/0.75, and Dice similarity coefficient (DSC) is 0.61. The automatic method counts fewer PVS than the manual count, because it ignores the smallest PVS (length <2 mm). For 20 subjects manual PVS annotations of a second observer were available. Compared with the correlation between the automatic and manual PVS, higher inter-observer ICC was observed (0.85/0.88), but DSC was lower (0.49 in 4 persons). Longer PVS are observed posterior in the CSO compared with anterior in the CSO. Higher PVS tortuosity are observed in the center of the CSO compared with the periphery of the CSO.Our fully automatic method can detect PVS in a 2D slab in the CSO, and extract quantitative PVS parameters by performing 3D tracking. This method enables automated quantitative analysis of PVS. |
first_indexed | 2024-04-12T01:17:28Z |
format | Article |
id | doaj.art-44fd2cf3da0c44aea0f0b0a90bd62ae5 |
institution | Directory Open Access Journal |
issn | 2666-2450 |
language | English |
last_indexed | 2024-04-12T01:17:28Z |
publishDate | 2022-01-01 |
publisher | Elsevier |
record_format | Article |
series | Cerebral Circulation - Cognition and Behavior |
spelling | doaj.art-44fd2cf3da0c44aea0f0b0a90bd62ae52022-12-22T03:53:55ZengElsevierCerebral Circulation - Cognition and Behavior2666-24502022-01-013100142Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRIJ.M. Spijkerman0J.J.M. Zwanenburg1W.H. Bouvy2M.I. Geerlings3G.J. Biessels4J. Hendrikse5P.R. Luijten6H.J. Kuijf7Department of Radiology, University Medical Center Utrecht, Utrecht, the NetherlandsDepartment of Radiology, University Medical Center Utrecht, Utrecht, the NetherlandsBrain Center Rudolf Magnus, Department of Neurology, University Medical Center Utrecht, Utrecht, the NetherlandsJulius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht, the NetherlandsBrain Center Rudolf Magnus, Department of Neurology, University Medical Center Utrecht, Utrecht, the NetherlandsDepartment of Radiology, University Medical Center Utrecht, Utrecht, the NetherlandsDepartment of Radiology, University Medical Center Utrecht, Utrecht, the NetherlandsImage Sciences Institute, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, the Netherlands; Corresponding author.Perivascular spaces (PVS) are believed to be involved in brain waste disposal. PVS are associated with cerebral small vessel disease. At higher field strengths more PVS can be observed, challenging manual assessment. We developed a method to automatically detect and quantify PVS.A machine learning approach identified PVS in an automatically positioned ROI in the centrum semiovale (CSO), based on -resolution T2-weighted TSE scans. Next, 3D PVS tracking was performed in 50 subjects (mean age 62.9 years (range 27–78), 19 male), and quantitative measures were extracted. Maps of PVS density, length, and tortuosity were created. Manual PVS annotations were available to train and validate the automatic method.Good correlation was found between the automatic and manual PVS count: ICC (absolute/consistency) is 0.64/0.75, and Dice similarity coefficient (DSC) is 0.61. The automatic method counts fewer PVS than the manual count, because it ignores the smallest PVS (length <2 mm). For 20 subjects manual PVS annotations of a second observer were available. Compared with the correlation between the automatic and manual PVS, higher inter-observer ICC was observed (0.85/0.88), but DSC was lower (0.49 in 4 persons). Longer PVS are observed posterior in the CSO compared with anterior in the CSO. Higher PVS tortuosity are observed in the center of the CSO compared with the periphery of the CSO.Our fully automatic method can detect PVS in a 2D slab in the CSO, and extract quantitative PVS parameters by performing 3D tracking. This method enables automated quantitative analysis of PVS.http://www.sciencedirect.com/science/article/pii/S2666245022001076Perivascular spacesCentrum semiovaleQuantification7 tesla MRIMachine learning |
spellingShingle | J.M. Spijkerman J.J.M. Zwanenburg W.H. Bouvy M.I. Geerlings G.J. Biessels J. Hendrikse P.R. Luijten H.J. Kuijf Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI Cerebral Circulation - Cognition and Behavior Perivascular spaces Centrum semiovale Quantification 7 tesla MRI Machine learning |
title | Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI |
title_full | Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI |
title_fullStr | Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI |
title_full_unstemmed | Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI |
title_short | Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI |
title_sort | automatic quantification of perivascular spaces in t2 weighted images at 7 t mri |
topic | Perivascular spaces Centrum semiovale Quantification 7 tesla MRI Machine learning |
url | http://www.sciencedirect.com/science/article/pii/S2666245022001076 |
work_keys_str_mv | AT jmspijkerman automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT jjmzwanenburg automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT whbouvy automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT migeerlings automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT gjbiessels automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT jhendrikse automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT prluijten automaticquantificationofperivascularspacesint2weightedimagesat7tmri AT hjkuijf automaticquantificationofperivascularspacesint2weightedimagesat7tmri |