Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts

Matteo Mancini, Sjoerd B. Vos, Vejay N. Vakharia, Aidan G. O'Keeffe, Karin Trimmel, Frederik Barkhof, Christian Dorfer, Salil Soman, Gavin P. Winston, Chengyuan Wu, John S. Duncan, Rachel Sparks, Sebastien Ourselin

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Diffusion MRI and tractography hold great potential for surgery planning, especially to preserve eloquent white matter during resections. However, fiber tract reconstruction requires an expert with detailed understanding of neuroanatomy. Several automated approaches have been proposed, using different strategies to reconstruct the white matter tracts in a supervised fashion. However, validation is often limited to comparison with manual delineation by overlap-based measures, which is limited in characterizing morphological and topological differences. In this work, we set up a fully automated pipeline based on anatomical criteria that does not require manual intervention, taking advantage of atlas-based criteria and advanced acquisition protocols available on clinical-grade MRI scanners. Then, we extensively validated it on epilepsy patients with specific focus on language-related bundles. The validation procedure encompasses different approaches, including simple overlap with manual segmentations from two experts, feasibility ratings from external multiple clinical raters and relation with task-based functional MRI. Overall, our results demonstrate good quantitative agreement between automated and manual segmentation, in most cases better performances of the proposed method in qualitative terms, and meaningful relationships with task-based fMRI. In addition, we observed significant differences between experts in terms of both manual segmentation and external ratings. These results offer important insights on how different levels of validation complement each other, supporting the idea that overlap-based measures, although quantitative, do not offer a full perspective on the similarities and differences between automated and manual methods.
Original languageEnglish
Article number101883
JournalNeuroImage: Clinical
Volume23
DOIs
Publication statusPublished - 2019

Cite this

Mancini, Matteo ; Vos, Sjoerd B. ; Vakharia, Vejay N. ; O'Keeffe, Aidan G. ; Trimmel, Karin ; Barkhof, Frederik ; Dorfer, Christian ; Soman, Salil ; Winston, Gavin P. ; Wu, Chengyuan ; Duncan, John S. ; Sparks, Rachel ; Ourselin, Sebastien. / Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts. In: NeuroImage: Clinical. 2019 ; Vol. 23.
@article{c05a4d68bd2c48f3837ab1a060ba930e,
title = "Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts",
abstract = "Diffusion MRI and tractography hold great potential for surgery planning, especially to preserve eloquent white matter during resections. However, fiber tract reconstruction requires an expert with detailed understanding of neuroanatomy. Several automated approaches have been proposed, using different strategies to reconstruct the white matter tracts in a supervised fashion. However, validation is often limited to comparison with manual delineation by overlap-based measures, which is limited in characterizing morphological and topological differences. In this work, we set up a fully automated pipeline based on anatomical criteria that does not require manual intervention, taking advantage of atlas-based criteria and advanced acquisition protocols available on clinical-grade MRI scanners. Then, we extensively validated it on epilepsy patients with specific focus on language-related bundles. The validation procedure encompasses different approaches, including simple overlap with manual segmentations from two experts, feasibility ratings from external multiple clinical raters and relation with task-based functional MRI. Overall, our results demonstrate good quantitative agreement between automated and manual segmentation, in most cases better performances of the proposed method in qualitative terms, and meaningful relationships with task-based fMRI. In addition, we observed significant differences between experts in terms of both manual segmentation and external ratings. These results offer important insights on how different levels of validation complement each other, supporting the idea that overlap-based measures, although quantitative, do not offer a full perspective on the similarities and differences between automated and manual methods.",
author = "Matteo Mancini and Vos, {Sjoerd B.} and Vakharia, {Vejay N.} and O'Keeffe, {Aidan G.} and Karin Trimmel and Frederik Barkhof and Christian Dorfer and Salil Soman and Winston, {Gavin P.} and Chengyuan Wu and Duncan, {John S.} and Rachel Sparks and Sebastien Ourselin",
year = "2019",
doi = "10.1016/j.nicl.2019.101883",
language = "English",
volume = "23",
journal = "NeuroImage: Clinical",
issn = "2213-1582",
publisher = "Elsevier BV",

}

Mancini, M, Vos, SB, Vakharia, VN, O'Keeffe, AG, Trimmel, K, Barkhof, F, Dorfer, C, Soman, S, Winston, GP, Wu, C, Duncan, JS, Sparks, R & Ourselin, S 2019, 'Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts' NeuroImage: Clinical, vol. 23, 101883. https://doi.org/10.1016/j.nicl.2019.101883

Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts. / Mancini, Matteo; Vos, Sjoerd B.; Vakharia, Vejay N.; O'Keeffe, Aidan G.; Trimmel, Karin; Barkhof, Frederik; Dorfer, Christian; Soman, Salil; Winston, Gavin P.; Wu, Chengyuan; Duncan, John S.; Sparks, Rachel; Ourselin, Sebastien.

In: NeuroImage: Clinical, Vol. 23, 101883, 2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automated fiber tract reconstruction for surgery planning: Extensive validation in language-related white matter tracts

AU - Mancini, Matteo

AU - Vos, Sjoerd B.

AU - Vakharia, Vejay N.

AU - O'Keeffe, Aidan G.

AU - Trimmel, Karin

AU - Barkhof, Frederik

AU - Dorfer, Christian

AU - Soman, Salil

AU - Winston, Gavin P.

AU - Wu, Chengyuan

AU - Duncan, John S.

AU - Sparks, Rachel

AU - Ourselin, Sebastien

PY - 2019

Y1 - 2019

N2 - Diffusion MRI and tractography hold great potential for surgery planning, especially to preserve eloquent white matter during resections. However, fiber tract reconstruction requires an expert with detailed understanding of neuroanatomy. Several automated approaches have been proposed, using different strategies to reconstruct the white matter tracts in a supervised fashion. However, validation is often limited to comparison with manual delineation by overlap-based measures, which is limited in characterizing morphological and topological differences. In this work, we set up a fully automated pipeline based on anatomical criteria that does not require manual intervention, taking advantage of atlas-based criteria and advanced acquisition protocols available on clinical-grade MRI scanners. Then, we extensively validated it on epilepsy patients with specific focus on language-related bundles. The validation procedure encompasses different approaches, including simple overlap with manual segmentations from two experts, feasibility ratings from external multiple clinical raters and relation with task-based functional MRI. Overall, our results demonstrate good quantitative agreement between automated and manual segmentation, in most cases better performances of the proposed method in qualitative terms, and meaningful relationships with task-based fMRI. In addition, we observed significant differences between experts in terms of both manual segmentation and external ratings. These results offer important insights on how different levels of validation complement each other, supporting the idea that overlap-based measures, although quantitative, do not offer a full perspective on the similarities and differences between automated and manual methods.

AB - Diffusion MRI and tractography hold great potential for surgery planning, especially to preserve eloquent white matter during resections. However, fiber tract reconstruction requires an expert with detailed understanding of neuroanatomy. Several automated approaches have been proposed, using different strategies to reconstruct the white matter tracts in a supervised fashion. However, validation is often limited to comparison with manual delineation by overlap-based measures, which is limited in characterizing morphological and topological differences. In this work, we set up a fully automated pipeline based on anatomical criteria that does not require manual intervention, taking advantage of atlas-based criteria and advanced acquisition protocols available on clinical-grade MRI scanners. Then, we extensively validated it on epilepsy patients with specific focus on language-related bundles. The validation procedure encompasses different approaches, including simple overlap with manual segmentations from two experts, feasibility ratings from external multiple clinical raters and relation with task-based functional MRI. Overall, our results demonstrate good quantitative agreement between automated and manual segmentation, in most cases better performances of the proposed method in qualitative terms, and meaningful relationships with task-based fMRI. In addition, we observed significant differences between experts in terms of both manual segmentation and external ratings. These results offer important insights on how different levels of validation complement each other, supporting the idea that overlap-based measures, although quantitative, do not offer a full perspective on the similarities and differences between automated and manual methods.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85066340194&origin=inward

UR - https://www.ncbi.nlm.nih.gov/pubmed/31163386

U2 - 10.1016/j.nicl.2019.101883

DO - 10.1016/j.nicl.2019.101883

M3 - Article

VL - 23

JO - NeuroImage: Clinical

JF - NeuroImage: Clinical

SN - 2213-1582

M1 - 101883

ER -