Cargando…

Task-driven assessment of experimental designs in diffusion MRI: A computational framework

This paper proposes a task-driven computational framework for assessing diffusion MRI experimental designs which, rather than relying on parameter-estimation metrics, directly measures quantitative task performance. Traditional computational experimental design (CED) methods may be ill-suited to exp...

Descripción completa

Detalles Bibliográficos
Autores principales: Epstein, Sean C., Bray, Timothy J. P., Hall-Craggs, Margaret A., Zhang, Hui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8500429/
https://www.ncbi.nlm.nih.gov/pubmed/34624064
http://dx.doi.org/10.1371/journal.pone.0258442
_version_ 1784580445408591872
author Epstein, Sean C.
Bray, Timothy J. P.
Hall-Craggs, Margaret A.
Zhang, Hui
author_facet Epstein, Sean C.
Bray, Timothy J. P.
Hall-Craggs, Margaret A.
Zhang, Hui
author_sort Epstein, Sean C.
collection PubMed
description This paper proposes a task-driven computational framework for assessing diffusion MRI experimental designs which, rather than relying on parameter-estimation metrics, directly measures quantitative task performance. Traditional computational experimental design (CED) methods may be ill-suited to experimental tasks, such as clinical classification, where outcome does not depend on parameter-estimation accuracy or precision alone. Current assessment metrics evaluate experiments’ ability to faithfully recover microstructural parameters rather than their task performance. The method we propose addresses this shortcoming. For a given MRI experimental design (protocol, parameter-estimation method, model, etc.), experiments are simulated start-to-finish and task performance is computed from receiver operating characteristic (ROC) curves and associated summary metrics (e.g. area under the curve (AUC)). Two experiments were performed: first, a validation of the pipeline’s task performance predictions against clinical results, comparing in-silico predictions to real-world ROC/AUC; and second, a demonstration of the pipeline’s advantages over traditional CED approaches, using two simulated clinical classification tasks. Comparison with clinical datasets validates our method’s predictions of (a) the qualitative form of ROC curves, (b) the relative task performance of different experimental designs, and (c) the absolute performance (AUC) of each experimental design. Furthermore, we show that our method outperforms traditional task-agnostic assessment methods, enabling improved, more useful experimental design. Our pipeline produces accurate, quantitative predictions of real-world task performance. Compared to current approaches, such task-driven assessment is more likely to identify experimental designs that perform well in practice. Our method is not limited to diffusion MRI; the pipeline generalises to any task-based quantitative MRI application, and provides the foundation for developing future task-driven end-to end CED frameworks.
format Online
Article
Text
id pubmed-8500429
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-85004292021-10-09 Task-driven assessment of experimental designs in diffusion MRI: A computational framework Epstein, Sean C. Bray, Timothy J. P. Hall-Craggs, Margaret A. Zhang, Hui PLoS One Research Article This paper proposes a task-driven computational framework for assessing diffusion MRI experimental designs which, rather than relying on parameter-estimation metrics, directly measures quantitative task performance. Traditional computational experimental design (CED) methods may be ill-suited to experimental tasks, such as clinical classification, where outcome does not depend on parameter-estimation accuracy or precision alone. Current assessment metrics evaluate experiments’ ability to faithfully recover microstructural parameters rather than their task performance. The method we propose addresses this shortcoming. For a given MRI experimental design (protocol, parameter-estimation method, model, etc.), experiments are simulated start-to-finish and task performance is computed from receiver operating characteristic (ROC) curves and associated summary metrics (e.g. area under the curve (AUC)). Two experiments were performed: first, a validation of the pipeline’s task performance predictions against clinical results, comparing in-silico predictions to real-world ROC/AUC; and second, a demonstration of the pipeline’s advantages over traditional CED approaches, using two simulated clinical classification tasks. Comparison with clinical datasets validates our method’s predictions of (a) the qualitative form of ROC curves, (b) the relative task performance of different experimental designs, and (c) the absolute performance (AUC) of each experimental design. Furthermore, we show that our method outperforms traditional task-agnostic assessment methods, enabling improved, more useful experimental design. Our pipeline produces accurate, quantitative predictions of real-world task performance. Compared to current approaches, such task-driven assessment is more likely to identify experimental designs that perform well in practice. Our method is not limited to diffusion MRI; the pipeline generalises to any task-based quantitative MRI application, and provides the foundation for developing future task-driven end-to end CED frameworks. Public Library of Science 2021-10-08 /pmc/articles/PMC8500429/ /pubmed/34624064 http://dx.doi.org/10.1371/journal.pone.0258442 Text en © 2021 Epstein et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Epstein, Sean C.
Bray, Timothy J. P.
Hall-Craggs, Margaret A.
Zhang, Hui
Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title_full Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title_fullStr Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title_full_unstemmed Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title_short Task-driven assessment of experimental designs in diffusion MRI: A computational framework
title_sort task-driven assessment of experimental designs in diffusion mri: a computational framework
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8500429/
https://www.ncbi.nlm.nih.gov/pubmed/34624064
http://dx.doi.org/10.1371/journal.pone.0258442
work_keys_str_mv AT epsteinseanc taskdrivenassessmentofexperimentaldesignsindiffusionmriacomputationalframework
AT braytimothyjp taskdrivenassessmentofexperimentaldesignsindiffusionmriacomputationalframework
AT hallcraggsmargareta taskdrivenassessmentofexperimentaldesignsindiffusionmriacomputationalframework
AT zhanghui taskdrivenassessmentofexperimentaldesignsindiffusionmriacomputationalframework