Detecting microstructural deviations in individuals with deep diffusion MRI tractometry

Maxime Chamberland; Sila Genc; Chantal M.W. Tax; Dmitri Shastin; Kristin Koller; Erika P. Raven; Adam Cunningham; Joanne Doherty; Marianne B.M. van den Bree; Greg D. Parker; Khalid Hamandi; William P. Gray; Derek K. Jones

doi:10.1038/s43588-021-00126-8

Detecting microstructural deviations in individuals with deep diffusion MRI tractometry

Maxime Chamberland
, Sila Genc
, Chantal M.W. Tax
, Dmitri Shastin
, Kristin Koller
, Erika P. Raven
, Adam Cunningham
, Joanne Doherty
, Marianne B.M. van den Bree
, Greg D. Parker
, Khalid Hamandi
, William P. Gray
, Derek K. Jones

Research output: Contribution to journal › Article › Academic › peer-review

54 Citations (Scopus)

Abstract

Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to move away from the current approach of group-wise comparisons to methods with the sensitivity to detect altered tissue states at the individual level. This would ultimately enable the early detection and interpretation of microstructural abnormalities in individual patients, an important step towards personalized medicine in translational imaging. To this end, Detect was developed to advance diffusion magnetic resonance imaging tractometry towards single-patient analysis. By operating on the manifold of white-matter pathways and learning normative microstructural features, our framework captures idiosyncrasies in patterns along white-matter pathways. Our approach paves the way from traditional group-based comparisons to true personalized radiology, taking microstructural imaging from the bench to the bedside.

Original language	English
Pages (from-to)	598-606
Number of pages	9
Journal	Nature Computational Science
Volume	1
Issue number	9
DOIs	https://doi.org/10.1038/s43588-021-00126-8
Publication status	Published - Sept 2021
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported by a Wellcome Trust Investigator Award (grant no. 096646/Z/11/Z), a Wellcome Trust Strategic Award (grant no. 104943/Z/14/Z), and an EPSRC equipment grant (no. EP/M029778/1) to D.K.J., a Sir Henry Wellcome Fellowship (grant no. 215944/Z/19/Z) and VENI grant (no. 17331) from the Dutch Research Council (NWO) to C.M.W.T., a Wellcome Trust GW4-CAT Fellowship (grant no. 220537/Z/20/Z) to D.S., a Wellcome Trust Fellowship (grant no. 102003/Z/13/Z) to J.D. and an NIH NICDH fellowship (grant no. 1F32HD103313-01) to EPR. This study is also supported by the Brain Repair and Intracranial Neurotherapeutics (BRAIN) Unit, funded by Welsh Government through Health and Care Research Wales. M.C. was in part supported by the Radboud Excellence Initiative Fellowship. The authors thank M. Descoteaux and J.-C. Houde (Sherbrooke Connectivity Imaging Laboratory) for their useful discussions and code sharing.

Funding

This work was supported by a Wellcome Trust Investigator Award (grant no. 096646/Z/11/Z), a Wellcome Trust Strategic Award (grant no. 104943/Z/14/Z), and an EPSRC equipment grant (no. EP/M029778/1) to D.K.J., a Sir Henry Wellcome Fellowship (grant no. 215944/Z/19/Z) and VENI grant (no. 17331) from the Dutch Research Council (NWO) to C.M.W.T., a Wellcome Trust GW4-CAT Fellowship (grant no. 220537/Z/20/Z) to D.S., a Wellcome Trust Fellowship (grant no. 102003/Z/13/Z) to J.D. and an NIH NICDH fellowship (grant no. 1F32HD103313-01) to EPR. This study is also supported by the Brain Repair and Intracranial Neurotherapeutics (BRAIN) Unit, funded by Welsh Government through Health and Care Research Wales. M.C. was in part supported by the Radboud Excellence Initiative Fellowship. The authors thank M. Descoteaux and J.-C. Houde (Sherbrooke Connectivity Imaging Laboratory) for their useful discussions and code sharing. This work was supported by a Wellcome Trust Investigator Award (grant no. 096646/Z/11/Z), a Wellcome Trust Strategic Award (grant no. 104943/Z/14/Z), and an EPSRC equipment grant (no. EP/M029778/1) to D.K.J., a Sir Henry Wellcome Fellowship (grant no. 215944/Z/19/Z) and VENI grant (no. 17331) from the Dutch Research Council (NWO) to C.M.W.T., a Wellcome Trust GW4-CAT Fellowship (grant no. 220537/Z/20/Z) to D.S., a Wellcome Trust Fellowship (grant no. 102003/Z/13/Z) to J.D. and an NIH NICDH fellowship (grant no. 1F32HD103313-01) to EPR. This study is also supported by the Brain Repair and Intracranial Neurotherapeutics (BRAIN) Unit, funded by Welsh Government through Health and Care Research Wales. M.C. was in part supported by the Radboud Excellence Initiative Fellowship. The authors thank M. Descoteaux and J.-C. Houde (Sherbrooke Connectivity Imaging Laboratory) for their useful discussions and code sharing.

Funders	Funder number
National Institutes of Health	1F32HD103313-01
Wellcome Trust	096646/Z/11/Z, 104943/Z/14/Z
Engineering and Physical Sciences Research Council	215944/Z/19/Z, EP/M029778/1, 17331
Nederlandse Organisatie voor Wetenschappelijk Onderzoek	102003/Z/13/Z, 220537/Z/20/Z

Access to Document

10.1038/s43588-021-00126-8

Cite this

Chamberland, M., Genc, S., Tax, C. M. W., Shastin, D., Koller, K., Raven, E. P., Cunningham, A., Doherty, J., van den Bree, M. B. M., Parker, G. D., Hamandi, K., Gray, W. P., & Jones, D. K. (2021). Detecting microstructural deviations in individuals with deep diffusion MRI tractometry. Nature Computational Science, 1(9), 598-606. https://doi.org/10.1038/s43588-021-00126-8

@article{13bbee10451c426ebeda8acf4fa7f5b3,

title = "Detecting microstructural deviations in individuals with deep diffusion MRI tractometry",

abstract = "Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to move away from the current approach of group-wise comparisons to methods with the sensitivity to detect altered tissue states at the individual level. This would ultimately enable the early detection and interpretation of microstructural abnormalities in individual patients, an important step towards personalized medicine in translational imaging. To this end, Detect was developed to advance diffusion magnetic resonance imaging tractometry towards single-patient analysis. By operating on the manifold of white-matter pathways and learning normative microstructural features, our framework captures idiosyncrasies in patterns along white-matter pathways. Our approach paves the way from traditional group-based comparisons to true personalized radiology, taking microstructural imaging from the bench to the bedside.",

author = "Maxime Chamberland and Sila Genc and Tax, \{Chantal M.W.\} and Dmitri Shastin and Kristin Koller and Raven, \{Erika P.\} and Adam Cunningham and Joanne Doherty and \{van den Bree\}, \{Marianne B.M.\} and Parker, \{Greg D.\} and Khalid Hamandi and Gray, \{William P.\} and Jones, \{Derek K.\}",

note = "Funding Information: This work was supported by a Wellcome Trust Investigator Award (grant no. 096646/Z/11/Z), a Wellcome Trust Strategic Award (grant no. 104943/Z/14/Z), and an EPSRC equipment grant (no. EP/M029778/1) to D.K.J., a Sir Henry Wellcome Fellowship (grant no. 215944/Z/19/Z) and VENI grant (no. 17331) from the Dutch Research Council (NWO) to C.M.W.T., a Wellcome Trust GW4-CAT Fellowship (grant no. 220537/Z/20/Z) to D.S., a Wellcome Trust Fellowship (grant no. 102003/Z/13/Z) to J.D. and an NIH NICDH fellowship (grant no. 1F32HD103313-01) to EPR. This study is also supported by the Brain Repair and Intracranial Neurotherapeutics (BRAIN) Unit, funded by Welsh Government through Health and Care Research Wales. M.C. was in part supported by the Radboud Excellence Initiative Fellowship. The authors thank M. Descoteaux and J.-C. Houde (Sherbrooke Connectivity Imaging Laboratory) for their useful discussions and code sharing. ",

year = "2021",

month = sep,

doi = "10.1038/s43588-021-00126-8",

language = "English",

volume = "1",

pages = "598--606",

journal = "Nature Computational Science",

issn = "2662-8457",

publisher = "Nature Publishing Group",

number = "9",

}

TY - JOUR

T1 - Detecting microstructural deviations in individuals with deep diffusion MRI tractometry

AU - Chamberland, Maxime

AU - Genc, Sila

AU - Tax, Chantal M.W.

AU - Shastin, Dmitri

AU - Koller, Kristin

AU - Raven, Erika P.

AU - Cunningham, Adam

AU - Doherty, Joanne

AU - van den Bree, Marianne B.M.

AU - Parker, Greg D.

AU - Hamandi, Khalid

AU - Gray, William P.

AU - Jones, Derek K.

N1 - Funding Information: This work was supported by a Wellcome Trust Investigator Award (grant no. 096646/Z/11/Z), a Wellcome Trust Strategic Award (grant no. 104943/Z/14/Z), and an EPSRC equipment grant (no. EP/M029778/1) to D.K.J., a Sir Henry Wellcome Fellowship (grant no. 215944/Z/19/Z) and VENI grant (no. 17331) from the Dutch Research Council (NWO) to C.M.W.T., a Wellcome Trust GW4-CAT Fellowship (grant no. 220537/Z/20/Z) to D.S., a Wellcome Trust Fellowship (grant no. 102003/Z/13/Z) to J.D. and an NIH NICDH fellowship (grant no. 1F32HD103313-01) to EPR. This study is also supported by the Brain Repair and Intracranial Neurotherapeutics (BRAIN) Unit, funded by Welsh Government through Health and Care Research Wales. M.C. was in part supported by the Radboud Excellence Initiative Fellowship. The authors thank M. Descoteaux and J.-C. Houde (Sherbrooke Connectivity Imaging Laboratory) for their useful discussions and code sharing.

PY - 2021/9

Y1 - 2021/9

N2 - Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to move away from the current approach of group-wise comparisons to methods with the sensitivity to detect altered tissue states at the individual level. This would ultimately enable the early detection and interpretation of microstructural abnormalities in individual patients, an important step towards personalized medicine in translational imaging. To this end, Detect was developed to advance diffusion magnetic resonance imaging tractometry towards single-patient analysis. By operating on the manifold of white-matter pathways and learning normative microstructural features, our framework captures idiosyncrasies in patterns along white-matter pathways. Our approach paves the way from traditional group-based comparisons to true personalized radiology, taking microstructural imaging from the bench to the bedside.

AB - Most diffusion magnetic resonance imaging studies of disease rely on statistical comparisons between large groups of patients and healthy participants to infer altered tissue states in the brain; however, clinical heterogeneity can greatly challenge their discriminative power. There is currently an unmet need to move away from the current approach of group-wise comparisons to methods with the sensitivity to detect altered tissue states at the individual level. This would ultimately enable the early detection and interpretation of microstructural abnormalities in individual patients, an important step towards personalized medicine in translational imaging. To this end, Detect was developed to advance diffusion magnetic resonance imaging tractometry towards single-patient analysis. By operating on the manifold of white-matter pathways and learning normative microstructural features, our framework captures idiosyncrasies in patterns along white-matter pathways. Our approach paves the way from traditional group-based comparisons to true personalized radiology, taking microstructural imaging from the bench to the bedside.

UR - https://www.scopus.com/pages/publications/85125246053

U2 - 10.1038/s43588-021-00126-8

DO - 10.1038/s43588-021-00126-8

M3 - Article

C2 - 35865756

SN - 2662-8457

VL - 1

SP - 598

EP - 606

JO - Nature Computational Science

JF - Nature Computational Science

IS - 9

ER -

Detecting microstructural deviations in individuals with deep diffusion MRI tractometry

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this