Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images

Muhammad Febrian Rachmadi (Lead / Corresponding author), Maria Del C. Valdés-Hernández, Hongwei Li, Ricardo Guerrero, Rozanna Meijboom, Stewart Wiseman, Adam Waldman, Jianguo Zhang, Daniel Rueckert, Joanna Wardlaw, Taku Komura

Research output: Contribution to journalArticle

Abstract

We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered "normal". Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions' segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

Original languageEnglish
Article number101685
Pages (from-to)1-13
Number of pages13
JournalComputerized Medical Imaging and Graphics
Volume79
Early online date27 Nov 2019
DOIs
Publication statusPublished - Jan 2020

Fingerprint

Magnetic resonance
Multiple Sclerosis
Brain
Magnetic Resonance Spectroscopy
Sampling
Learning
Tissue Extracts
Arteriosclerosis
Learning algorithms
Learning systems
Pathology
White Matter
Growth
Magnetic resonance imaging
Support vector machines
Textures
Tissue
Neural networks
Supervised Machine Learning
Processing

Keywords

  • White matter hyperintensities (WMH)
  • Multiple sclerosis (MS) lesion
  • unsupervised lesion segmentation
  • irregularity map
  • penumbra of brain's lesion
  • characterisation of WMH and MS lesions

Cite this

Rachmadi, Muhammad Febrian ; Valdés-Hernández, Maria Del C. ; Li, Hongwei ; Guerrero, Ricardo ; Meijboom, Rozanna ; Wiseman, Stewart ; Waldman, Adam ; Zhang, Jianguo ; Rueckert, Daniel ; Wardlaw, Joanna ; Komura, Taku. / Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images. In: Computerized Medical Imaging and Graphics. 2020 ; Vol. 79. pp. 1-13.
@article{50db3a8cd8f74c119759f64028f6a8ae,
title = "Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images",
abstract = "We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered {"}normal{"}. Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions' segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.",
keywords = "White matter hyperintensities (WMH), Multiple sclerosis (MS) lesion, unsupervised lesion segmentation, irregularity map, penumbra of brain's lesion, characterisation of WMH and MS lesions",
author = "Rachmadi, {Muhammad Febrian} and Vald{\'e}s-Hern{\'a}ndez, {Maria Del C.} and Hongwei Li and Ricardo Guerrero and Rozanna Meijboom and Stewart Wiseman and Adam Waldman and Jianguo Zhang and Daniel Rueckert and Joanna Wardlaw and Taku Komura",
note = "The first author would like to thank Indonesia Endowment Fund for Education (LPDP) of Ministry of Finance, Republic of Indonesia, for funding his study at School of Informatics, the University of Edinburgh. Funds from Row Fogo Charitable Trust (Grant No. BRO-D.FID3668413)(MCVH) are also gratefully acknowledged. Data collection and sharing for this project was partially funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research and Development, LLC.; Johnson and Johnson Pharmaceutical Research and Development LLC.; Lumosity; Lundbeck; Merck and Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. FutureMS is supported by an exemplar grant from the Stratified Medicine Scotland Innovation Centre and funding from Biogen, Inc (Cambridge, Massachusetts, https://www.biogen.com/). RM (and partially MCVH) salaries are supported by the CSO-PME grant to the Stratified Medicine Scotland Innovation Centre. References Copyright {\circledC} 2019 Elsevier Ltd. All rights reserved.",
year = "2020",
month = "1",
doi = "10.1016/j.compmedimag.2019.101685",
language = "English",
volume = "79",
pages = "1--13",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier",

}

Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images. / Rachmadi, Muhammad Febrian (Lead / Corresponding author); Valdés-Hernández, Maria Del C.; Li, Hongwei; Guerrero, Ricardo; Meijboom, Rozanna; Wiseman, Stewart; Waldman, Adam; Zhang, Jianguo; Rueckert, Daniel; Wardlaw, Joanna; Komura, Taku.

In: Computerized Medical Imaging and Graphics, Vol. 79, 101685, 01.2020, p. 1-13.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images

AU - Rachmadi, Muhammad Febrian

AU - Valdés-Hernández, Maria Del C.

AU - Li, Hongwei

AU - Guerrero, Ricardo

AU - Meijboom, Rozanna

AU - Wiseman, Stewart

AU - Waldman, Adam

AU - Zhang, Jianguo

AU - Rueckert, Daniel

AU - Wardlaw, Joanna

AU - Komura, Taku

N1 - The first author would like to thank Indonesia Endowment Fund for Education (LPDP) of Ministry of Finance, Republic of Indonesia, for funding his study at School of Informatics, the University of Edinburgh. Funds from Row Fogo Charitable Trust (Grant No. BRO-D.FID3668413)(MCVH) are also gratefully acknowledged. Data collection and sharing for this project was partially funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research and Development, LLC.; Johnson and Johnson Pharmaceutical Research and Development LLC.; Lumosity; Lundbeck; Merck and Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. FutureMS is supported by an exemplar grant from the Stratified Medicine Scotland Innovation Centre and funding from Biogen, Inc (Cambridge, Massachusetts, https://www.biogen.com/). RM (and partially MCVH) salaries are supported by the CSO-PME grant to the Stratified Medicine Scotland Innovation Centre. References Copyright © 2019 Elsevier Ltd. All rights reserved.

PY - 2020/1

Y1 - 2020/1

N2 - We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered "normal". Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions' segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

AB - We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered "normal". Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions' segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

KW - White matter hyperintensities (WMH)

KW - Multiple sclerosis (MS) lesion

KW - unsupervised lesion segmentation

KW - irregularity map

KW - penumbra of brain's lesion

KW - characterisation of WMH and MS lesions

UR - http://www.scopus.com/inward/record.url?scp=85076844379&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2019.101685

DO - 10.1016/j.compmedimag.2019.101685

M3 - Article

C2 - 31846826

VL - 79

SP - 1

EP - 13

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

M1 - 101685

ER -