Komura, Taku

Valdes Hernandez, Maria

Rachmadi, Muhammad Febrian

other

2020-04-03T12:18:28Z

2020-04-03T12:18:28Z

2020-06-25

White matter hyperintensities (WMH) are neuroradiological features seen in T2 Fluid-Attenuated Inversion Recovery (T2-FLAIR) brain magnetic resonance imaging (MRI) and have been commonly associated with stroke, ageing, dementia, and Alzheimer’s disease (AD) progression. As a marker of neuro-degenerative disease, WMH may change over time and follow the clinical condition of the patient. In contrast to the early longitudinal studies of WMH, recent studies have suggested that the progression of WMH may be a dynamic, non-linear process where different clusters of WMH may shrink, stay unchanged, or grow. In this thesis, these changes are referred to as the “evolution of WMH”. The main objective of this thesis is to develop machine learning methods for prediction of WMH evolution in structural brain MRI from one-time (baseline) assessment. Predicting the evolution of WMH is challenging because the rate and direction of WMH evolution varies greatly across previous studies. Furthermore, the evolution of WMH is a non-deterministic problem because some clinical factors that possibly influence it are still not known. In this thesis, different learning schemes of deep learning algorithm and data modalities are proposed to produce the best estimation of WMH evolution. Furthermore, a scheme to simulate the non-deterministic nature of WMH evolution, named auxiliary input, was also proposed. In addition to the development of prediction model for WMH evolution, machine learning methods for segmentation of early WMH, characterisation of WMH, and simulation of WMH progression and regression are also developed as parts of this thesis.

https://hdl.handle.net/1842/36938

http://dx.doi.org/10.7488/era/239

en

The University of Edinburgh

Rachmadi,M.F., Vald´es-Hern´andez, M. D. C., Li, H., Guerrero, R., Meijboom, R.,Wiseman,S.,Waldman,A.,Zhang,J.,Rueckert,D.,Wardlaw,J.,andKomura, T.(2020). LimitedOne-timeSamplingIrregularityMap(LOTS-IM)forautomatic unsupervised assessment of white matter hyperintensities and multiple sclerosis lesions in structural brain magnetic resonance images. Computerized Medical Imaging and Graphics, 79:101685.

Malla, P., Uziel, C., Vald´es-Hern´andez, M. D. C., Rachmadi,M.F., & Komura, T. (2019). Evaluation of enhanced learning techniques for segmenting ischaemic strokelesionsinbrainmagneticresonanceperfusionimagesusingaconvolutional neural network scheme. Frontiers in Neuroinformatics, 13, 33

Jeong, Y.,Rachmadi,M.F., Vald´es-Hern´andez, M. D. C., & Komura, T. (2019). Dilated saliency U-Net for white matter hyperintensities segmentation using irregularity age map. Frontiers in Aging Neuroscience, 11, 150.

Rachmadi, M. F., Vald´es-Hern´andez, M. D. C., Agan, M. L. F., Di Perri, C., Komura, T., & Alzheimer’s Disease Neuroimaging Initiative. (2018). Segmentation of white matter hyperintensities using convolutional neural networks with globalspatialinformationinroutineclinicalbrainMRIwithnoneormildvascular pathology. Computerized Medical Imaging and Graphics, 66, 28-43

Rachmadi,M.F.,Vald´es-Hern´andezez,M.d. C.,Agan,M.L.F.,andKomura,T. (2017a). Deep learning vs. conventional machine learning: Pilot study of WMH segmentation in brain MRI with absence or mild vascular pathology. Journal of Imaging, 3(4):66.

Rachmadi,M.F., del C. Vald´es-Hern´andez, M., Makin, S., Wardlaw, J. M., and Komura, T. (2019a). Predicting the evolution of white matter hyperintensities in brainMRIusinggenerativeadversarialnetworksandirregularitymap. InMedical Image Computing and Computer Assisted Intervention – MICCAI 2019, pages 146–154, Cham. Springer International Publishing.

Rachmadi,M.F., Vald´es-Hern´andez, M. d. C., and Komura, T. (2018c). Automatic irregular texture detection in brain MRI without human supervision. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, pages 506–513, Cham. Springer International Publishing

Rachmadi, M. F., Vald´es-Hern´andez, M. D. C.,M., and Komura, T. (2018a). Transfer learning for task adaptation of brain lesion assessment and prediction of brain abnormalities progression/regression using irregularity age map in brain MRI. In International Workshop on PRedictive Intelligence In MEdicine, pages 85–93, Cham. Springer International Publishing.

Rachmadi,M.F., Vald´es-Hern´andez, M. d. C., and Komura, T. (2017c). Voxelbased irregularity age map (IAM) for brain’s white matter hyperintensities in MRI. In 2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS), pages 321–326. IEEE

Rachmadi, M. F., Vald´es-Hern´andez, M. d. C., Agan, M. L. F., and Komura, T. (2017b). Evaluation of four supervised learning schemes in white matter hyperintensities segmentation in absence or mild presence of vascular pathology. In Medical Image Understanding and Analysis, pages 482–493, Cham. Springer International Publishing

DBMforMRI URL: https://github.com/febrianrachmadi/boltzmannmachine

LOTS-IM URL: https://github.com/febrianrachmadi/lots-iam-gpu

DEPmodel URL: https://github.com/febrianrachmadi/dep-gan-im

Alzheimer’s disease

predictive models

white matter hyperintensities

MRI

irregularity mapping

Development of machine learning schemes for segmentation, characterisation, and evolution prediction of white matter hyperintensities in structural brain MRI

Thesis or Dissertation

Doctoral

PhD Doctor of Philosophy