Current Applications and Future Promises of Machine Learning in Diffusion MRI

Diffusion-Weighted Magnetic Resonance Imaging (DW-MRI) explores the random motion of diffusing water molecules in biological tissue and can provide information on the tissue structure at a microscopic scale. DW-MRI in used in many applications both in the brain and other parts of the body such as the breast and prostate, and novelcomputational methods are at the core of advancements in DW-MRI, both in terms of research and its clinical translation. This article reviews the ways in whichmachine learning anddeep learning is currently applied in DW-MRI. We will also discuss the more traditional methods used for processing diffusion MRI and the potential of deep learning in augmenting these existing methods in the future.

[1]  Gözde B. Ünal,et al.  Diffusion MRI Spatial Super-Resolution Using Generative Adversarial Networks , 2018, PRIME@MICCAI.

[2]  Timothy Edward John Behrens,et al.  Diffusion MRI : from quantitative measurement to in vivo neuroanatomy , 2014 .

[3]  Klaus H. Maier-Hein,et al.  Adversarial Networks for the Detection of Aggressive Prostate Cancer , 2017, ArXiv.

[4]  J. E. Tanner,et al.  Spin diffusion measurements : spin echoes in the presence of a time-dependent field gradient , 1965 .

[5]  A. Raftery.  Approximate Bayes factors and accounting for model uncertainty in generalised linear models , 1996 .

[6]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

[7]  Dinggang Shen,et al.  3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients , 2016, MICCAI.

[8]  P. Basser,et al.  MR diffusion tensor spectroscopy and imaging. , 1994, Biophysical journal.

[9]  Madhu S. Nair,et al.  Computer-aided classification of prostate cancer grade groups from MRI images using texture features and stacked sparse autoencoder , 2018, Comput. Medical Imaging Graph..

[10]  L. Schad,et al.  Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T , 2017, NMR in biomedicine.

[11]  Leonard E White,et al.  Diffusion tensor imaging assessment of brain white matter maturation during the first postnatal year. , 2007, AJR. American journal of roentgenology.

[12]  Eileen Luders,et al.  Decoding gender dimorphism of the human brain using multimodal anatomical and diffusion MRI data , 2013, NeuroImage.

[13]  M. Horsfield,et al.  Diffusion tensor MRI tractography and cognitive impairment in multiple sclerosis , 2012, Neurology.

[14]  Aaron J. Newman,et al.  Using CForest to Analyze Diffusion Tensor Imaging Data: A Study of White Matter Integrity in Healthy Aging , 2016, Brain Connect..

[15]  Ayman El-Baz,et al.  A new non-invasive approach for early classification of renal rejection types using diffusion-weighted MRI , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[16]  R. Peeters,et al.  Age-related microstructural differences quantified using myelin water imaging and advanced diffusion MRI , 2015, Neurobiology of Aging.

[17]  D. Alexander.  A general framework for experiment design in diffusion MRI and its application in measuring direct tissue‐microstructure features , 2008, Magnetic resonance in medicine.

[18]  Daniel C. Alexander,et al.  Machine learning based compartment models with permeability for white matter microstructure imaging , 2017, NeuroImage.

[19]  Olivier Salvado,et al.  Lesion segmentation from multimodal MRI using random forest following ischemic stroke , 2014, NeuroImage.

[20]  P. Choyke,et al.  Diffusion-weighted magnetic resonance imaging as a cancer biomarker: consensus and recommendations. , 2009, Neoplasia.

[21]  Jürgen Hennig,et al.  Disentangling micro from mesostructure by diffusion MRI: A Bayesian approach , 2017, NeuroImage.

[22]  Hui Zhang,et al.  Imaging brain microstructure with diffusion MRI: practicality and applications , 2019, NMR in biomedicine.

[23]  Daniel Cremers,et al.  q-Space Novelty Detection with Variational Autoencoders , 2018, Computational Diffusion MRI.

[24]  Gareth J. Barker,et al.  Investigating Cervical Spinal Cord Structure Using Axial Diffusion Tensor Imaging , 2002, NeuroImage.

[25]  M. P. van den Heuvel,et al.  Deep learning predictions of survival based on MRI in amyotrophic lateral sclerosis , 2016, NeuroImage: Clinical.

[26]  Tammy Riklin-Raviv,et al.  Ensemble of expert deep neural networks for spatio‐temporal denoising of contrast‐enhanced MRI sequences , 2017, Medical Image Anal..

[27]  Peter F. Neher,et al.  TractSeg - Fast and accurate white matter tract segmentation , 2018, NeuroImage.

[28]  Dmitriy A Yablonskiy,et al.  Theoretical models of the diffusion weighted MR signal , 2010, NMR in biomedicine.

[29]  A. Alexander,et al.  Diffusion tensor imaging of the brain , 2007, Neurotherapeutics.

[30]  R. Gonzalez,et al.  Diffusion-weighted MR imaging of the brain. , 2000, Radiology.

[31]  S. Mori,et al.  Diffusion tensor imaging of normal brain development , 2013, Pediatric Radiology.

[32]  Antonio Criminisi,et al.  Image Quality Transfer via Random Forest Regression: Applications in Diffusion MRI , 2014, MICCAI.

[33]  Pew-Thian Yap,et al.  Robust Fusion of Diffusion MRI Data for Template Construction , 2017, Scientific Reports.

[34]  Dorit Merhof,et al.  Diffusion MRI Signal Augmentation: From Single Shell to Multi Shell with Deep Learning , 2016, MICCAI 2016.

[35]  Masoom A. Haider,et al.  Prostate cancer localization with multispectral MRI based on Relevance Vector Machines , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[36]  Ramana V. Grandhi,et al.  A Bayesian approach for quantification of model uncertainty , 2010, Reliab. Eng. Syst. Saf..

[37]  Carl-Fredrik Westin,et al.  A Bayesian approach for stochastic white matter tractography , 2006, IEEE Transactions on Medical Imaging.

[38]  V. Kiselev,et al.  Quantifying brain microstructure with diffusion MRI: Theory and parameter estimation , 2016, NMR in biomedicine.

[39]  R. Henry,et al.  Diffusion Tensor MR Imaging and Fiber Tractography: Theoretic Underpinnings , 2008, American Journal of Neuroradiology.

[40]  Antonio Criminisi,et al.  Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution , 2017, MICCAI.

[41]  H. Aerts,et al.  Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR , 2017, Scientific Reports.

[42]  Jan Wolber,et al.  Diffusion MRI for prediction of response of rectal cancer to chemoradiation , 2002, The Lancet.

[43]  Dorit Merhof,et al.  Direct Estimation of Fiber Orientations Using Deep Learning in Diffusion Imaging , 2016, MLMI@MICCAI.

[44]  Daniel C. Alexander,et al.  An unsupervised group average cortical parcellation using HARDI data , 2015 .

[45]  Masoom A. Haider,et al.  Prostate Cancer Localization With Multispectral MRI Using Cost-Sensitive Support Vector Machines and Conditional Random Fields , 2010, IEEE Transactions on Image Processing.

[46]  Xiaoying Wang,et al.  Performance of U-net based pyramidal lucas-kanade registration on free-breathing multi-b-value diffusion MRI of the kidney. , 2018, The British journal of radiology.

[47]  Jürgen Hennig,et al.  Fully automated classification of HARDI in vivo data using a support vector machine , 2009, NeuroImage.

[48]  Alexander Wong,et al.  Fully automated segmentation of prostate whole gland and transition zone in diffusion-weighted MRI using convolutional neural networks , 2017, Journal of medical imaging.

[49]  Iasonas Kokkinos,et al.  Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images , 2018, MICCAI.

[50]  Rachid Deriche,et al.  Deterministic and Probabilistic Tractography Based on Complex Fibre Orientation Distributions , 2009, IEEE Transactions on Medical Imaging.

[51]  Antonio Criminisi,et al.  Bayesian Image Quality Transfer , 2016, MICCAI.

[52]  Fatma Taher,et al.  Computer-Aided Diagnostic System for Early Detection of Acute Renal Transplant Rejection Using Diffusion-Weighted MRI , 2019, IEEE Transactions on Biomedical Engineering.

[53]  Rachid Deriche,et al.  Mathematical methods for diffusion MRI processing , 2009, NeuroImage.

[54]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[55]  Peter F. Neher,et al.  Fiber tractography using machine learning , 2017, NeuroImage.

[56]  Antonio Criminisi,et al.  Image quality transfer and applications in diffusion MRI , 2017, NeuroImage.

[57]  M. Lythgoe,et al.  Deep learning diffusion fingerprinting to detect brain tumour response to chemotherapy , 2017, bioRxiv.

[58]  Hamid Soltanian-Zadeh,et al.  Predicting Final Extent of Ischemic Infarction Using Artificial Neural Network Analysis of Multi-Parametric MRI in Patients with Stroke , 2009, 2009 International Joint Conference on Neural Networks.

[59]  Rachid Deriche,et al.  Assessing the feasibility of estimating axon diameter using diffusion models and machine learning , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[60]  Daniele Ravì,et al.  Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy , 2019, Medical Image Anal..

[61]  Meng Law,et al.  Clinical applications of diffusion tensor imaging. , 2014, World neurosurgery.

[62]  Ning-Yu An,et al.  Differentiation of clinically benign and malignant breast lesions using diffusion‐weighted imaging , 2002, Journal of magnetic resonance imaging : JMRI.

[63]  Brian D Ross,et al.  Predicting and monitoring cancer treatment response with diffusion‐weighted MRI , 2010, Journal of magnetic resonance imaging : JMRI.

[64]  Lothar R Schad,et al.  Machine learning in preoperative glioma MRI: Survival associations by perfusion‐based support vector machine outperforms traditional MRI , 2014, Journal of magnetic resonance imaging : JMRI.

[65]  Daniel Cremers,et al.  q-Space Deep Learning for Twelve-Fold Shorter and Model-Free Diffusion MRI Scans , 2015, MICCAI.