Predictive markers for Parkinson's disease using deep neural nets on neuromelanin sensitive MRI

Neuromelanin sensitive magnetic resonance imaging (NMS-MRI) has been crucial in identifying abnormalities in the substantia nigra pars compacta (SNc) in Parkinson's disease (PD) as PD is characterized by loss of dopaminergic neurons in the SNc. Current techniques employ estimation of contrast ratios of the SNc, visualized on NMS-MRI, to discern PD patients from the healthy controls. However, the extraction of these features is time-consuming and laborious and moreover provides lower prediction accuracies. Furthermore, these do not account for patterns of subtle changes in PD in the SNc. To mitigate this, our work establishes a computer-based analysis technique that uses convolutional neural networks (CNNs) to create prognostic and diagnostic biomarkers of PD from NMS-MRI. Our technique not only performs with a superior testing accuracy (80%) as compared to contrast ratio-based classification (56.5% testing accuracy) and radiomics classifier (60.3% testing accuracy), but also supports discriminating PD from atypical parkinsonian syndromes (85.7% test accuracy). Moreover, it has the capability to locate the most discriminative regions on the neuromelanin contrast images. These discriminative activations demonstrate that the left SNc plays a key role in the classification in comparison to the right SNc, and are in agreement with the concept of asymmetry in PD. Overall, the proposed technique has the potential to support radiological diagnosis of PD while facilitating deeper understanding into the abnormalities in SNc.

[1]  M. Ingalhalikar,et al.  Altered structural connectivity of the motor subnetwork in multiple system atrophy with cerebellar features , 2018, European Radiology.

[2]  P. Yates,et al.  PATHOLOGICAL BASIS FOR NEUROTRANSMITTER CHANGES IN PARKINSON'S DISEASE , 1983, Neuropathology and applied neurobiology.

[3]  F. Valldeoriola,et al.  Discriminating cognitive status in Parkinson’s disease through functional connectomics and machine learning , 2017, Scientific Reports.

[4]  Sabina Sonia Tangaro,et al.  Complex networks reveal early MRI markers of Parkinson's disease , 2018, Medical Image Anal..

[5]  Salvatore Nigro,et al.  Magnetic resonance support vector machine discriminates essential tremor with rest tremor from tremor‐dominant Parkinson disease , 2014, Movement disorders : official journal of the Movement Disorder Society.

[6]  Ehsan Adeli,et al.  Joint feature-sample selection and robust diagnosis of Parkinson's disease from MRI data , 2016, NeuroImage.

[7]  Madhuri Behari,et al.  Regions-of-interest based automated diagnosis of Parkinson's disease using T1-weighted MRI , 2015, Expert Syst. Appl..

[8]  Jan Kassubek,et al.  Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification , 2016, Movement disorders : official journal of the Movement Disorder Society.

[9]  Yasuo Terayama,et al.  Neuromelanin magnetic resonance imaging of locus ceruleus and substantia nigra in Parkinson's disease , 2006, Neuroreport.

[10]  Yi Wang,et al.  3D texture analyses within the substantia nigra of Parkinson's disease patients on quantitative susceptibility maps and R2∗ maps , 2019, NeuroImage.

[11]  Mikel Ariz,et al.  Dynamic Atlas-Based Segmentation and Quantification of Neuromelanin-Rich Brainstem Structures in Parkinson Disease , 2019, IEEE Transactions on Medical Imaging.

[12]  P. Pal,et al.  Motor asymmetry and neuromelanin imaging: Concordance in Parkinson's disease. , 2018, Parkinsonism & related disorders.

[13]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[14]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[15]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[16]  Scott A. Wylie,et al.  Handedness and motor symptom asymmetry in Parkinson's disease , 2010, Journal of Neurology, Neurosurgery & Psychiatry.

[17]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  Lakshminarayanan Samavedham,et al.  Unsupervised learning based feature extraction for differential diagnosis of neurodegenerative diseases: A case study on early-stage diagnosis of Parkinson disease , 2015, Journal of Neuroscience Methods.

[20]  A. Cerasa,et al.  Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy , 2014, Journal of Neuroscience Methods.

[21]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  A. Lees,et al.  A clinicopathologic study of 100 cases of Parkinson's disease. , 1993, Archives of neurology.

[24]  Jitender Saini,et al.  Altered Brain Wiring in Parkinson's Disease: A Structural Connectome-Based Analysis , 2017, Brain Connect..

[25]  Stanley Fahn,et al.  Neuromelanin detection by magnetic resonance imaging (MRI) and its promise as a biomarker for Parkinson’s disease , 2018, npj Parkinson's Disease.

[26]  M. Hallett,et al.  Clinical research criteria for the diagnosis of progressive supranuclear palsy (Steele-Richardson-Olszewski syndrome) , 1996, Neurology.

[27]  M. Ingalhalikar,et al.  Predictive markers for Parkinson’s disease using deep neural nets on neuromelanin sensitive MRI , 2019, bioRxiv.

[28]  Hidekazu Tomimoto,et al.  Neuromelanin Magnetic Resonance Imaging in Parkinson's Disease and Multiple System Atrophy , 2013, European Neurology.

[29]  Aldo Quattrone,et al.  Magnetic resonance support vector machine discriminates between Parkinson disease and progressive supranuclear palsy , 2014, Movement disorders : official journal of the Movement Disorder Society.

[30]  Raymond Y Huang,et al.  Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging , 2017, Clinical Cancer Research.

[31]  M Hutchinson,et al.  Structural changes of the substantia nigra in Parkinson's disease as revealed by MR imaging. , 2000, AJNR. American journal of neuroradiology.

[32]  Yasuo Terayama,et al.  Differentiation of early-stage parkinsonisms using neuromelanin-sensitive magnetic resonance imaging. , 2014, Parkinsonism & related disorders.

[33]  Hiroki Shirato,et al.  3D neuromelanin-sensitive magnetic resonance imaging with semi-automated volume measurement of the substantia nigra pars compacta for diagnosis of Parkinson’s disease , 2013, Neuroradiology.

[34]  Yasuo Terayama,et al.  Changes in substantia nigra and locus coeruleus in patients with early-stage Parkinson's disease using neuromelanin-sensitive MR imaging , 2013, Neuroscience Letters.

[35]  Bradley J. Erickson,et al.  Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status , 2017, Journal of Digital Imaging.

[36]  P Sandroni,et al.  Second consensus statement on the diagnosis of multiple system atrophy , 2008, Neurology.

[37]  P. Pal,et al.  Three‐dimensional neuromelanin‐sensitive magnetic resonance imaging of the substantia nigra in Parkinson's disease , 2018, European journal of neurology.

[38]  O. Rascol,et al.  MRI supervised and unsupervised classification of Parkinson's disease and multiple system atrophy , 2018, Movement disorders : official journal of the Movement Disorder Society.