Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning.

Background: Patients with Parkinson's disease (PD) and progressive supranuclear palsy Richardson's syndrome (PSP-RS) often show overlapping clinical features, leading to misdiagnoses. The objective of this study was to investigate the feasibility and utility of using multi-modal MRI datasets for an automatic differentiation of PD patients, PSP-RS patients, and healthy control (HC) subjects. Material and Methods: T1-weighted, T2-weighted, and diffusion-tensor (DTI) MRI datasets from 45 PD patients, 20 PSP-RS patients, and 38 HC subjects were available for this study. Using an atlas-based approach, regional values of brain morphology (T1-weighted), brain iron metabolism (T2-weighted), and microstructural integrity (DTI) were measured and employed for feature selection and subsequent classification using combinations of various established machine learning methods. Results: The optimal machine learning model using regional morphology features only achieved a classification accuracy of 65% (67/103 correct classifications) differentiating PD patients, PSP-RS patients, and HC subjects. The optimal machine learning model using only quantitative T2 values performed slightly better and achieved an accuracy of 75.7% (78/103). The optimal classifier using DTI features alone performed considerably better with 95.1% accuracy (98/103). The optimal multi-modal classifier using all features also achieved an accuracy of 95.1% but required more features and achieved a slightly lower F1-score compared to the optimal model using DTI features alone. Conclusion: Machine learning models using multi-modal MRI perform significantly better than uni-modal machine learning models using morphological parameters based on T1-weighted MRI datasets alone or brain iron metabolism markers based on T2-weighted MRI datasets alone. However, machine learnig models using regional brain microstructural integrity metrics computed from DTI datasets perform similar to the optimal multi-modal machine learning model. Thus, given the results from this study cohort, it appears that morphology and brain iron metabolism markers may not provide additional value for classification compared to using DTI metrics alone.

Defining reperfusion post endovascular therapy in ischemic stroke using MR-dynamic contrast enhanced perfusion.

OBJECTIVES: Cerebral blood flow (CBF) measurements after endovascular therapy (EVT) for acute ischemic stroke are important to distinguish early secondary injury related to persisting ischemia from that related to reperfusion when considering clinical response and infarct growth. METHODS: We compare reperfusion quantified by the modified Thrombolysis in Cerebral Infarction Score (mTICI) with perfusion measured by MRI dynamic contrast-enhanced perfusion within 5 h of EVT anterior circulation stroke. MR perfusion (rCBF, rCBV, rTmax, rT0) and mTICI scores were included in a predictive model for change in NIHSS at 24 h and diffusion-weighted imaging (DWI) lesion growth (acute to 24 h MRI) using a machine learning RRELIEFF feature selection coupled with a support vector regression. RESULTS: For all perfusion parameters, mean values within the acute infarct for the TICI-2b group (considered clinically good reperfusion) were not significantly different from those in the mTICI <2b (clinically poor reperfusion). However, there was a statistically significant difference in perfusion values within the acute infarct region of interest between the mTICI-3 group versus both mTICI-2b and <2b (p = 0.02). The features that made up the best predictive model for change in NIHSS and absolute DWI lesion volume change was rT0 within acute infarct ROI and admission CTA collaterals respectively. No other variables, including mTICI scores, were selected for these best models. The correlation coefficients (Root mean squared error) for the cross-validation were 0.47 (13.7) and 0.51 (5.7) for change in NIHSS and absolute DWI lesion volume change. CONCLUSION: MR perfusion following EVT provides accurate physiological approach to understanding the relationship of CBF, clinical outcome, and DWI growth. ADVANCES IN KNOWLEDGE: MR perfusion CBF acquired is a robust, objective reperfusion measurement providing following recanalization of the target occlusion which is critical to distinguish potential therapeutic harm from the failed technical success of EVT as well as improve the responsiveness of clinical trial outcomes to disease modification.

Building an Otoscopic screening prototype tool using deep learning.

BACKGROUND: Otologic diseases are often difficult to diagnose accurately for primary care providers. Deep learning methods have been applied with great success in many areas of medicine, often outperforming well trained human observers. The aim of this work was to develop and evaluate an automatic software prototype to identify otologic abnormalities using a deep convolutional neural network. MATERIAL AND METHODS: A database of 734 unique otoscopic images of various ear pathologies, including 63 cerumen impactions, 120 tympanostomy tubes, and 346 normal tympanic membranes were acquired. 80% of the images were used for the training of a convolutional neural network and the remaining 20% were used for algorithm validation. Image augmentation was employed on the training dataset to increase the number of training images. The general network architecture consisted of three convolutional layers plus batch normalization and dropout layers to avoid over fitting. RESULTS: The validation based on 45 datasets not used for model training revealed that the proposed deep convolutional neural network is capable of identifying and differentiating between normal tympanic membranes, tympanostomy tubes, and cerumen impactions with an overall accuracy of 84.4%. CONCLUSION: Our study shows that deep convolutional neural networks hold immense potential as a diagnostic adjunct for otologic disease management.

Improved Automatic Morphology-Based Classification of Parkinson's Disease and Progressive Supranuclear Palsy.

OBJECTIVES: The overlapping symptoms of Parkinson's disease (PD) and progressive supranuclear palsy-Richardson's syndrome (PSP-RS) often make a correct clinical diagnosis difficult. The volume of subcortical brain structures derived from high-resolution T1-weighted magnetic resonance imaging (MRI) datasets is frequently used for individual level classification of PD and PSP-RS patients. The aim of this study was to evaluate the benefit of including additional morphological features beyond the simple regional volume, as well as clinical features, and morphological features of cortical structures for an automatic classification of PD and PSP-RS patients. MATERIAL AND METHODS: A total of 98 high-resolution T1-weighted MRI datasets from 76 PD patients, and 22 PSP-RS patients were available for this study. Using an atlas-based approach, the volume, surface area, and surface-area-to-volume ratio (SA:V) of 21 subcortical and 48 cortical brain regions were calculated and used as features for a support vector machine classification after application of a RELIEF feature selection method. RESULTS: The comparison of the classification results suggests that including all three morphological parameters (volume, surface area and SA:V) can considerably improve classification accuracy compared to using volume or surface area alone. Likewise, including clinical patient features in addition to morphological parameters also considerably increases the classification accuracy. In contrast to this, integrating morphological features of other cortical structures did not lead to improved classification accuracy. Using this optimal set-up, an accuracy of 98% was achieved with only one falsely classified PD and one falsely classified PSP-RS patient. CONCLUSION: The results of this study suggest that clinical features as well as more advanced morphological features should be used for future computer-aided diagnosis systems to differentiate PD and PSP-RS patients based on morphological parameters.

Widespread diffusion changes differentiate Parkinson's disease and progressive supranuclear palsy.

BACKGROUND: Parkinson's disease (PD) and progressive supranuclear palsy - Richardson's syndrome (PSP-RS) are often represented by similar clinical symptoms, which may challenge diagnostic accuracy. The objective of this study was to investigate and compare regional cerebral diffusion properties in PD and PSP-RS subjects and evaluate the use of these metrics for an automatic classification framework. MATERIAL AND METHODS: Diffusion-tensor MRI datasets from 52 PD and 21 PSP-RS subjects were employed for this study. Using an atlas-based approach, regional median values of mean diffusivity (MD), fractional anisotropy (FA), radial diffusivity (RD), and axial diffusivity (AD) were measured and employed for feature selection using RELIEFF and subsequent classification using a support vector machine. RESULTS: According to RELIEFF, the top 17 diffusion values consisting of deep gray matter structures, the brainstem, and frontal cortex were found to be especially informative for an automatic classification. A MANCOVA analysis performed on these diffusion values as dependent variables revealed that PSP-RS and PD subjects differ significantly (p < .001). Generally, PSP-RS subjects exhibit reduced FA, and increased MD, RD, and AD values in nearly all brain structures analyzed compared to PD subjects. The leave-one-out cross-validation of the support vector machine classifier revealed that the classifier can differentiate PD and PSP-RS subjects with an accuracy of 87.7%. More precisely, six PD subjects were wrongly classified as PSP-RS and three PSP-RS subjects were wrongly classified as PD. CONCLUSION: The results of this study demonstrate that PSP-RS subjects exhibit widespread and more severe diffusion alterations compared to PD patients, which appears valuable for an automatic computer-aided diagnosis approach.