R. Prashanth

Automatic classification and prediction models for early Parkinson's disease diagnosis from SPECT imaging

Propose methods for very accurate classification of early PD using only 4 features.Used public database which is large and diverse making the developed models robust.First study to develop accurate prognostic model based on SBR features for early PD. Early and accurate diagnosis of Parkinsons disease (PD) is important for early management, proper prognostication and for initiating neuroprotective therapies once they become available. Recent neuroimaging techniques such as dopaminergic imaging using single photon emission computed tomography (SPECT) with 123I-Ioflupane (DaTSCAN) have shown to detect even early stages of the disease. In this paper, we use the striatal binding ratio (SBR) values that are calculated from the 123I-Ioflupane SPECT scans (as obtained from the Parkinsons progression markers initiative (PPMI) database) for developing automatic classification and prediction/prognostic models for early PD. We used support vector machine (SVM) and logistic regression in the model building process. We observe that the SVM classifier with RBF kernel produced a high accuracy of more than 96% in classifying subjects into early PD and healthy normal; and the logistic model for estimating the risk of PD also produced high degree of fitting with statistical significance indicating its usefulness in PD risk estimation. Hence, we infer that such models have the potential to aid the clinicians in the PD diagnostic process.

High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning

Early (or preclinical) diagnosis of Parkinsons disease (PD) is crucial for its early management as by the time manifestation of clinical symptoms occur, more than 60% of the dopaminergic neurons have already been lost. It is now established that there exists a premotor stage, before the start of these classic motor symptoms, characterized by a constellation of clinical features, mostly non-motor in nature such as Rapid Eye Movement (REM) sleep Behaviour Disorder (RBD) and olfactory loss. In this paper, we use the non-motor features of RBD and olfactory loss, along with other significant biomarkers such as Cerebrospinal fluid (CSF) measurements and dopaminergic imaging markers from 183 healthy normal and 401 early PD subjects, as obtained from the Parkinsons Progression Markers Initiative (PPMI) database, to classify early PD subjects from normal using Naïve Bayes, Support Vector Machine (SVM), Boosted Trees and Random Forests classifiers. We observe that SVM classifier gave the best performance (96.40% accuracy, 97.03% sensitivity, 95.01% specificity, and 98.88% area under ROC). We infer from the study that a combination of non-motor, CSF and imaging markers may aid in the preclinical diagnosis of PD.

High-Accuracy Classification of Parkinson's Disease Through Shape Analysis and Surface Fitting in 123I-Ioflupane SPECT Imaging

Early and accurate identification of Parkinsonian syndromes (PS) involving presynaptic degeneration from nondegenerative variants such as scans without evidence of dopaminergic deficit (SWEDD) and tremor disorders is important for effective patient management as the course, therapy, and prognosis differ substantially between the two groups. In this study, we use single photon emission computed tomography (SPECT) images from healthy normal, early PD, and SWEDD subjects, as obtained from the Parkinsons Progression Markers Initiative (PPMI) database, and process them to compute shape- and surface-fitting-based features. We use these features to develop and compare various classification models that can discriminate between scans showing dopaminergic deficit, as in PD, from scans without the deficit, as in healthy normal or SWEDD. Along with it, we also compare these features with striatal binding ratio (SBR)-based features, which are well established and clinically used, by computing a feature-importance score using random forests technique. We observe that the support vector machine (SVM) classifier gives the best performance with an accuracy of 97.29%. These features also show higher importance than the SBR-based features. We infer from the study that shape analysis and surface fitting are useful and promising methods for extracting discriminatory features that can be used to develop diagnostic models that might have the potential to help clinicians in the diagnostic process.

Parkinson's disease detection using olfactory loss and REM sleep disorder features

In Parkinsons disease, there exists a prodromal or a premotor phase characterized by symptoms like olfactory loss and sleep disorders, which may last for years or even decades before the onset of motor clinical symptoms. Diagnostic tools based on machine learning using these features can be very useful as they have the potential in early diagnosis of the disease. In the paper, we use olfactory loss feature from 40-item University of Pennsylvania Smell Identification Test (UPSIT) and Sleep behavior disorder feature from Rapid eye movement sleep Behavior Disorder Screening Questionnaire (RBDSQ), obtained from the Parkinsons Progression Markers Initiative (PPMI) database, to develop automated diagnostic models using Support Vector Machine (SVM) and classification tree methods. The advantage of using UPSIT and RBDSQ is that they are quick, cheap, and can be self-administered. Results show that the models performed with high accuracy and sensitivity, and that they have the potential to aid in early diagnosis of Parkinsons disease.

Shape features as biomarkers in early Parkinson's disease

In vivo dopaminergic imaging through [123I]FP-CIT Single Photon Emission Computerized Tomography (SPECT) provide useful information which enhances the accuracy of diagnosis of PD. Such imaging techniques have given rise to new class of subjects termed scans without evidence of dopaminergic Deficit (SWEDD) subjects, who are clinically diagnosed as PD but show normal dopaminergic scans. Although it is now established that the appearance of striatal uptake patterns, as seen in the SPECT images, change in shape during PD as compared to Normal or SWEDD subjects, as per our knowledge, there have been no studies on the quantification of the shape of these uptake regions. We in our study, use the [123I]FP-CIT SPECT data from 20 Normal, 20 SWEDD and 20 Early PD subjects from the Parkinsons Progression Markers Initiative (PPMI) database to segment, followed by quantification of these regions. It is observed that the quantification parameters show good amount of variation in PD as compared to Normal or SWEDD subjects. Hence, it is inferred that these parameters may be useful biomarkers for the early diagnosis of PD.

Early detection of Parkinson's disease through shape based features from 123 I-Ioflupane SPECT imaging

Detection of Parkinsons disease (PD) at an early stage is important for effective management and for initiating neuroprotective strategies early in the therapeutic process. Single photon emission computed tomography (SPECT) using 123I-Ioflupane (DaTSCANTM, GE Healthcare; also known as [123I]FP-CIT) have shown to be a sensitive marker for PD even in the early stages of the disease. In this paper, we carry out image processing to compute shape-based features which are radial and gradient features from SPECT scans from 163 early-stage PD and 187 healthy normal subjects obtained from the Parkinsons Progression Markers Initiative (PPMI), and use them along with the striatal binding ratio (SBR) values, also provided by the PPMI as features to classify between the two using Discriminant Analysis and Support Vector Machine (SVM). We observe a high accuracy of 99.42% in classification. It is inferred that such models can aid clinicians in the early diagnostics of PD.

Surface fitting in SPECT imaging useful for detecting Parkinson's Disease and Scans Without Evidence of Dopaminergic Deficit

Dopaminergic imaging using Single Photon Emission Computed Tomography (SPECT) with 123I-Ioflupane have shown to increase the diagnostic accuracy in Parkinsons Disease (PD). Studies show that around 10% of subjects who are clinically diagnosed as PD, have SPECT scans in the normal range and are called Scans Without Evidence of Dopaminergic Deficit (SWEDD) subjects. Subsequent follow-up on these subjects has indicated that they are unlikely to have PD. Detection and differentiation of PD and SWEDD is problematic in the early stages of the disease. Early and accurate diagnosis of PD and also SWEDD is crucial for early management, avoidance of unnecessary medical examinations and therapies; and their side-effects. We in our paper, use the SPECT images from 35 Normal, 36 PD and 38 SWEDD subjects as obtained from the Parkinsons Progression Markers Initiative (PPMI) database, to carry out intensity-based surface fitting using polynomial model. This is the first time that such kind of modeling is carried out on the SPECT images for the characterization of PD. Our results show that the surface profile in terms of model coefficients and goodness-of-fit parameters is different for Normal, Early PD and SWEDD subjects. Such kind of modeling may aid in the diagnosis of early PD and SWEDD from SPECT images.

Novel and improved stage estimation in Parkinson's disease using clinical scales and machine learning

Abstract The stage and severity of Parkinsons disease (PD) is an important factor to consider for taking effective therapeutic decisions. Although the Movement Disorder Society-Unified Parkinsons Disease Rating Scale (MDS-UPDRS) provides an effective instrument evaluating the most pertinent features of PD, it does not allow PD staging. On the other hand, the Hoehn and Yahr (HY) scale which provides staging, does not evaluate many relevant features of PD. In this paper, we propose a novel and improved staging for PD using the MDS-UPDRS features and the HY scale, and developing prediction models to estimate the stage (normal, early or moderate) and severity of PD using machine learning techniques such as ordinal logistic regression (OLR), support vector machine (SVM), AdaBoost- and RUSBoost-based classifiers. Along with this, feature importance in PD is also estimated using Random forests. We observe that the predictive models of SVM, Adaboost-based ensemble, Random forests and probabilistic generative model performed well with the AdaBoost-based ensemble giving the highest accuracy of 97.46%. Body bradykinesia, tremor, facial expression (hypomimia), constancy of rest tremor and handwriting (micrographia) were observed to be the most important features in PD. It is inferred that MDS-UPDRS combined with classifiers can form effective tools to predict PD staging which can aid clinicians in the diagnostic process.

Early detection of Parkinson’s disease through patient questionnaire and predictive modelling

Early detection of Parkinsons disease (PD) is important which can enable early initiation of therapeutic interventions and management strategies. However, methods for early detection still remain an unmet clinical need in PD. In this study, we use the Patient Questionnaire (PQ) portion from the widely used Movement Disorder Society-Unified Parkinsons Disease Rating Scale (MDS-UPDRS) to develop prediction models that can classify early PD from healthy normal using machine learning techniques that are becoming popular in biomedicine: logistic regression, random forests, boosted trees and support vector machine (SVM). We carried out both subject-wise and record-wise validation for evaluating the machine learning techniques. We observe that these techniques perform with high accuracy and high area under the ROC curve (both >95%) in classifying early PD from healthy normal. The logistic model demonstrated statistically significant fit to the data indicating its usefulness as a predictive model. It is inferred that these prediction models have the potential to aid clinicians in the diagnostic process by joining the items of a questionnaire through machine learning.

perception-based design for tele-presence

We present a novel perception-driven approach to low-cost tele-presence systems, to support immersive experience in continuity between projected video and conferencing room.We use geometry and spectral correction to impart for perceptual continuity to the whole scene. The geometric correction comes from a learning-based approach to identifying horizontal and vertical surfaces. Our method redraws the projected video to match its vanishing point with that of the conference room in which it is projected. We quantify intuitive concepts such as the depth-of-field using a Gabor filter analysis of overall images of the conference room. We equalise spectral features across the projected video and the conference room, for spectral continuity between the two.