Unsupervised learning based feature extraction for differential diagnosis of neurodegenerative diseases: A case study on early-stage diagnosis of Parkinson disease

Singh, Gurpreet; Samavedham, Lakshminarayanan

doi:10.1016/j.jneumeth.2015.08.011

Cited by 65 publications

(42 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The somewhat subjective nature of UPDRS evaluation makes this scale also prone to inter-rater variability. There have been multiple attempts to improve the reliability and accuracy of disease metrics and establishing early diagnosis, such as feature extraction algorithms using MRI data (Noh et al, 2015, Singh and Samavedham, 2015), population-based modeling using a combination of genetic and clinical data (Nalls et al, 2015) or combination of DAT SPECT and clinical data (Suwijn et al, 2015). Despite this, though we recognize uncertainties associated with onset (both time of diagnosis and time of first reported symptom) and disease metrics, the present framework with image-driven textural features had to rely on standard and validated data such as UPDRS and best available date of first symptom/diagnosis.…”

Section: Discussionmentioning

confidence: 99%

Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments

Rahmim

Salimpour

Jain

et al. 2016

NeuroImage: Clinical

View full text Add to dashboard Cite

Dopamine transporter (DAT) SPECT imaging is increasingly utilized for diagnostic purposes in suspected Parkinsonian syndromes. We performed a cross-sectional study to investigate whether assessment of texture in DAT SPECT radiotracer uptake enables enhanced correlations with severity of motor and cognitive symptoms in Parkinson's disease (PD), with the long-term goal of enabling clinical utility of DAT SPECT imaging, beyond standard diagnostic tasks, to tracking of progression in PD. Quantitative analysis in routine DAT SPECT imaging, if performed at all, has been restricted to assessment of mean regional uptake. We applied a framework wherein textural features were extracted from the images. Notably, the framework did not require registration to a common template, and worked in the subject-native space. Image analysis included registration of SPECT images onto corresponding MRI images, automatic region-of-interest (ROI) extraction on the MRI images, followed by computation of Haralick texture features. We analyzed 141 subjects from the Parkinson's Progressive Marker Initiative (PPMI) database, including 85 PD and 56 healthy controls (HC) (baseline scans with accompanying 3 T MRI images). We performed univariate and multivariate regression analyses between the quantitative metrics and different clinical measures, namely (i) the UPDRS (part III - motor) score, disease duration as measured from (ii) time of diagnosis (DD-diag.) and (iii) time of appearance of symptoms (DD-sympt.), as well as (iv) the Montreal Cognitive Assessment (MoCA) score. For conventional mean uptake analysis in the putamen, we showed significant correlations with clinical measures only when both HC and PD were included (Pearson correlation r = − 0.74, p-value < 0.001). However, this was not significant when applied to PD subjects only (r = − 0.19, p-value = 0.084), and no such correlations were observed in the caudate. By contrast, for the PD subjects, significant correlations were observed in the caudate when including texture metrics, with (i) UPDRS (p-values < 0.01), (ii) DD-diag. (p-values < 0.001), (iii) DD-sympt (p-values < 0.05), and (iv) MoCA (p-values < 0.01), while no correlations were observed for conventional analysis (p-values = 0.94, 0.34, 0.88 and 0.96, respectively). Our results demonstrated the ability to capture valuable information using advanced texture metrics from striatal DAT SPECT, enabling significant correlations of striatal DAT binding with clinical, motor and cognitive outcomes, and suggesting that textural features hold potential as biomarkers of PD severity and progression.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments

Rahmim

Salimpour

Jain

et al. 2016

NeuroImage: Clinical

View full text Add to dashboard Cite

show abstract

“…In AD, classification accuracy in large-scale studies (for example, n > 500) converges on ~90%, but in other areas, such as autism and ADHD, large-scale studies show substantially lower accuracy. Though there are some exceptional large-scale studies with very high accuracy 39,69–71 , none of these models have been prospectively tested on independent data and thus await independent validation.…”

Section: A Critical Evaluation Of Clinical Predictive Modelingmentioning

confidence: 99%

Building better biomarkers: brain models in translational neuroimaging

et al. 2017

View full text Add to dashboard Cite

Despite its great promise, neuroimaging has yet to substantially impact clinical practice and public health. However, a developing synergy between emerging analysis techniques and data-sharing initiatives has the potential to transform the role of neuroimaging in clinical applications. We review the state of translational neuroimaging and outline an approach to developing brain signatures that can be shared, tested in multiple contexts and applied in clinical settings. The approach rests on three pillars: (i) the use of multivariate pattern-recognition techniques to develop brain signatures for clinical outcomes and relevant mental processes; (ii) assessment and optimization of their diagnostic value; and (iii) a program of broad exploration followed by increasingly rigorous assessment of generalizability across samples, research contexts and populations. Increasingly sophisticated models based on these principles will help to overcome some of the obstacles on the road from basic neuroscience to better health and will ultimately serve both basic and applied goals.

show abstract

“…Recent advances in the areas of machine learning and data-driven analysis have demonstrated the utility of different brain imaging modalities for automated diagnosis of PD. These studies have utilized a host of techniques that include supervised predictive models such as support vector machines (SVMs) (Abos et al, 2017;Amoroso, La Rocca, Monaco, Bellotti, & Tangaro, 2018;Cherubini, Morelli, et al, 2014;Cherubini, Nistico, et al, 2014;Huppertz et al, 2016;Rana et al, 2015;Salvatore et al, 2014) as well as unsupervised models such as self-organizing maps (Peran et al, 2018;Singh & Samavedham, 2015) on data acquired from morphological T1 weighted MRI, functional MRI, diffusion tensor imaging, SPECT, etc. (Adeli et al, 2016;Ariz et al, 2018) and have reported high but variable accuracies.…”

Section: Introductionmentioning

confidence: 99%

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

Shinde

Prasad

Saboo

et al. 2019

Preprint

View full text Add to dashboard Cite

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). PD is characterized by loss of dopaminergic neurons in SNc and 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 based on convolutional neural networks (CNNs) to create prognostic and diagnostic biomarkers of PD from NMS-MRI. The technique not only performs with a superior cross-validation accuracy (83.7%) as well as testing accuracy (80%) as compared to contrast ratio-based classification (52.7% cross-validation and 56.5% testing accuracy) and radiomics based classifier (81.1% cross-validation and 60.3% testing accuracy); but also locates 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.

show abstract

Unsupervised learning based feature extraction for differential diagnosis of neurodegenerative diseases: A case study on early-stage diagnosis of Parkinson disease

Cited by 65 publications

References 45 publications

Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments

Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments

Building better biomarkers: brain models in translational neuroimaging

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

Contact Info

Product

Resources

About