Prion disease diagnosis using subject-specific imaging biomarkers within a multi-kernel Gaussian process.

Liane S Canas,Harpreet Hyare,Frederik Barkhof,Enrico De Vita,John Collinge,Tze How Mok,Sébastien Ourselin,Marc Modat,Catherine F Slattery,Ross W Paterson,Carole H Sudre,Jonathan M Schott,Akin Nihat,Alexander J.M Foulkes,Simon Mead,M Jorge Cardoso,John Thornton

doi:10.1016/j.nicl.2019.102051

Abstract

Prion diseases are a group of rare neurodegenerative conditions characterised by a high rate of progression and highly heterogeneous phenotypes. Whilst the most common form of prion disease occurs sporadically (sporadic Creutzfeldt-Jakob disease, sCJD), other forms are caused by prion protein gene mutations, or exposure to prions in the diet or by medical procedures, such us surgeries. To date, there are no accurate quantitative imaging biomarkers that can be used to predict the future clinical diagnosis of a healthy subject, or to quantify the progression of symptoms over time. Besides, CJD is commonly mistaken for other forms of dementia. Due to the heterogeneity of phenotypes and the lack of a consistent geometrical pattern of disease progression, the approaches used to study other types of neurodegenerative diseases are not satisfactory to capture the progression of human form of prion disease. In this paper, using a tailored framework, we aim to classify and stratify patients with prion disease, according to the severity of their illness. The framework is initialised with the extraction of subject-specific imaging biomarkers. The extracted biomakers are then combined with genetic and demographic information within a Gaussian Process classifier, used to calculate the probability of a subject to be diagnosed with prion disease in the next year. We evaluate the effectiveness of the proposed method in a cohort of patients with inherited and sporadic forms of prion disease. The model has shown to be effective in the prediction of both inherited CJD (92% of accuracy) and sporadic CJD (95% of accuracy). However the model has shown to be less effective when used to stratify the different stages of the disease, in which the average accuracy is 85%, whilst the recall is 59%. Finally, our framework was extended as a differential diagnosis tool to identify both forms of CJD among another neurodegenerative disease. In summary we have developed a novel method for prion disease diagnosis and prediction of clinical onset using multiple sources of features, which may have use in other disorders with heterogeneous imaging features.

Highlights

Prion diseases, known as transmissible spongiform encephalopathies (TSEs), are a group of progressive neurodegenerative conditions, which cause cognitive impairment and neurological deficits (Collinge, 2001)
Over thirty different mutations in prion protein gene (PRNP) have been found in patients presenting inherited prion diseases (IPD), with about 95% of familial cases caused by four mutations and insertions of five or six octapeptide repeats (Johnson, 2005)
Despite the promise of quantitative biomarkers, clinical diagnosis still relies only in the qualitative evaluation of MRI scans. To address this limitation we proposed a framework that aims to (i) extract quantitative imaging biomarkers from magnetic resonance (MR) images, (ii) show that those are fit for the diagnosis of CJD in its earlier stages, and (iii) diagnose and stratify the subjects according to severity stages of symptoms design based on a widely used clinical severity measure, the MRC Prion Disease Rating Scale Thompson et al (2013a)

Summary

Introduction

Known as transmissible spongiform encephalopathies (TSEs), are a group of progressive neurodegenerative conditions, which cause cognitive impairment and neurological deficits (Collinge, 2001). The sporadic form (sCJD) is the most common and it accounts for about 85% of the annual incidence of human prion disease. This form of CJD shows a significant neuronal loss, and vacuolisation within cell bodies and dendrites that gives a spongiform appearance to the cerebral cortex and deep nuclei (Johnson, 2005). The inherited prion diseases (IPD) are caused by autosomal dominant inheritance of mutations in the PRNP gene, which in total are responsible for 10–15% of the incidence of human prion disease (Mead, 2006). The clinical course of IPD can be much longer than sCJD, up to 20 years (Mead, 2006). Due to these long clinical durations, IPD has a similar prevalence in the population than sCJD, despite a much lower incidence

Objectives

Methods

Results