Update on neuroimaging for categorization of Parkinson's disease and atypical parkinsonism

MRI classification of progressive supranuclear palsy, Parkinson disease and controls using deep learning and machine learning algorithms for the identification of regions and tracts of interest as potential biomarkers

BACKGROUND

Quantitative magnetic resonance imaging (MRI) analysis has shown promise in differentiating neurodegenerative Parkinsonian syndromes and has significantly advanced our understanding of diseases like progressive supranuclear palsy (PSP) in recent years.

OBJECTIVE

The aim of this study was to develop, implement and compare MRI analysis algorithms based on artificial intelligence (AI) that can differentiate PSP not only from healthy controls but also from Parkinson disease (PD), by analyzing changes in brain structure and microstructure. Specifically, this study focused on identifying regions of interest (ROIs) and tracts of interest (TOIs) that are crucial for the algorithms to provide clinically relevant performance indices for the distinction between disease variants.

METHODS

MR data comprised diffusion tensor imaging (DTI - tractwise fractional anisotropy statistics (TFAS)) and T1-weighted (T1-w) data (texture analysis of the corpus callosum (CC)). One subject sample with 74 PSP patients and 63 controls was recorded at 3.0T at multiple sites. The other sample came from a single site, consisting of 66 PSP patients, 66 PD patients, and 44 controls, recorded at 1.5T. Four different machine learning algorithms (ML) and a deep learning (DL) neural network approach using Tensor Flow were implemented for the study. The training of the algorithms was performed on 80 % of the data, which included the entire single-site data and parts of the multiple-site data. The validation process was conducted on the remaining data, thereby consistently separating training and validation data.

RESULTS

A random forest algorithm and a DL neural network classified PSP and healthy controls with accuracies of 92 % and 95 %, respectively. Particularly, DTI derived measures for the pons, midbrain tegmentum, superior cerebral peduncle, putamen, and CC contributed to high accuracies. Furthermore, DL neural network classification of PSP and PD with 86 % accuracy showed the importance of 19 structures. The four most important features were DTI derived measures for prefrontal white matter, the fasciculus frontooccipitalis, the midbrain tegmentum, and the CC area II. This DL network achieved a sensitivity of 88 % and specificity of 85 %, resulting in a Youden-index of 0.72.

CONCLUSION

The primary goal of the present study was to compare multiple ML-methods and a DL approach to identify the least necessary set of brain structures to classify PSP vs. controls and PSP vs. PD by ranking them in a hierarchical order of importance. That way, this study demonstrated the potential of AI approaches to MRI as possible diagnostic and scientific tools to differentiate variants of neurodegenerative Parkinsonism.

Multiple system atrophy: advances in pathophysiology, diagnosis, and treatment

Multiple system atrophy is an adult-onset, sporadic, and progressive neurodegenerative disease. People with this disorder report a wide range of motor and non-motor symptoms. Overlap in the clinical presentation of multiple system atrophy with other movement disorders (eg, Parkinson's disease and progressive supranuclear palsy) is a concern for accurate and timely diagnosis. Over the past 5 years, progress has been made in understanding key pathophysiological events in multiple system atrophy, including the seeding of α-synuclein inclusions and the detection of disease-specific α-synuclein strains. Diagnostic criteria were revised in 2022 with the intention to improve the accuracy of a diagnosis of multiple system atrophy, particularly for early disease stages. Early signals of efficacy in clinical trials have indicated the potential for disease-modifying therapies for multiple system atrophy, although no trial has yet provided unequivocal evidence of neuroprotection in this rare disease. The advances in pathophysiology could play a part in biomarker discovery for early diagnosis as well as in the development of disease-modifying therapies.

Simple biomarkers to distinguish Parkinson's disease from its mimics in clinical practice: a comprehensive review and future directions

In the last few years, a plethora of biomarkers have been proposed for the differentiation of Parkinson's disease (PD) from its mimics. Most of them consist of complex measures, often based on expensive technology, not easily employed outside research centers. MRI measures have been widely used to differentiate between PD and other parkinsonism. However, these measurements were often performed manually on small brain areas in small patient cohorts with intra- and inter-rater variability. The aim of the current review is to provide a comprehensive and updated overview of the literature on biomarkers commonly used to differentiate PD from its mimics (including parkinsonism and tremor syndromes), focusing on parameters derived by simple qualitative or quantitative measurements that can be used in routine practice. Several electrophysiological, sonographic and MRI biomarkers have shown promising results, including the blink-reflex recovery cycle, tremor analysis, sonographic or MRI assessment of substantia nigra, and several qualitative MRI signs or simple linear measures to be directly performed on MR images. The most significant issue is that most studies have been conducted on small patient cohorts from a single center, with limited reproducibility of the findings. Future studies should be carried out on larger international cohorts of patients to ensure generalizability. Moreover, research on simple biomarkers should seek measurements to differentiate patients with different diseases but similar clinical phenotypes, distinguish subtypes of the same disease, assess disease progression, and correlate biomarkers with pathological data. An even more important goal would be to predict the disease in the preclinical phase.

Contribution of MRI for the Early Diagnosis of Parkinsonism in Patients with Diagnostic Uncertainty

BACKGROUND

International clinical criteria are the reference for the diagnosis of degenerative parkinsonism in clinical research, but they may lack sensitivity and specificity in the early stages.

OBJECTIVES

To determine whether magnetic resonance imaging (MRI) analysis, through visual reading or machine-learning approaches, improves diagnostic accuracy compared with clinical diagnosis at an early stage in patients referred for suspected degenerative parkinsonism.

MATERIALS

Patients with initial diagnostic uncertainty between Parkinson's disease (PD), progressive supranuclear palsy (PSP), and multisystem atrophy (MSA), with brain MRI performed at the initial visit (V1) and available 2-year follow-up (V2), were included. We evaluated the accuracy of the diagnosis established based on: (1) the international clinical diagnostic criteria for PD, PSP, and MSA at V1 ("Clin1"); (2) MRI visual reading blinded to the clinical diagnosis ("MRI"); (3) both MRI visual reading and clinical criteria at V1 ("MRI and Clin1"), and (4) a machine-learning algorithm ("Algorithm"). The gold standard diagnosis was established by expert consensus after a 2-year follow-up.

RESULTS

We recruited 113 patients (53 with PD, 31 with PSP, and 29 with MSA). Considering the whole population, compared with clinical criteria at the initial visit ("Clin1": balanced accuracy, 66.2%), MRI visual reading showed a diagnostic gain of 14.3% ("MRI": 80.5%; P = 0.01), increasing to 19.2% when combined with the clinical diagnosis at the initial visit ("MRI and Clin1": 85.4%; P < 0.0001). The algorithm achieved a diagnostic gain of 9.9% ("Algorithm": 76.1%; P = 0.08).

CONCLUSION

Our study shows the use of MRI analysis, whether by visual reading or machine-learning methods, for early differentiation of parkinsonism. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Quantitative MRI protocol and decision model for a 'one stop shop' early-stage Parkinsonism diagnosis: Study design

Differentiating among early-stage parkinsonisms is a challenge in clinical practice. Quantitative MRI can aid the diagnostic process, but studies with singular MRI techniques have had limited success thus far. Our objective is to develop a multi-modal MRI method for this purpose. In this review we describe existing methods and present a dedicated quantitative MRI protocol, a decision model and a study design to validate our approach ahead of a pilot study. We present example imaging data from patients and a healthy control, which resemble related literature.

Comparison of mean diffusivity, R2* relaxation rate and morphometric biomarkers for the clinical differentiation of parkinsonism

INTRODUCTION

Quantitative biomarkers for clinical differentiation of parkinsonian syndromes are still lacking. Our aim was to evaluate the value of combining clinically feasible manual measurements of R2* relaxation rates and mean diffusivity (MD) in subcortical regions and brainstem morphometric measurements to improve the discrimination of parkinsonian syndromes.

METHODS

Twenty-two healthy controls (HC), 25 patients with Parkinson's disease (PD), 19 with progressive supranuclear palsy (PSP) and 27 with multiple system atrophy (MSA, 21 with the parkinsonian variant -MSAp, 6 with the cerebellar variant -MSAc) were recruited. R2*, MD measurements and morphometric biomarkers including the midbrain to pons area ratio and the Magnetic Resonance Parkinsonism Index (MRPI) were compared between groups and their diagnostic performances were assessed.

RESULTS

Morphometric biomarkers discriminated better patients with PSP (ratio: AUC 0.89, MRPI: AUC 0.89) and MSAc (ratio: AUC 0.82, MRPI: AUC 0.75) from other groups. R2* and MD measurements in the posterior putamen performed better in separating patients with MSAp from PD (R2*: AUC 0.89; MD: AUC 0.89). For the three-class classification "MSA vs PD vs PSP", the combination of MD and R2* measurements in the posterior putamen with morphometric biomarkers (AUC: 0.841) outperformed each marker separately. At the individual-level, there were seven discordances between imaging-based prediction and clinical diagnosis involving MSA. Using the new Movement Disorder Society criteria for the diagnosis of MSA, three of these seven patients were clinically reclassified as predicted by quantitative imaging.

CONCLUSION

Combining R2* and MD measurements in the posterior putamen with morphometric biomarkers improves the discrimination of parkinsonism.

The "Hot Cross Bun Sign" in Spinocerebellar Ataxia Types 2 and 7-Case Reports and Review of Literature

Background

The "hot cross bun" sign is a cruciform hyperintensity is seen on T2 weighted imaging within the pons. The sign is considered to be pathognomic for Multiple system atrophy type C. The clinical and radiological features of Multiple system atrophy type C overlap with the autosomal dominant inherited ataxias. We present a case series of 3 African patients with genetically proven Spinocerebellar Ataxia presenting with the Hot cross bun sign and a scoping review of similar studies.

Cases

We described the phenotypic and radiological presentation of genetically confirmed SCA-2 in two, and SCA-7 in one patient, with the "hot cross bun" sign.

Literature Review

We performed a scoping review on the Hot Cross Bun Sign.A total of 66 articles were retrieved. We describe the diverse aetiologies of the sign and associated phenotypic and radiological features. We review the Spinocerebellar Ataxias described with a Hot cross bun sign and make comparisons to Multiple System Atrophy Type C [Ref. 1,2].

Conclusions

To our knowledge this is the first description of an African cohort presenting with the Hot Cross Bun Sign. We expand the differential diagnosis of the Hot Cross Bun Sign.

Multiple system atrophy

Multiple system atrophy (MSA) is a rare neurodegenerative disease that is characterized by neuronal loss and gliosis in multiple areas of the central nervous system including striatonigral, olivopontocerebellar and central autonomic structures. Oligodendroglial cytoplasmic inclusions containing misfolded and aggregated α-synuclein are the histopathological hallmark of MSA. A firm clinical diagnosis requires the presence of autonomic dysfunction in combination with parkinsonism that responds poorly to levodopa and/or cerebellar ataxia. Clinical diagnostic accuracy is suboptimal in early disease because of phenotypic overlaps with Parkinson disease or other types of degenerative parkinsonism as well as with other cerebellar disorders. The symptomatic management of MSA requires a complex multimodal approach to compensate for autonomic failure, alleviate parkinsonism and cerebellar ataxia and associated disabilities. None of the available treatments significantly slows the aggressive course of MSA. Despite several failed trials in the past, a robust pipeline of putative disease-modifying agents, along with progress towards early diagnosis and the development of sensitive diagnostic and progression biomarkers for MSA, offer new hope for patients.

Tau-PET and multimodal imaging in clinically atypical multiple system atrophy masquerading as progressive supranuclear palsy

INTRODUCTION

Multiple system atrophy (MSA) typically presents with parkinsonism, ataxia and/or autonomic dysfunction. Occasionally, clinically atypical (ca-MSA) cases masquerade as progressive supranuclear palsy (PSP). We aimed to investigate whether different neuroimaging modalities could facilitate differentiation and whether histopathologic characteristics could explain the atypical presentation.

METHODS

We identified 3 neuropathologically-defined ca-MSA patients with clinically diagnosed PSP who underwent various antemortem brain imaging: MRI and PET imaging using ¹¹C-Pittsburgh compound B, ¹⁸F-flortaucipir, and ¹⁸F-fluorodeoxyglucose. We compared clinical features, brainstem planimetry, and radiotracer standardized uptake value ratios in ca-MSA to 10 autopsy-confirmed PSP patients and 10 healthy controls (imaging only). We also compared histologic count of neuronal loss, iron deposition and α-synuclein-immunoreactive glial cytoplasmic inclusion burden to 10 autopsy-confirmed MSA-parkinsonism (MSA-P) cases.

RESULTS

Ca-MSA had better PSP Saccadic Impairment Scale scores (p = 0.003) and more frequent good levodopa response (p = 0.061) than PSP. Ca-MSA showed higher midbrain-to-pons ratio and lower Magnetic Resonance Parkinsonism Index than PSP (each, p = 0.036) and exhibited lower glucose metabolism in the putamen and globus pallidus versus PSP (p = 0.017) and controls (p = 0.007). These same regions showed higher flortaucipir uptake in ca-MSA than PSP (p = 0.007 for putamen, p = 0.049 for pallidum) and controls (p = 0.012). Lower flortaucipir retention was observed in the subthalamic nucleus versus PSP (p = 0.007). The putamen-to-subthalamic ratio distinguished ca-MSA from PSP. No histopathological differences were observed for ca-MSA versus typical MSA-P.

CONCLUSION

Severity of saccadic impairment, levodopa responsiveness, MRI planimetric measurements, and different patterns of fluorodeoxyglucose and flortaucipir uptake can help improve antemortem differentiation of MSA masquerading as PSP from true PSP.

An MRI-Based Clinical-Perfusion Model Predicts Pathological Subtypes of Prevascular Mediastinal Tumors

This study aimed to build machine learning prediction models for predicting pathological subtypes of prevascular mediastinal tumors (PMTs). The candidate predictors were clinical variables and dynamic contrast–enhanced MRI (DCE-MRI)–derived perfusion parameters. The clinical data and preoperative DCE–MRI images of 62 PMT patients, including 17 patients with lymphoma, 31 with thymoma, and 14 with thymic carcinoma, were retrospectively analyzed. Six perfusion parameters were calculated as candidate predictors. Univariate receiver-operating-characteristic curve analysis was performed to evaluate the performance of the prediction models. A predictive model was built based on multi-class classification, which detected lymphoma, thymoma, and thymic carcinoma with sensitivity of 52.9%, 74.2%, and 92.8%, respectively. In addition, two predictive models were built based on binary classification for distinguishing Hodgkin from non-Hodgkin lymphoma and for distinguishing invasive from noninvasive thymoma, with sensitivity of 75% and 71.4%, respectively. In addition to two perfusion parameters (efflux rate constant from tissue extravascular extracellular space into the blood plasma, and extravascular extracellular space volume per unit volume of tissue), age and tumor volume were also essential parameters for predicting PMT subtypes. In conclusion, our machine learning–based predictive model, constructed with clinical data and perfusion parameters, may represent a useful tool for differential diagnosis of PMT subtypes.