Differential diagnosis of parkinsonism based on deep metabolic imaging indices

Abstract

The clinical presentations of early idiopathic Parkinson’s disease (PD) substantially overlap with those of atypical parkinsonian syndromes like multiple system atrophy (MSA) and progressive supranuclear palsy (PSP). This study aimed to develop metabolic imaging indices based on deep learning to support the differential diagnosis of these conditions. Methods: A benchmark Huashan parkinsonian PET imaging (HPPI, China) database including 1275 parkinsonian patients and 863 non-parkinsonian subjects with ¹⁸F-FDG PET images was established to support artificial intelligence development. A 3D deep convolutional neural network was developed to extract deep metabolic imaging (DMI) indices, which was blindly evaluated in an independent cohort with longitudinal follow-up from the HPPI, and an external German cohort of 90 parkinsonian patients with different imaging acquisition protocols. Results: The proposed DMI indices had less ambiguity space in the differential diagnosis. They achieved sensitivities of 98.1%, 88.5%, and 84.5%, and specificities of 90.0%, 99.2%, and 97.8% for the diagnosis of PD, MSA, and PSP in the blind test cohort. In the German cohort, They resulted in sensitivities of 94.1%, 82.4%, 82.1%, and specificities of 84.0%, 99.9%, 94.1% respectively. Employing the PET scans independently achieved comparable performance to the integration of demographic and clinical information into the DMI indices. Conclusion: The DMI indices developed on the HPPI database show potential to provide an early and accurate differential diagnosis for parkinsonism and is robust when dealing with discrepancies between populations and imaging acquisitions.