FDG-PET combined with learning vector quantization allows classification of neurodegenerative diseases and reveals the trajectory of idiopathic REM sleep behavior disorder

• Published in: Computer methods and programs in biomedicine Vol. 225; p. 107042
• Main Authors: van Veen, Rick, Meles, Sanne K., Renken, Remco J., Reesink, Fransje E., Oertel, Wolfgang H., Janzen, Annette, de Vries, Gert-Jan, Leenders, Klaus L., Biehl, Michael
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2022
• Subjects: FDG-PET; Idiopathic REM sleep behavior disorder trajectories; Learning vector quantization; Neurodegenerative diseases; Relevance learning; SSM/PCA; FDG-PET; Idiopathic REM sleep behavior disorder trajectories; Relevance learning; Neurodegenerative diseases; Learning vector quantization; SSM/PCA
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2022.107042

•Differential diagnosis of Parkinson’s disease, Alzheimer’s disease, and dementia with Lewy bodies based on FDG-PET data.•Longitudinal REM sleep behavior disorder conversion trajectory analysis.•Explainable and actionable learning vector quantization and relevance learning in neuroradiology.•Visualizing diagnoses of neurodegenerative diseases in a low-dimensional discriminant space.•Visualizing prototypical activity profiles and relevance maps for the classification of neurodegenerative diseases. 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) combined with principal component analysis (PCA) has been applied to identify disease-related brain patterns in neurodegenerative disorders such as Parkinson’s disease (PD), Dementia with Lewy Bodies (DLB) and Alzheimer’s disease (AD). These patterns are used to quantify functional brain changes at the single subject level. This is especially relevant in determining disease progression in idiopathic REM sleep behavior disorder (iRBD), a prodromal stage of PD and DLB. However, the PCA method is limited in discriminating between neurodegenerative conditions. More advanced machine learning algorithms may provide a solution. In this study, we apply Generalized Matrix Learning Vector Quantization (GMLVQ) to FDG-PET scans of healthy controls, and patients with AD, PD and DLB. Scans of iRBD patients, scanned twice with an approximate 4 year interval, were projected into GMLVQ space to visualize their trajectory. We applied a combination of SSM/PCA and GMLVQ as a classifier on FDG-PET data of healthy controls, AD, DLB, and PD patients. We determined the diagnostic performance by performing a ten times repeated ten fold cross validation. We analyzed the validity of the classification system by inspecting the GMLVQ space. First by the projection of the patients into this space. Second by representing the axis, that span this decision space, into a voxel map. Furthermore, we projected a cohort of RBD patients, whom have been scanned twice (approximately 4 years apart), into the same decision space and visualized their trajectories. The GMLVQ prototypes, relevance diagonal, and decision space voxel maps showed metabolic patterns that agree with previously identified disease-related brain patterns. The GMLVQ decision space showed a plausible quantification of FDG-PET data. Distance traveled by iRBD subjects through GMLVQ space per year (i.e. velocity) was correlated with the change in motor symptoms per year (Spearman’s rho =0.62, P=0.004). In this proof-of-concept study, we show that GMLVQ provides a classification of patients with neurodegenerative disorders, and may be useful in future studies investigating speed of progression in prodromal disease stages.