Klaus L. Leenders

Purpose: Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias. Methods: We demonstrate the use of the recently proposed machine learning method Iterated Relevance Matrix Analysis (IRMA) for harmonization of center-specific effects in brain ¹⁸F-Fluorodeoxyglucose (¹⁸F-FDG) PET scans. The center difference is learned by applying IRMA on PCA-based feature vectors of healthy controls (HC), resulting in a subspace V, representing information not comparable between centers, and the remaining subspace U, where no center differences are present. In this proof-of-concept study, we demonstrate the properties of the method using data from four centers. After center-harmonization, a Generalized Matrix Learning Vector Quantization (GMLVQ) model was trained to discriminate between Parkinson’s disease, Alzheimer’s disease and Dementia with Lewy Bodies. Results: At the initial IRMA iteration, the system was able to determine the center origin of the four HC cohorts almost perfectly. The method required six iterations, corresponding to a six-dimensional subspace V, to determine the entire center difference. An uncorrected disease classification model was highly biased to center-specific effects, creating a falsely inflated performance when applying internal (cross-) validation. The cross-validation performance of the center-harmonized model remained high, while it generalized significantly better to unseen test cohorts. Furthermore, the framework is highly transparent, providing analytic reconstructions of the correction and visualizations of the data in voxel space. Conclusion: IRMA can be used to learn and disregard center-specific information in features extracted from brain ¹⁸F-FDG PET scans, while retaining disease-specific information.

We investigated different degrees of muscle co-activity in simple hand movement at behavioral and cerebral level in healthy subjects and Parkinson’s disease (PD) patients. We compared ‘singular’ movements, dominated by the activity of one agonist muscle, to ‘composite’ movements, requiring conjoint activity of multiple muscles, in a center-out (right hand) step-tracking task. Behavioral parameters were obtained by EMG and kinematic recordings. FMRI was used to investigate differences in underlying brain activ¬¬ations between PD patients (N= 12) and healthy (age-matched) subjects (N= 18). In healthy subjects, composite movements recruited the striatum and cortical areas comprising bilaterally the supplementary motor area and premotor cortex, contralateral medial prefrontal cortex, primary motor cortex, primary visual cortex, and ipsilateral superior parietal cortex. Contrarily, the ipsilateral cerebellum was more involved in singular movements. This striking dichotomy between striatal and cortical recruitment versus cerebellar involvement may reflect the complementary roles of these areas in motor control, in which the basal ganglia are involved in movement selection and the cerebellum in movement optimization. Compared to healthy subjects, PD patients showed decreased activation of the striatum and cortical areas in composite movement, while performing worse at behavioral level. This implies that PD patients are especially impaired on tasks requiring highly tuned muscle co-activity. Singular movement, on the other hand, was characterized by a combination of increased activation of the ipsilateral parietal cortex and left cerebellum. As singular movement performance was only slightly compromised, we interpret this as a reflection of increased visuospatial processing, possibly as a compensational mechanism.