High-content phenotyping of Parkinson's disease patient stem cell-derived midbrain dopaminergic neurons using machine learning classification.

Combining multiple Parkinson's disease (PD) relevant cellular phenotypes might increase the accuracy of midbrain dopaminergic neuron (mDAN) in vitro models. We differentiated patient-derived induced pluripotent stem cells (iPSCs) with a LRRK2 G2019S mutation, isogenic control, and genetically unrelated iPSCs into mDANs. Using automated fluorescence microscopy in 384-well-plate format, we identified elevated levels of α-synuclein (αSyn) and serine 129 phosphorylation, reduced dendritic complexity, and mitochondrial dysfunction. Next, we measured additional image-based phenotypes and used machine learning (ML) to accurately classify mDANs according to their genotype. Additionally, we show that chemical compound treatments, targeting LRRK2 kinase activity or αSyn levels, are detectable when using ML classification based on multiple image-based phenotypes. We validated our approach using a second isogenic patient-derived SNCA gene triplication mDAN model which overexpresses αSyn. This phenotyping and classification strategy improves the practical exploitability of mDANs for disease modeling and the identification of novel LRRK2-associated drug targets.

3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network.

We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.