Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.

Differentially Private Graph Neural Networks for Whole-Graph Classification

Graph Neural Networks (GNNs) have established themselves as state-of-the-art for many machine learning applications such as the analysis of social and medical networks. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of graphs. In this work, we introduce a framework for differential private graph-level classification. Our method is applicable to graph deep learning on multi-graph datasets and relies on differentially private stochastic gradient descent (DP-SGD). We show results on a variety of datasets and evaluate the impact of different GNN architectures and training hyperparameters on model performance for differentially private graph classification, as well as the scalability of the method on a large medical dataset. Our experiments show that DP-SGD can be applied to graph classification tasks with reasonable utility losses. Furthermore, we apply explainability techniques to assess whether similar representations are learned in the private and non-private settings. Our results can also function as robust baselines for future work in this area.

Structural studies on the impurities of troglitazone

The impurity profile study of troglitazone has been carried out primarily by (liquid chromatography-mass spectrometry) LC-MS. Four process-related impurities have been detected by LC-MS and were confirmed by co-injection with authentic samples. Apart from the process-related impurities, two polar by-products were characterized by mass spectral data and comparison with reference samples, while one non-polar by-product and one degradation product have been isolated by means of preparative HPLC and characterized by 2D NMR and mass spectral study. Single-crystal X-ray diffraction studies have been carried out on the degradation product. The formation and characterization of these by-products and degradation product are discussed.

Troglitazone, an euglycemic antidiabetic drug

Troglitazone (or 5-{4-[(6-hydroxy-2,5,7,8-tetramethyl-chroman-2-yl) methoxy]benzyl}thiazolidine-2,4-dione, C24H27NO5S) is the first euglycemic drug. The molecules are held together in the lattice by intermolecular hydrogen bonds between the hydroxy O atom of the chroman moiety, and the ketone O and ring N atom of the thiazolidine-2,4-dione moiety.

Synthesis and biological activity of novel thiazolidinediones

Novel compounds having a dual pharmacophore were synthesised and evaluated for their insulin sensitiser and anti-inflammatory properties in different animal models.