Atlas-ISTN: Joint segmentation, registration and atlas construction with image-and-spatial transformer networks.

Deep learning models for semantic segmentation are able to learn powerful representations for pixel-wise predictions, but are sensitive to noise at test time and may lead to implausible topologies. Image registration models on the other hand are able to warp known topologies to target images as a means of segmentation, but typically require large amounts of training data, and have not widely been benchmarked against pixel-wise segmentation models. We propose the Atlas Image-and-Spatial Transformer Network (Atlas-ISTN), a framework that jointly learns segmentation and registration on 2D and 3D image data, and constructs a population-derived atlas in the process. Atlas-ISTN learns to segment multiple structures of interest and to register the constructed atlas labelmap to an intermediate pixel-wise segmentation. Additionally, Atlas-ISTN allows for test time refinement of the model's parameters to optimize the alignment of the atlas labelmap to an intermediate pixel-wise segmentation. This process both mitigates for noise in the target image that can result in spurious pixel-wise predictions, as well as improves upon the one-pass prediction of the model. Benefits of the Atlas-ISTN framework are demonstrated qualitatively and quantitatively on 2D synthetic data and 3D cardiac computed tomography and brain magnetic resonance image data, out-performing both segmentation and registration baseline models. Atlas-ISTN also provides inter-subject correspondence of the structures of interest.

MOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images.

Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.

Copper(ii) complexes of N-propargyl cyclam ligands reveal a range of coordination modes and colours, and unexpected reactivity.

The coordination chemistry of N-functionalised cyclam ligands has a rich history, yet cyclam derivatives with pendant alkynes are largely unexplored. This is despite the significant potential and burgeoning application of N-propargyl cyclams and related compounds in the creation of diversely functionalised cyclam derivatives via copper-catalysed azide-alkyne 'click' reactions. Herein we describe single crystal X-ray diffraction and spectroscopic investigations of the coordination chemistry of copper(ii) complexes of cyclam derivatives with between 1 and 4 pendant alkynes. The crystal structures of these copper complexes unexpectedly reveal a range of coordination modes, and the surprising occurrence of five unique complexes within a single recrystallisation of the tetra-N-propargyl cyclam ligand. One of these species exhibits weak intramolecular copper-alkyne coordination, and another is formed by a surprising intramolecular copper-mediated hydroalkoxylation reaction with the solvent methanol, transforming one of the pendant alkynes to an enol ether. Multiple functionalisation of the tetra-N-propargyl ligand is demonstrated via a 'tetra-click' reaction with benzyl azide, and the copper-binding behaviour of the resulting tetra-triazole ligand is characterised spectroscopically.

Antitubercular Bis-Substituted Cyclam Derivatives: Structure-Activity Relationships and in Vivo Studies.

We recently reported the discovery of nontoxic cyclam-derived compounds that are active against drug-resistant Mycobacterium tuberculosis. In this paper we report exploration of the structure-activity relationship for this class of compounds, identifying several simpler compounds with comparable activity. The most promising compound identified, possessing significantly improved water solubility, displayed high levels of bacterial clearance in an in vivo zebrafish embryo model, suggesting this compound series has promise for in vivo treatment of tuberculosis.