Possibilities and limitations of convolutional neural network machine learning architectures in the characterisation of achiral orthogonal smectic liquid crystals.

Machine learning is becoming a valuable tool in the characterisation and property prediction of liquid crystals. It is thus worthwhile to be aware of the possibilities but also the limitations of current machine learning algorithms. In this study we investigated a phase sequence of isotropic - fluid smecticA - hexatic smectic B - soft crystal CrE - crystalline. This is a sequence of transitions between orthogonal phases, which are expected to be difficult to distinguish, because of only minute changes in order. As expected, strong first order transitions such as the liquid to liquid crystal transition and the crystallisation can be distinguished with high accuracy. It is shown that also the hexatic SmB to soft crystal CrE transition is clearly characterised, which represents the transition from short- to long-range order. Limitations of convolutional neural networks can be observed for the fluid to hexatic SmA to SmB transition, where both phases exhibit short-range ordering.

Novel application of in vivo microdialysis in a rat Achilles tendon acute injury model.

Tendon injury and healing involve intricate changes to tissue metabolism, biology, and inflammation. Current techniques often require animal euthanasia or tissue destruction, limiting assessment of dynamic changes in tendon, including treatment response, disease development, rupture risk, and healing progression. Microdialysis, a minimally invasive technique, offers potential for longitudinal assessment, yet it has not been applied to rat tendon models. Therefore, the objective of this study is to adapt a novel application of an in vivo assay, microdialysis, using acute injury as a model for extreme disruption of the tendon homeostasis. We hypothesize that microdialysis will be able to detect measurable differences in the healing responses of acute injury with high specificity and sensitivity. Overall results suggest that microdialysis is a promising in vivo technique for longitudinal assessment for this system with strong correlations between extracellular fluid (ECF) and dialysate concentrations and reasonable recovery rates considering the limitations of this model. Strong positive correlations were found between dialysate and extracellular fluid (ECF) concentration for each target molecule of interest including metabolites, inflammatory mediators, and collagen synthesis and degradation byproducts. These results suggest that microdialysis is capable of detecting changes in tendon healing following acute tendon injury with high specificity and sensitivity. In summary, this is the first study to apply microdialysis to a rat tendon model and assess its efficacy as a direct measurement of tendon metabolism, biology, and inflammation.NEW & NOTEWORTHY This study adapts a novel application of microdialysis to rat tendon models, offering a minimally invasive avenue for longitudinal tendon assessment. Successfully detecting changes in tendon healing after acute injury, it showcases strong correlations between extracellular fluid and dialysate concentrations. The results highlight the potential of microdialysis as a direct measure of tendon metabolism, biology, and inflammation, bypassing the need for animal euthanasia and tissue destruction.

Cerebellar Volume and Disease Staging in Parkinson's Disease: An ENIGMA-PD Study.

BACKGROUND: Increasing evidence points to a pathophysiological role for the cerebellum in Parkinson's disease (PD). However, regional cerebellar changes associated with motor and non-motor functioning remain to be elucidated. OBJECTIVE: To quantify cross-sectional regional cerebellar lobule volumes using three dimensional T1-weighted anatomical brain magnetic resonance imaging from the global ENIGMA-PD working group. METHODS: Cerebellar parcellation was performed using a deep learning-based approach from 2487 people with PD and 1212 age and sex-matched controls across 22 sites. Linear mixed effects models compared total and regional cerebellar volume in people with PD at each Hoehn and Yahr (HY) disease stage, to an age- and sex- matched control group. Associations with motor symptom severity and Montreal Cognitive Assessment scores were investigated. RESULTS: Overall, people with PD had a regionally smaller posterior lobe (dmax = -0.15). HY stage-specific analyses revealed a larger anterior lobule V bilaterally (dmax = 0.28) in people with PD in HY stage 1 compared to controls. In contrast, smaller bilateral lobule VII volume in the posterior lobe was observed in HY stages 3, 4, and 5 (dmax = -0.76), which was incrementally lower with higher disease stage. Within PD, cognitively impaired individuals had lower total cerebellar volume compared to cognitively normal individuals (d = -0.17). CONCLUSIONS: We provide evidence of a dissociation between anterior "motor" lobe and posterior "non-motor" lobe cerebellar regions in PD. Whereas less severe stages of the disease are associated with larger motor lobe regions, more severe stages of the disease are marked by smaller non-motor regions. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Machine learning classification of polar sub-phases in liquid crystal MHPOBC.

Experimental polarising microscopy texture images of the fluid smectic phases and sub-phases of the classic liquid crystal MHPOBC were classified as paraelectric (SmA*), ferroelectric (SmC*), ferrielectric (SmC1/3*), and antiferroelectric (SmCA*) using convolutional neural networks, CNNs. Two neural network architectures were tested, a sequential convolutional neural network with varying numbers of layers and a simplified inception model with varying number of inception blocks. Both models are successful in binary classifications between different phases as well as classification between all four phases. Optimised architectures for the multi-phase classification achieved accuracies of (84 ± 2)% and (93 ± 1)% for sequential convolutional and inception networks, respectively. The results of this study contribute to the understanding of how CNNs may be used in classifying liquid crystal phases. Especially the inception model is of sufficient accuracy to allow automated characterization of liquid crystal phase sequences and thus opens a path towards an additional method to determine the phases of novel liquid crystals for applications in electro-optics, photonics or sensors. The outlined procedure of supervised machine learning can be applied to practically all liquid crystal phases and materials, provided the infrastructure of training data and computational power is provided.

Fluorescence Spectra Predict Microcystin-LR and Disinfection Byproduct Formation Potential in Lake Water.

Disinfection byproducts (DBPs) and algal toxins can be expensive to monitor and represent significant potential risks to human health. DBPs, including haloacetic acids and trihalomethanes, are possible or probable human carcinogens. Microcystin-LR-produced by cyanobacteria-is linked with various adverse health effects. Here we show that fluorescence spectra predict both microcystin-LR occurrence and DBP formation potential (DBPfp) in lake water. We compared models with either fluorescence spectra or a suite of water quality predictors as inputs. A regularized logistic regression model with fluorescence spectral inputs correctly classified 94% of test data with respect to microcystin-LR occurrence, with a 96% probability of correctly ranking a detect/nondetect pair. Regularized linear regression predicted DBPfp based on fluorescence inputs with a combined R2 of 0.83 on test data. A gradient-boosted classifier with seven water quality inputs was comparable in detecting microcystin-LR (91% correct), as was UV254 in predicting DBPfp (combined test R2 = 0.84), but no single parameter matched fluorescence spectra over both predictive tasks. Results highlight the potential for multiparameter monitoring via fluorescence spectroscopy, extending previous work on predicting DBPs alone. As a high-frequency monitoring tool, this approach could supplement mass spectrometric methods that may only be applicable at low frequency due to resource limitations.