Analysis of cell shape and movement from 3D time-lapsed datasets is currently very challenging. We therefore designed Cell Tracking Profiler for analysing cell behaviour from complex datasets and demonstrate its effectiveness by analysing stem cell behaviour during muscle regeneration in zebrafish. AbstractAccurate measurements of cell morphology and behaviour are fundamentally important for understanding how disease, molecules and drugs affect cell function in vivo. Using muscle stem cell (muSC) responses to injury in zebrafish as our biological paradigm we have established a ground truth for muSC cell behaviour. This revealed that variability in segmentation and tracking algorithms from commonly used programs are errorprone, leading us to develop a fast semi-automated image analysis pipeline that allows user defined parameters for segmentation and correction of cell tracking. Cell Tracking Profiler (CTP) operates through the freely available Icy platform, and allows usermanaged cell tracking from 3D time-lapsed datasets to provide measures of cell shape and movement. Using dimensionality reduction methods, multiple correlation and regression analyses we identify myosin II-dependent parameters of muSC behaviour during regeneration. CTP and the associated statistical tools we have developed thus provide a powerful framework for analysing complex cell behaviour in vivo from 4D datasets.

Central vascular stiffening, determined in vivo via pulse wave velocity (PWV), independently predicts cardiovascular event risk and is accelerated in obesity. Little is known regarding potential regional variations in arterial stiffening in obesity. We assessed aortic and femoral PWV with ex vivo analyses of femoral and coronary structure/function in a mouse model of western diet (WD; high‐fat/high‐sugar)‐induced obesity. WD increased aortic and femoral PWV. Ex vivo femoral artery analysis revealed a leftward shift in the strain‐stress relationship, increased modulus of elasticity, and decreased compliance indicative of increased stiffness following WD. Confocal and multiphoton fluorescence microscopy revealed that increased femoral stiffness involved decreased elastin/collagen ratio in WD. Analysis of the femoral internal elastic lamina (IEL) revealed reduced number and size of fenestrae with WD. Coronary artery stiffness/structure was unchanged by WD. Functionally, femoral, not coronary, arteries exhibited endothelial dysfunction while coronary, not femoral, arteries exhibited increased vasoconstrictor responsiveness. Overall, our data highlight important regional variations in arterial stiffening/dysfunction and highlight IEL fenestrae remodeling as a potential contributor to femoral artery stiffening in obesity.

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27% using a novel pointing game metric. CLEAR Image excels in identifying cases of 'causal overdetermination' where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.

The monotonous routine of medical image analysis under tight time constraints has always led to work fatigue for many medical practitioners. Medical image interpretation can be error-prone and this can increase the risk of an incorrect procedure being recommended. While the advancement of complex deep learning models has achieved performance beyond human capability in some computer vision tasks, widespread adoption in the medical field has been held back, among other factors, by poor model interpretability and a lack of high-quality labelled data. This paper introduces a model interpretation and visualisation framework for the analysis of the feature extraction process of a deep convolutional neural network and applies it to abnormality detection using the musculoskeletal radiograph dataset (MURA, Stanford). The proposed framework provides a mechanism for interpreting DenseNet deep learning architectures. It aims to provide a deeper insight about the paths of feature generation and reasoning within a DenseNet architecture. When evaluated on MURA at abnormality detection tasks, the model interpretation framework has been shown capable of identifying limitations in the reasoning of a DenseNet architecture applied to radiography, which can in turn be ameliorated through model interpretation and visualization.

No abstract