Generalizing the Enhanced-Deep-Super-Resolution Neural Network to Brain MR Images: A Retrospective Study on the Cam-CAN Dataset.

The Enhanced-Deep-Super-Resolution (EDSR) model is a state-of-the-art convolutional neural network suitable for improving image spatial resolution. It was previously trained with general-purpose pictures and then, in this work, tested on biomedical magnetic resonance (MR) images, comparing the network outcomes with traditional up-sampling techniques. We explored possible changes in the model response when different MR sequences were analyzed. T1w and T2w MR brain images of 70 human healthy subjects (F:M, 40:30) from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) repository were down-sampled and then up-sampled using EDSR model and BiCubic (BC) interpolation. Several reference metrics were used to quantitatively assess the performance of up-sampling operations (RMSE, pSNR, SSIM, and HFEN). Two-dimensional and three-dimensional reconstructions were evaluated. Different brain tissues were analyzed individually. The EDSR model was superior to BC interpolation on the selected metrics, both for two- and three- dimensional reconstructions. The reference metrics showed higher quality of EDSR over BC reconstructions for all the analyzed images, with a significant difference of all the criteria in T1w images and of the perception-based SSIM and HFEN in T2w images. The analysis per tissue highlights differences in EDSR performance related to the gray-level values, showing a relative lack of outperformance in reconstructing hyperintense areas. The EDSR model, trained on general-purpose images, better reconstructs MR T1w and T2w images than BC, without any retraining or fine-tuning. These results highlight the excellent generalization ability of the network and lead to possible applications on other MR measurements.

Review of the Heat Stress-Induced Responses in Dairy Cattle.

In the dairy cattle sector, the evaluation of the effects induced by heat stress is still one of the most impactful and investigated aspects as it is strongly connected to both sustainability of the production and animal welfare. On the other hand, more recently, the possibility of collecting a large dataset made available by the increasing technology diffusion is paving the way for the application of advanced numerical techniques based on machine learning or big data approaches. In this scenario, driven by rapid change, there could be the risk of dispersing the relevant information represented by the physiological animal component, which should maintain the central role in the development of numerical models and tools. In light of this, the present literature review aims to consolidate and synthesize existing research on the physiological consequences of heat stress in dairy cattle. The present review provides, in a single document, an overview, as complete as possible, of the heat stress-induced responses in dairy cattle with the intent of filling the existing research gap for extracting the veterinary knowledge present in the literature and make it available for future applications also in different research fields.

Biomechanical and metabolic responses to seat-tube angle variation during cycling in tri-athletes.

One of the most physically demanding parts of triathlon is the transition from cycling to running. Many tri-athletes believe that increasing seat-tube angle (STA) can bring advantages in the following running part. The aim of this study was to evaluate the effects of inverting the support of the seat, for increasing STA, on the metabolic response and on the muscle activation pattern, maintaining a controlled kinematic. Moreover, a muscle-skeletal model was applied to evaluate the hypothesis that increasing STA changes force-producing capabilities of muscles crossing the hip. Ten tri-athletes cycled at two different power levels and with two different STA's. Gas exchange data, kinematics and surface electromyography (sEMG) were acquired during the tests. sEMG was measured from eight muscles of the right side of the body. A model of muscle mechanics and energy expenditure was applied to estimate variations of force production capabilities and muscle energy consumption between the two STA configurations. Inverting the support of the seat showed no significant effects on kinematic, Oxygen consumption, muscle activations and muscle power production capabilities. Nevertheless, an interesting advantage can be the tendency to less activate gastrocnemius and biceps femoris: this could lead to minor muscle fatigue during the following running phase.