Automated segmentation of cell organelles in volume electron microscopy using deep learning.

Recent advances in computing power triggered the use of artificial intelligence in image analysis in life sciences. To train these algorithms, a large enough set of certified labeled data is required. The trained neural network is then capable of producing accurate instance segmentation results that will then need to be re-assembled into the original dataset: the entire process requires substantial expertise and time to achieve quantifiable results. To speed-up the process, from cell organelle detection to quantification across electron microscopy modalities, we propose a deep-learning based approach for fast automatic outline segmentation (FAMOUS), that involves organelle detection combined with image morphology, and 3D meshing to automatically segment, visualize and quantify cell organelles within volume electron microscopy datasets. From start to finish, FAMOUS provides full segmentation results within a week on previously unseen datasets. FAMOUS was showcased on a HeLa cell dataset acquired using a focused ion beam scanning electron microscope, and on yeast cells acquired by transmission electron tomography. RESEARCH HIGHLIGHTS: Introducing a rapid, multimodal machine-learning workflow for the automatic segmentation of 3D cell organelles. Successfully applied to a variety of volume electron microscopy datasets and cell lines. Outperforming manual segmentation methods in time and accuracy. Enabling high-throughput quantitative cell biology.

U-Net based vessel segmentation for murine brains with small micro-magnetic resonance imaging reference datasets.

Identification and quantitative segmentation of individual blood vessels in mice visualized with preclinical imaging techniques is a tedious, manual or semiautomated task that can require weeks of reviewing hundreds of levels of individual data sets. Preclinical imaging, such as micro-magnetic resonance imaging (µMRI) can produce tomographic datasets of murine vasculature across length scales and organs, which is of outmost importance to study tumor progression, angiogenesis, or vascular risk factors for diseases such as Alzheimer's. Training a neural network capable of accurate segmentation results requires a sufficiently large amount of labelled data, which takes a long time to compile. Recently, several reasonably automated approaches have emerged in the preclinical context but still require significant manual input and are less accurate than the deep learning approach presented in this paper-quantified by the Dice score. In this work, the implementation of a shallow, three-dimensional U-Net architecture for the segmentation of vessels in murine brains is presented, which is (1) open-source, (2) can be achieved with a small dataset (in this work only 8 µMRI imaging stacks of mouse brains were available), and (3) requires only a small subset of labelled training data. The presented model is evaluated together with two post-processing methodologies using a cross-validation, which results in an average Dice score of 61.34% in its best setup. The results show, that the methodology is able to detect blood vessels faster and more reliably compared to state-of-the-art vesselness filters with an average Dice score of 43.88% for the used dataset.

Effects of 8-week increment aerobic exercise program on bone metabolism and body composition in young non-athletes.

PURPOSE: The effects of aerobic exercise on bone metabolism are still unclear. Thus, the main goal of this study was to explore if there was an effect of the short-term aerobic exercise program on the bone remodeling process and if there were sex differences in the effect of the training program on bone metabolism. METHODS: Twenty-one participants (men and women) aged 20-23 performed an 8-week aerobic exercise program three times per week in 1-h sessions with increases in the exercise load every 2 weeks. Bone density, bone mineral content and concentration of markers of bone metabolism: osteocalcin, C-terminal procollagen type I peptide, pyridinoline, parathyroid hormone, osteoprotegerin, and the receptor activator of nuclear kappa B ligand by ELISA were measured at the start and at the end of the study, while changes in body composition were assessed by a bioelectric impedance analysis method 6 times during the study. RESULTS: The aerobic exercise program increased the concentration of osteocalcin (11.34 vs 14.24 ng/ml), pyridinoline (67.51 vs 73.99 nmol/l), and the receptor activator of nuclear kappa B ligand (95.122 vs 158.15 pg/ml). A statistically significant increase in bone density at neck mean (1.122 vs 1.176 g/cm3) and in bone mineral content at dual femur (33.485 vs 33.700 g) was found in women, while there was no statistically significant change at any site in men. CONCLUSION: 8 weeks of the aerobic exercise program with increment in intensity increased some of bone remodeling biomarkers and showed different effects for men and women.

Changes in Blood Pressure After Single Bout of Aerobic Exercise in Young Healthy People- Influence of Body Composition.

Amount of change in blood pressure after exercise is related to risk of hypertension and cardiovascular diseases. The aim of this study was to determine whether there is a difference in the amount of change of blood pressure after exercise among people with different morphological characteristics, especially with differences in percent of body fat. 30 healthy subjects (15 males and 15 females) aged 25-30 years were included in the study. They were measured for weight and height, and their body composition was assesed by bioelectrical impendance device GAYA 357. Blood pressure was measured at rest and immediately after performing Cooper´s test. After classification of subjects according to BMI (body mass index) and according to percent of body fat (PBF) differences in the size of change in blood pressure among categories were compared. Results indicate that there is no difference between sexes in amount of change for DBP, but there is difference in change of SBP; in males this change was significantly higher than in females. We also found difference in SBP results at rest between different categories of BMI (p=0,023), that was not influenced by gender, while the difference between categories based on different PBF were under the influence of gender. Based on results conclusion can be made that percent of body fat is a factor that influence amount of change in blood pressure with exercise, and is potentially important, and could be predictive factor, like BMI or together with it, in determining the risk of hypertension in young healthy people.