Microscopy Image Dataset for Deep Learning-Based Quantitative Assessment of Pulmonary Vascular Changes.

Pulmonary hypertension (PH) is a syndrome complex that accompanies a number of diseases of different etiologies, associated with basic mechanisms of structural and functional changes of the pulmonary circulation vessels and revealed pressure increasing in the pulmonary artery. The structural changes in the pulmonary circulation vessels are the main limiting factor determining the prognosis of patients with PH. Thickening and irreversible deposition of collagen in the pulmonary artery branches walls leads to rapid disease progression and a therapy effectiveness decreasing. In this regard, histological examination of the pulmonary circulation vessels is critical both in preclinical studies and clinical practice. However, measurements of quantitative parameters such as the average vessel outer diameter, the vessel walls area, and the hypertrophy index claimed significant time investment and the requirement for specialist training to analyze micrographs. A dataset of pulmonary circulation vessels for pathology assessment using semantic segmentation techniques based on deep-learning is presented in this work. 609 original microphotographs of vessels, numerical data from experts' measurements, and microphotographs with outlines of these measurements for each of the vessels are presented. Furthermore, here we cite an example of a deep learning pipeline using the U-Net semantic segmentation model to extract vascular regions. The presented database will be useful for the development of new software solutions for the analysis of histological micrograph.

Inhibition of JAK1,2 Prevents Fibrotic Remodeling of Pulmonary Vascular Bed and Improves Outcomes in the Rat Model of Chronic Thromboembolic Pulmonary Hypertension.

Chronic thromboembolic pulmonary hypertension (CTEPH) is a rare complication of acute pulmonary embolism with poor clinical outcomes. Therapeutic approaches to prevention of fibrotic remodeling of the pulmonary vascular bed in CTEPH are limited. In this work, we tested the hypothesis that Janus kinase 1/2 (JAK1/2) inhibition with ruxolitinib might prevent and attenuate CTEPH in a rat model. CTEPH was induced by repeated embolization of the pulmonary artery with partially biodegradable 180 ± 30 µm alginate microspheres. Two weeks after the last injection of microspheres, ruxolitinib was administered orally at doses of 0.86, 2.58, and 4.28 mg/kg per day for 4 weeks. Prednisolone (1.475 mg/kg, i.m.) was used as a reference drug. Ruxolitinib in all doses as well as prednisolone reduced pulmonary vascular wall hypertrophy. Ruxolitinib at a dose of 2.58 mg/kg and prednisolone reduced vascular wall fibrosis. Prednisolone treatment resulted in decreased right ventricular systolic pressure. Pulmonary vascular resistance was lower in the prednisolone and ruxolitinib (4.28 mg/kg) groups in comparison with the placebo group. The plasma level of brain natriuretic peptide was lower in groups receiving ruxolitinib at doses of 2.58 and 4.28 mg/kg versus placebo. This study demonstrated that JAK1/2 inhibitor ruxolitinib dose-dependently reduced pulmonary vascular remodeling, thereby preventing CTEPH formation in rats.

Melatonin: Manager of psychosomatic and metabolic disorders in polymorbid cardiovascular pathology.

Objectives: To investigate the relationship between changes in circadian patterns of melatonin and clinical manifestations of polymorbid cardiovascular pathology (PCVP) in young men and to analyze the effectiveness of their complex treatment. Materials and methods: We made the immunohistochemical (IHC) analysis of epiphysis tissues from autopsies of 25 men aged 32-44 with PCVP and metabolic syndrome (MS) who had died as a result of ischemic cardiomyopathy (IC) and 25 persons after the car accident as a control group. Then, 93 young men aged 35-44 with PCVP, metabolic syndrome, and depressive spectrum disorders (DSD) were divided into three groups: (1) standard therapy; (2) standard therapy and psychotherapy sessions; (3) standard therapy in combination with psychotherapeutic and psychophysiological visual and auditory correction sessions. The control group included 24 conditionally healthy male volunteers. Before and after the treatment, we studied the anthropometric status, lipid and carbohydrate metabolism indicators, the level of urinary 6-hydroxymelatonin sulfate, the degree of nocturnal decrease in blood pressure (BP), and the relationship of these indicators with circadian variations of melatonin excretion. Results: Young polymorbid patients who died from IC have a lower expression of melatonin type 1 and 2 receptors. All patients with PCVP showed a decrease in the nocturnal melatonin excretion fraction and a correlation with higher severity of depressive (r = -0.72) and anxiety (r = -0.66) symptoms. Reduced values of the 6-hydroxymelatonin sulfate (6-SM) in the 1st (r = 0.45), 2nd (r = 0.39), and 3rd (r = 0.51) groups before treatment was associated with periods of increased BP. The achievement of melatonin excretion reference values and normalization of biochemical parameters of carbohydrate and lipid metabolism, daily BP profile, and psychophysiological state were noted in all three patients' groups, with a more pronounced effect in group 3. Conclusion: Low nocturnal melatonin excretion levels are associated with greater severity of clinical symptoms and a higher risk of death in patients with PCVP. Therefore, comprehensive therapy may be more effective for correcting this disease.

Shape anomaly detection under strong measurement noise: An analytical approach to adaptive thresholding.

We suggest an analytical approach to the adaptive thresholding in a shape anomaly detection problem. We find an analytical expression for the distribution of the cosine similarity score between a reference shape and an observational shape hindered by strong measurement noise that depends solely on the noise level and is independent of the particular shape analyzed. The analytical treatment is also confirmed by computer simulations and shows nearly perfect agreement. Using this analytical solution, we suggest an improved shape anomaly detection approach based on adaptive thresholding. We validate the noise robustness of our approach using typical shapes of normal and pathological electrocardiogram cycles hindered by additive white noise. We show explicitly that under high noise levels our approach considerably outperforms the conventional tactic that does not take into account variations in the noise level.