Semantic segmentation of human cell nucleus using deep U-Net and other versions of U-Net models.

The deep learning models play an essential role in many areas, including medical image analysis. These models extract important features without human intervention. In this paper, we propose a deep convolution neural network, named as deep U-Net model, for the segmentation of the cell nucleus, a critical functional unit that determines the function and structure of the body. The nucleus contains all kinds of DNA, RNA, chromosomes, and genes governing all life activities, and its disorder may lead to different types of diseases such as cancer, heart disease, diabetes, Alzheimer's, etc. If the nucleus structure is known correctly, diseases due to nucleus disorder may be detected early. It may also reduce the drug discovery time if the shape and size of the nucleus are known. We evaluate the performance of the proposed models on the nucleus segmentation data set used by the Data Science Bowl 2018 competition hosted by Kaggle. We compare its performance with that of the U-Net, Attention U-Net, R2U-Net, Attention R2U-Net, and both versions of the U-Net++ with and without supervision, in terms of loss, dice coefficient, dice loss, intersection over union, and accuracy. Our model performs better than the existing models.

A Prospective Observational Comparative Study of Novel Autologous Negative Pressure Epidermal Harvesting System (ANPEHS or EHS) and Suction Blister Grafting (SBG) in Treatment of Stable Vitiligo.

BACKGROUND: Vitiligo surgery has evolved a long way from punch skin grafts to the epidermal cell suspension and latest to the extracted hair follicle outer root sheath cell suspension transplantation (EHFORSCS). In the latest development, the novel technique autologous negative pressure epidermal harvesting system (ANPEHS) seems to be a good addition to the prevailing therapy in vitiligo. AIMS AND OBJECTIVES: The aim of this work was to study and compare novel ANPEHS and suction blister grafting (SBG) in the treatment of stable vitiligo. MATERIALS AND METHODS: This was a prospective, single-centered, observational, open-labeled comparative study of the rate and final extent of repigmentation in ANPEHS or EHS and SBG in the management of stable vitiligo. The patients in this study were drawn from the outpatient Department of Dermatology of a Tertiary Care Hospital of the Armed Forces from July 1 2015 to December 31, 2016. A total of 40 patients with at least two comparable depigmented patches of 6 months' stability were recruited. Both procedures were performed in the same patient on the same day. Informed consents were taken from all the patients. Each patient in the study had undergone a detailed clinical, general physical, systemic, and a dermatological examination. Clinical photographs had been taken before and after grafting, monthly for the first 6 months then bimonthly for the next 6 months. Donor site was preferably inner aspect of thigh. STATISTICAL ANALYSIS USED: "Chi-square test" and "statistical significance" (P value) methods. RESULTS: Of total 80 patches, excellent results were seen in 82.9% patches by using the EHS method and 80% excellent results by using the SBG method. Similarly, very good results were seen in 2.9% patches and good results in 5.7% patches by using both methods. 11.4% patches showed poor results by using the SBG method and 8.6% patches showed poor results by using the EHS method. CONCLUSIONS: The EHS method is a simple, painless, less time-consuming, expensive but effective technique to produce homogeneous repigmentation without any donor site anesthesia and complication.

Convergent synthesis and preliminary biological evaluations of the stilbenolignan (+/-)-aiphanol and various congeners.

Treatment of an equimolar mixture of stilbene 7 and cinnamyl alcohol 8 with silver carbonate in acetone-benzene afforded a ca. 2:1:2:1 mixture of the stilbenolignan (+/-)-aiphanol (1) and congeners 2-4 each of which show significant anti-angiogenic and COX-2 inhibitory properties.