Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives.

Deep learning has demonstrated remarkable performance across various tasks in medical imaging. However, these approaches primarily focus on supervised learning, assuming that the training and testing data are drawn from the same distribution. Unfortunately, this assumption may not always hold true in practice. To address these issues, unsupervised domain adaptation (UDA) techniques have been developed to transfer knowledge from a labeled domain to a related but unlabeled domain. In recent years, significant advancements have been made in UDA, resulting in a wide range of methodologies, including feature alignment, image translation, self-supervision, and disentangled representation methods, among others. In this paper, we provide a comprehensive literature review of recent deep UDA approaches in medical imaging from a technical perspective. Specifically, we categorize current UDA research in medical imaging into six groups and further divide them into finer subcategories based on the different tasks they perform. We also discuss the respective datasets used in the studies to assess the divergence between the different domains. Finally, we discuss emerging areas and provide insights and discussions on future research directions to conclude this survey.

"Free" copper: a new endogenous chemical mediator of inflammation in birds.

For acceptance of any chemical agent as an endogenous chemical mediator of inflammation, the agent in question must fulfill some biological requirements which are (a) it should be ubiquitously present in tissues in inactive form, (b) it should be activated during process of inflammation whose increase should be identifiable, (c) it should induce or amplify some events of inflammation, (d) there must be some natural inhibitor of such active form in tissues, (e) it should be able to induce inflammatory reaction after exogenous injection, (f) such reaction should be inhibited by exogenous use of their antagonists, and (g) it should be amplified by use of agonists. Copper in its protein free or protein bound form are reported to act as pathogenic factor in inflammatory processes due to oxidative stress. But their role as endogenous chemical mediator of inflammation does not appear to be investigated thoroughly in light of abovementioned biological criterion of mediator. Present study aims at thorough exploration on role of free copper as endogenous chemical mediator of inflammation in light of above facts. It was done by estimation of total copper, protein-bound copper, and free copper along with estimation of free radical generation, increase in vascular permeability, and cellular infiltration during acute inflammatory reaction induced by carrageenan and concanavalin using chicken skin as test model. It was further evaluated by use of exogenous free copper in experimental model and their subsequent inhibition and amplification by chemical chelators of copper. Present study confirms that free copper fulfilled all the biological requirements for accepting it as an endogenous chemical mediator of inflammation.

Antidiabetic activity and phytochemical screening of crude extract of Stevia rebaudiana in alloxan-induced diabetic rats.

BACKGROUND: Stevia rebaudiana regulates blood sugar, prevents hypertension and tooth decay. Other studies have shown that it has antibacterial as well as antiviral property. METHODS: Preliminary phytochemical screening of aqueous, ether and methanolic extracts of S. rebaudiana was done. Acute and sub-acute toxicity were conducted on twenty four Albino rats, divided into one control (Group I) and three treatment groups viz. aqueous extract (Group II), ether extract (Group III) and methanolic extract (Group IV). For the study of antidiabetic effect of S. rebaudiana rats were divided into seven groups (n=6). Diabetes was induced by a single dose of 5% alloxan monohydrate (125 mg/kg, i.p.) after 24 hour fasting.Blood samples were analysed on day 0, 1, 5, 7, 14 and 28. RESULTS: Phytochemical tests showed presence of different kinds of phyto-constituents in aqueous, ether and methanol extract of Stevia rebaudiana leaves. Daily single dose (2.0 g/kg) administration of aqueous extract (A.E.) , ether extract (E.E.) and methanol extract (M.E.) for 28 days of S. rebaudiana could not show any significant change in ALT and AST levels in rats. Blood sugar level was found to be decreased on day 28 in groups of rats treated with A.E., E.E. and M.E. of S. rebaudiana. CONCLUSION: The extracts of Stevioside rebaudiana could decrease the blood glucose level in diabetic rats in time dependent manner.