The recent progress of computing, machine learning, and especially deep learning, for image recognition brings a meaningful effect for automatic detection of various diseases from chest X-ray images (CXRs). Here efficiency of lung segmentation and bone shadow exclusion techniques is demonstrated for analysis of 2D CXRs by deep learning approach to help radiologists identify suspicious lesions and nodules in lung cancer patients. Training and validation was performed on the original JSRT dataset (dataset #01), BSE-JSRT dataset, i.e. the same JSRT dataset, but without clavicle and rib shadows (dataset #02), original JSRT dataset after segmentation (dataset #03), and BSE-JSRT dataset after segmentation (dataset #04). The results demonstrate the high efficiency and usefulness of the considered pre-processing techniques in the simplified configuration even. The pre-processed dataset without bones (dataset #02) demonstrates the much better accuracy and loss results in comparison to the other pre-processed datasets after lung segmentation (datasets #02 and #03).
Abstract:With the rapid development of assisted reproductive technology, various reproductive disorders have been effectively addressed. Acupuncture-like therapies, including electroacupuncture (EA) and transcutaneous electrical acupoint stimulation (TEAS), become more popular world-wide. Increasing evidence has demonstrated that EA and TEAS are effective in treating gynecological disorders, especially infertility. This present paper describes how to select acupoints for the treatment of infertility from the view of theories of traditional Chinese medicine and how to determine critical parameters of electric pulses of EA/TEAS based on results from animal and clinical studies. It summarizes the principles of clinical application of EA/TEAS in treating various kinds of reproductive disorders, such as polycystic ovary syndrome (PCOS), pain induced by oocyte retrieval, diminished ovarian reserve, embryo transfer, and oligospermia/ asthenospermia. The possible underlying mechanisms mediating the therapeutic effects of EA/TEAS in reproductive medicine are also examined.
Acute phase proteins and inflammatory cytokines (IL-1β, IL-6, and TNF-α) show significant changes between the AMS group and the non-AMS group. Combination of inflammatory cytokines or acute phase proteins improves the specificity for diagnosis of AMS. This might provide objective indexes for scanning and screening individuals susceptible to AMS in the early stage of rapid ascending.
BackgroundDiabetes mellitus (DM) exacerbates coronary artery disease (CAD) morbidity and mortality. Mesenchymal stem cells (MSCs) play an important therapeutic role in myocardial ischemic injury. However, little is known about changes in the cardioprotective characteristics of MSCs from patients with DM.MethodsSternal bone marrow aspirates were taken at the time of coronary artery bypass graft surgery. The morphology and growth characteristics of hMSCs were observed in passage 3. Differences in gene expression profiling were measured by Affymetrix GeneChipHuman Genome U133 Plus 2.0 Arrays. Forty two adult male rats with experimentally CAD were randomized into three groups. MSCs from patients with CAD+DM or CAD were injected into the infarcted myocardium. Control animals received culture medium. Echocardiography, TUNEL, immunohistochemistry and Western-blot analysis were performed 4 weeks after transplantation.ResultsGrowth curves showed that proliferation of hMSCs in the CAD+DM group was significantly lower than in the CAD group. Nine transcripts of genes related to apoptosis containing Bcl-2 were found to differentiate the two groups. Transplantation of hMSCs in the infarcted border zone improved cardiac function, but DM partly impaired this effect. Similar results were observed from TUNEL, immunohistochemistry and Western-blot analysis.ConclusionshMSCs from patients with CAD+DM and CAD alone both have proliferative properties. Transplantation of hMSCs ameliorate heart function, but proliferative ability and myocardial protection decrease significantly in MSCs obtained from patients with CAD+DM compared with cultures from patients with CAD alone, possibly as a result of differences in Bcl-2 protein expression and reduced anti-apoptosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.