METHODS: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos.
RESULTS: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models.
CONCLUSION: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.
OBJECTIVES: To compare the effectiveness of anticoagulant therapies for the treatment of deep vein thrombosis in pregnancy. The anticoagulant drugs included are UFH, low molecular weight heparin (LMWH) and warfarin.
SEARCH STRATEGY: We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (March 2010) and reference lists of retrieved studies.
SELECTION CRITERIA: Randomised controlled trials comparing any combination of warfarin, UFH, LMWH and placebo in pregnant women.
DATA COLLECTION AND ANALYSIS: We used methods described in the Cochrane Handbooks for Systemic Reviews of Interventions for assessing the eligibility of studies identified by the search strategy. A minimum of two review authors independently assessed each study.
MAIN RESULTS: We did not identify any eligible studies for inclusion in the review.We identified three potential studies; after assessing eligibility, we excluded all three as they did not meet the prespecified inclusion criteria. One study compared LMWH and UFH in pregnant women with previous thromboembolic events and, for most of these women, anticoagulants were used as thromboprophylaxis. There were only three women who had a thromboembolic event during the current pregnancy and it was unclear whether the anticoagulant was used as therapy or prophylaxis. We excluded one study because it included only women undergoing caesarean birth. The third study was not a randomised trial.
AUTHORS' CONCLUSIONS: There is no evidence from randomised controlled trials on the effectiveness of anticoagulation for deep vein thrombosis in pregnancy. Further studies are required.
OBJECTIVE: Previously published findings showed that phytoestrogens could relieve menopausal complaints, thus, the present review was aimed at assessing the effects of phytoestrogens on thermoregulatory mechanism during menopausal transition.
RESULTS: The molecular mechanisms underlying hot flashes are complex. Oestrogen fluctuations cause hypothalamic thermoregulatory centre dysfunction, which leads to hot flashes during menopause. The phytoestrogens of interest, in relation to human health, include isoflavones, lignans, coumestans, and stilbenes, which are widely distributed in nature. The phytoestrogens are capable of reducing hot flashes via their oestrogen-like hormone actions. The potential effects of phytoestrogens on hot flashes and their molecular mechanisms of action on thermoregulatory centre are discussed in this review.
CONCLUSION: The effects of phytoestrogens on these mechanisms may help explain their beneficial effects in alleviating hot flashes and other menopausal discomforts.