Superb Microvascular Imaging Doppler Technique In The Evaluation Of Ovarian Stromal Vascularity In Women With Polycystic Ovary Syndrome.

OBJECTIVE: To compare the assessment of intra-ovarian stromal vascularity through transabdominal ultrasonography with colour Doppler imaging, power Doppler imaging, colour superb microvascular imaging and monochrome superb microvascular imaging in polycystic ovary syndrome cases. METHODS: The retrospective cross-sectional study was conducted at the Obstetrics and Gynaecology outpatient department of the Usak Training and Research Hospital, Turkey, from April 11 to June 18, 2018, and comprised grayscale colour Doppler imaging, power Doppler imaging, colour superb microvascular imaging and monochrome superb microvascular imaging of women with polycystic ovary syndrome. The recorded video images were evaluated by three radiologists and rated through consensus decision. Mean values for age, body mass index, follicle stimulating hormone and luteinizing hormone levels, luteinizing hormone-follicle stimulating hormone ratio, Ferriman Gallwey score, and mean ovarian volume of the subjects were evaluated. Data was analysed using Number Cruncher Statistical System. RESULTS: Of the 54 women evaluated, data of 42(77.8%) was included. There were a total of 83 ovaries, as the left ovary of 1(1.2%) patient was not visible. The mean age and body mass index were 24.02±5.8 years and 25.08±4.5kg/m2. Mean follicle stimulating hormone and luteinizing hormone levels were 5.51±1.91 and 7.91±6.13m IU/mL. Luteinizing hormone/follicle stimulating hormone ratio and Ferriman Gallwey score were 1.4±0.8 and 8.67 ±6.94, respectively. The mean ovarian volume was 12.2±3.43 cm3. The detection of vascularity was colour Doppler imaging 0.72±0.97, power Doppler imaging 0.96±1.08, colour superb microvascular imaging 2.47±1.25, and monochrome superb microvascular imaging 2.75±1.31. The techniques were significant for superb microvascular imaging Doppler than conventional Doppler (p<0.001). Hyper- ovarian stromal vascularity, like a 'stellate' sign, was detected in 17(20.5%) of the total 83 ovaries analysed. CONCLUSIONS: Transabdominal ultrasonography-colour superb microvascular imaging was found to be more effective in detecting ovarian vascularity than conventional Doppler technique in women with polycystic ovary syndrome.

ExGenNet: Learning to Generate Robotic Facial Expression Using Facial Expression Recognition.

The ability of a robot to generate appropriate facial expressions is a key aspect of perceived sociability in human-robot interaction. Yet many existing approaches rely on the use of a set of fixed, preprogrammed joint configurations for expression generation. Automating this process provides potential advantages to scale better to different robot types and various expressions. To this end, we introduce ExGenNet, a novel deep generative approach for facial expressions on humanoid robots. ExGenNets connect a generator network to reconstruct simplified facial images from robot joint configurations with a classifier network for state-of-the-art facial expression recognition. The robots' joint configurations are optimized for various expressions by backpropagating the loss between the predicted expression and intended expression through the classification network and the generator network. To improve the transfer between human training images and images of different robots, we propose to use extracted features in the classifier as well as in the generator network. Unlike most studies on facial expression generation, ExGenNets can produce multiple configurations for each facial expression and be transferred between robots. Experimental evaluations on two robots with highly human-like faces, Alfie (Furhat Robot) and the android robot Elenoide, show that ExGenNet can successfully generate sets of joint configurations for predefined facial expressions on both robots. This ability of ExGenNet to generate realistic facial expressions was further validated in a pilot study where the majority of human subjects could accurately recognize most of the generated facial expressions on both the robots.

The Moral Choice Machine.

Allowing machines to choose whether to kill humans would be devastating for world peace and security. But how do we equip machines with the ability to learn ethical or even moral choices? In this study, we show that applying machine learning to human texts can extract deontological ethical reasoning about "right" and "wrong" conduct. We create a template list of prompts and responses, such as "Should I [action]?", "Is it okay to [action]?", etc. with corresponding answers of "Yes/no, I should (not)." and "Yes/no, it is (not)." The model's bias score is the difference between the model's score of the positive response ("Yes, I should") and that of the negative response ("No, I should not"). For a given choice, the model's overall bias score is the mean of the bias scores of all question/answer templates paired with that choice. Specifically, the resulting model, called the Moral Choice Machine (MCM), calculates the bias score on a sentence level using embeddings of the Universal Sentence Encoder since the moral value of an action to be taken depends on its context. It is objectionable to kill living beings, but it is fine to kill time. It is essential to eat, yet one might not eat dirt. It is important to spread information, yet one should not spread misinformation. Our results indicate that text corpora contain recoverable and accurate imprints of our social, ethical and moral choices, even with context information. Actually, training the Moral Choice Machine on different temporal news and book corpora from the year 1510 to 2008/2009 demonstrate the evolution of moral and ethical choices over different time periods for both atomic actions and actions with context information. By training it on different cultural sources such as the Bible and the constitution of different countries, the dynamics of moral choices in culture, including technology are revealed. That is the fact that moral biases can be extracted, quantified, tracked, and compared across cultures and over time.