安卓平台上的医用图像信息采集系统的开发设计

为了探讨在安卓平台上构建医用图像采集系统的开发个案,分析通过以智能手机、平板电脑为核心安卓设备通过拍照获得化验单数据后进行文本识别并提交智慧医疗系统的解决方案。本文首先通过二值化算法形成低阈值图像数据,使用卷积神经元网络算法对文本进行逐一识别,使用K-means算法对识别后的单字文本进行字段记录值的整合并形成元数据库服务于其他智慧医疗系统模块。在使用9000组数据对神经元网络进行前期训练的前提下,该系统的识别准确率达到了99.5%以上。本系统具有一定的可行性,对未来智慧医疗的系统开发有实践意义。     

A deep neural network based classifier for brain tumor diagnosis

Classification process plays a key role in diagnosing brain tumors. Earlier research works are intended for identifying brain tumors using different classification techniques. However, the False Alarm Rates (FARs) of existing classification techniques are high. To improve the early-stage brain tumor diagnosis via classification the Weighted Correlation Feature Selection Based Iterative Bayesian Multivariate Deep Neural Learning (WCFS-IBMDNL) technique is proposed in this work. The WCFS-IBMDNL algorithm considers medical dataset for classifying the brain tumor diagnosis at an early stage. At first, the WCFS-IBMDNL technique performs Weighted Correlation-Based Feature Selection (WC-FS) by selecting subsets of medical features that are relevant for classification of brain tumors. After completing the feature selection process, the WCFS-IBMDNL technique uses Iterative Bayesian Multivariate Deep Neural Network (IBMDNN) classifier for reducing the misclassification error rate of brain tumor identification. The WCFS-IBMDNL technique was evaluated in JAVA language using Disease Diagnosis Rate (DDR), Disease Diagnosis Time (DDT), and FAR parameter through the epileptic seizure recognition dataset.     

Plasma gasification of the medical waste

In terms of infection control in hospitals, especially the Covid-19 pandemic that we are living in, it has revealed the necessity of proper disposal of medical waste. The increasing amount of medical waste with the pandemic is straining the capacity of incineration facilities or storage areas. Converting this waste to energy with gasification technologies instead of incineration is also important for sustainability. This study investigates the gasification characteristics of the medical waste in a novel updraft plasma gasifier with numerical simulations in the presence of the plasma reactions. Three different medical waste samples, chosen according to the carbon content and five different equivalence ratios (ER) ranging from 0.1 to 0.5 are considered in the simulations to compare the effects of different chemical compositions and waste feeding rates on hydrogen (H₂) content and syngas production. The outlet properties of a 10 kW microwave air plasma generator are used to define the plasma inlet in the numerical model and the air flow rate is held constant for all cases. Results showed that the maximum H₂ production can be obtained with ER = 0.1 for all waste samples.     

药物相互作用研究在新药研发和审评决策中的应用

药物相互作用改变了剂量效应关系，可能会降低疗效或增加毒性，是临床应用中合并用药治疗时重要的考虑因素。预测具有临床意义的药物相互作用是药物研发过程中获益风险评估的重要环节。本文概述了药物研发过程中药物相互作用研究的目的和意义，体内和体外研究的主要内容；梳理分析了2020年国家药品监督管理局（National Medical Products Administration, NMPA）和美国食品药品监督管理局（Food and Drug Administration, FDA）批准上市的新药药物相互作用研究情况，旨在为我国药物研发过程中药物相互作用研究及其监管审评提供参考。     

Crisis communication,anticipated food scarcity,and food preferences: Preregistered evidence of the insurance hypothesis

Whereas large-scale consumption of energy-dense foods contributes to climate change, we investigated whether exposure to climate change-induced food scarcity affects preferences toward these foods. Humans’ current psychological mechanisms have developed in their ancestral evolutionary past to respond to immediate threats and opportunities. Consequently, these mechanisms may not distinguish between cues to actual food scarcity and cues to food scarcity distant in time and space. Drawing on the insurance hypothesis, which postulates that humans should respond to environmental cues to food scarcity through increased energy consumption, we predicted that exposing participants to climate change-induced food scarcity content increases their preferences toward energy-dense foods, with this effect being particularly pronounced in women. Three experiments—including one preregistered laboratory study—confirm this notion. Our findings jointly demonstrate that receiving information about food shortages distant in time and space can influence current food preferences.     

Trademarks and the patent premium value: Evidence from medical and cosmetic products

The determinants of the premium value of patents for medical and cosmetic products are analyzed with respect to a complementary IP strategy such as trademarks. I discuss a novel method and database to gauge combinations of patent and trademark pairs regarding the same innovative project. The premium value is computed through a model of renewal decisions for the patent cohorts 1985–1990 that have been designated in the U.K. and Germany. After taking into the account several firm characteristics and patent indicators typically used in the literature, I find ample evidences that patent and trademark pairs are featured by higher valuations.     

A new multi criteria decision making approach for medical imaging systems considering risk factors

Effective and good quality imaging is important for medical decision-making and can reduce unnecessary costs and procedures. Therefore, decision making regarding any technology can present serious problems for healthcare centers with multi criteria decision making problems (MCDM). This paper is the first to develop the fuzzy axiomatic design with risk factors (RFAD) approach and to use it in multi attribute comparisons of medical imaging systems in a university hospital. Although most MCDM approaches in the literature treat risk factors as separate criteria, in real life every alternative has its own risks related to each criterion. The proposed approach integrates the risk factors in each criterion and calculates the information content to compare alternatives. This paper applies three different approaches to MCDM problems related to the selection of medical imaging systems for a university hospital.     

Retinal microaneurysms detection using adversarial pre-training with unlabeled multimodal images

The detection of retinal microaneurysms is crucial for the early detection of important diseases such as diabetic retinopathy. However, the detection of these lesions in retinography, the most widely available retinal imaging modality, remains a very challenging task. This is mainly due to the tiny size and low contrast of the microaneurysms in the images. Consequently, the automated detection of microaneurysms usually relies on extensive ad-hoc processing. In this regard, although microaneurysms can be more easily detected using fluorescein angiography, this alternative imaging modality is invasive and not adequate for regular preventive screening.In this work, we propose a novel deep learning methodology that takes advantage of unlabeled multimodal image pairs for improving the detection of microaneurysms in retinography. In particular, we propose a novel adversarial multimodal pre-training consisting in the prediction of fluorescein angiography from retinography using generative adversarial networks. This pre-training allows learning about the retina and the microaneurysms without any manually annotated data. Additionally, we also propose to approach the microaneurysms detection as a heatmap regression, which allows an efficient detection and precise localization of multiple microaneurysms. To validate and analyze the proposed methodology, we perform an exhaustive experimentation on different public datasets. Additionally, we provide relevant comparisons against different state-of-the-art approaches. The results show a satisfactory performance of the proposal, achieving an Average Precision of 64.90%, 31.36%, and 33.55% in the E-Ophtha, ROC, and DDR public datasets. Overall, the proposed approach outperforms existing deep learning alternatives while providing a more straightforward detection method that can be effectively applied to raw unprocessed retinal images.     

ASTEMA: Design and preliminary performance assessment of a novel tele-microsurgery system

To overcome the challenges of reconstructive microsurgery, a teleoperated robot called ASTEMA was built to help surgeons performing microanastomoses. The surgeons’ needs are first analyzed then the design steps are summarized. This robot is composed of three orthogonal linear actuators and a spherical wrist with its remote center of motion at the instrument tip. Geometric model of the spherical wrist was calibrated through mathematical optimization in order to compensate for imperfections of machining and assembling. Two preliminary experiments were carried out to assess the ASTEMA performance. The first was performed with a simple circular position trajectory. The second was a complex angular trajectory. Results show a significant improvement of gesture precision with respect to manual trajectory execution. They also show that subjects instinctively compensate the errors from the non-ideal wrist, thanks to visual feedback from microscope.