Endomapper dataset of complete calibrated endoscopy procedures.

Computer-assisted systems are becoming broadly used in medicine. In endoscopy, most research focuses on the automatic detection of polyps or other pathologies, but localization and navigation of the endoscope are completely performed manually by physicians. To broaden this research and bring spatial Artificial Intelligence to endoscopies, data from complete procedures is needed. This paper introduces the Endomapper dataset, the first collection of complete endoscopy sequences acquired during regular medical practice, making secondary use of medical data. Its main purpose is to facilitate the development and evaluation of Visual Simultaneous Localization and Mapping (VSLAM) methods in real endoscopy data. The dataset contains more than 24 hours of video. It is the first endoscopic dataset that includes endoscope calibration as well as the original calibration videos. Meta-data and annotations associated with the dataset vary from the anatomical landmarks, procedure labeling, segmentations, reconstructions, simulated sequences with ground truth and same patient procedures. The software used in this paper is publicly available.

Tailored cancer therapy by magnetic nanoparticle hyperthermia: A virtual scenario simulation method.

BACKGROUND AND OBJECTIVE: Hyperthermia is a cancer treatment aiming to induce cell death by directly warming cancerous tissues above 40 °C. This technique can be applied both individually and together with other cancer therapies. The main challenge for researchers and medics is to heat only tumoral cells avoiding global or localized heating of sane tissues. The objective in this study is to provide a realistic virtual scenario to develop an optimized multi-site injection plan for tailored magnetic nanoparticle-mediated hyperthermia applications. METHODS: A three-dimensional model of a cat's back was tested in three different simulation scenarios, showing the impact of magnetic nanoparticles in each specific environment configuration. RESULTS: As a result of this study. This simulation method can, minimising the affection to healthy tissue. CONCLUSIONS: This virtual method will help real and personalized therapy planning and tailor the dose and distribution of magnetic nanoparticles for an enhanced hyperthermia cancer treatment.

A Wearable Textile 3D Gesture Recognition Sensor Based on Screen-Printing Technology.

Research has developed various solutions in order for computers to recognize hand gestures in the context of human machine interface (HMI). The design of a successful hand gesture recognition system must address functionality and usability. The gesture recognition market has evolved from touchpads to touchless sensors, which do not need direct contact. Their application in textiles ranges from the field of medical environments to smart home applications and the automotive industry. In this paper, a textile capacitive touchless sensor has been developed by using screen-printing technology. Two different designs were developed to obtain the best configuration, obtaining good results in both cases. Finally, as a real application, a complete solution of the sensor with wireless communications is presented to be used as an interface for a mobile phone.

An Electrochemical Impedance Spectroscopy System for Monitoring Pineapple Waste Saccharification.

Electrochemical impedance spectroscopy (EIS) has been used for monitoring the enzymatic pineapple waste hydrolysis process. The system employed consists of a device called Advanced Voltammetry, Impedance Spectroscopy & Potentiometry Analyzer (AVISPA) equipped with a specific software application and a stainless steel double needle electrode. EIS measurements were conducted at different saccharification time intervals: 0, 0.75, 1.5, 6, 12 and 24 h. Partial least squares (PLS) were used to model the relationship between the EIS measurements and the sugar determination by HPAEC-PAD. On the other hand, artificial neural networks: (multilayer feed forward architecture with quick propagation training algorithm and logistic-type transfer functions) gave the best results as predictive models for glucose, fructose, sucrose and total sugars. Coefficients of determination (R²) and root mean square errors of prediction (RMSEP) were determined as R² > 0.944 and RMSEP < 1.782 for PLS and R² > 0.973 and RMSEP < 0.486 for artificial neural networks (ANNs), respectively. Therefore, a combination of both an EIS-based technique and ANN models is suggested as a promising alternative to the traditional laboratory techniques for monitoring the pineapple waste saccharification step.

Glyphosate detection by means of a voltammetric electronic tongue and discrimination of potential interferents.

A new electronic tongue to monitor the presence of glyphosate (a non-selective systemic herbicide) has been developed. It is based on pulse voltammetry and consists in an array of three working electrodes (Pt, Co and Cu) encapsulated on a methacrylate cylinder. The electrochemical response of the sensing array was characteristic of the presence of glyphosate in buffered water (phosphate buffer 0.1 mol · dm-3, pH 6.7). Rotating disc electrode (RDE) studies were carried out with Pt, Co and Cu electrodes in water at room temperature and at pH 6.7 using 0.1 mol · dm-3 of phosphate as a buffer. In the presence of glyphosate, the corrosion current of the Cu and Co electrodes increased significantly, probably due to the formation of Cu2+ or Co2+ complexes. The pulse array waveform for the voltammetric tongue was designed by taking into account some of the redox processes observed in the electrochemical studies. The PCA statistical analysis required four dimensions to explain 95% of variance. Moreover, a two-dimensional representation of the two principal components differentiated the water mixtures containing glyphosate. Furthermore, the PLS statistical analyses allowed the creation of a model to correlate the electrochemical response of the electrodes with glyphosate concentrations, even in the presence of potential interferents such as humic acids and Ca2+. The system offers a PLS prediction model for glyphosate detection with values of 098, -2.3 × 10-5 and 0.94 for the slope, the intercept and the regression coefficient, respectively, which is in agreement with the good fit between the predicted and measured concentrations. The results suggest the feasibility of this system to help develop electronic tongues for glyphosate detection.