Teaching the Virtual Brain.

As a complex three-dimensional organ, the inside of a human brain is difficult to properly visualize. Magnetic Resonance Imaging provides an accurate model of the brain of a patient, but its medical or educational analysis as a set of flat slices is not enough to fully grasp its internal structure. A virtual reality application has been developed to generate a complete three-dimensional model based on MRI data, which users can explore internally through random planar cuts and color cluster isolation. An indexed vertex triangulation algorithm has been designed to efficiently display large amounts of complex three-dimensional vertex clusters in simple mobile devices. Feedback from students suggests that the resulting application satisfactorily complements theoretical lectures, as virtual reality allows them to better observe different structures within the human brain.

Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: A machine learning approach within a 7-year prospective multi-center study.

OBJECTIVE: To analyze the performance of adenosine deaminase in pleural fluid combined with other parameters routinely measured in clinical practice and assisted by machine learning algorithms for the diagnosis of pleural tuberculosis in a low prevalence setting, and secondly, to identify effusions that are non-tuberculous and most likely malignant. PATIENTS AND METHODS: We prospectively analyzed 230 consecutive patients diagnosed with lymphocytic exudative pleural effusion from March 2013 to June 2020. Diagnosis according to the composite reference standard was achieved in all cases. Pre-test probability of pleural tuberculosis was 3.8% throughout the study period. Parameters included were: levels of adenosine deaminase, pH, glucose, proteins, and lactate dehydrogenase, red and white cell counts and lymphocyte percentage in pleural fluid, as well as age. We tested six different machine learning-based classifiers to categorize the patients. Two different classifications were performed: a) tuberculous/non-tuberculous and b) tuberculous/malignant/other. RESULTS: Out of a total of 230 patients with pleural effusion included in the study, 124 were diagnosed with malignant effusion and 44 with pleural tuberculosis, while 62 were given other diagnoses. In the tuberculous/non-tuberculous classification, and taking into account the validation predictions, the support vector machine yielded the best result: an AUC of 0.98, accuracy of 97%, sensitivity of 91%, and specificity of 98%, whilst in the tuberculous/malignant/other classification, this type of classifier yielded an overall accuracy of 80%. With this three-class classifier, the same sensitivity and specificity was achieved in the tuberculous/other classification, but it also allowed the correct classification of 90% of malignant cases. CONCLUSION: The level of adenosine deaminase in pleural fluid together with cell count, other routine biochemical parameters and age, combined with a machine-learning approach, is suitable for the diagnosis of pleural tuberculosis in a low prevalence scenario. Secondly, non-tuberculous effusions that are suspected to be malignant may also be identified with adequate accuracy.

Machine learning based method for the evaluation of the Analgesia Nociception Index in the assessment of general anesthesia.

Measuring the level of analgesia to adapt the opioids infusion during anesthesia to the real needs of the patient is still a challenge. This is a consequence of the absence of a specific measure capable of quantifying the nociception level of the patients. Unlike existing proposals, this paper aims to evaluate the suitability of the Analgesia Nociception Index (ANI) as a guidance variable to replicate the decisions made by the experts when a modification of the opioid infusion rate is required. To this end, different machine learning classifiers were trained with several sets of clinical features. Data for training were captured from 17 patients undergoing cholecystectomy surgery. Satisfactory results were obtained when including information about minimum values of ANI for predicting a change of dose. Specifically, a higher efficiency of the Support Vector Machine (SVM) classifier was observed compared with the situation in which the ANI index was not included: accuracy: 86.21% (83.62%-87.93%), precision: 86.11% (83.78%-88.57%), recall: 91.18% (88.24%-91.18%), specificity: 79.17% (75%-83.33%), AUC: 0.89 (0.87-0.90) and kappa index: 0.71 (0.66-0.75). The results of this research evidenced that including information about the minimum values of ANI together with the hemodynamic information outperformed the decisions made regarding only non-specific traditional signs such as heart rate and blood pressure. In addition, the analysis of the results showed that including the ANI monitor in the decision making process may anticipate a dose change to prevent hemodynamic events. Finally, the SVM was able to perform accurate predictions when making different decisions commonly observed in the clinical practice.

Improving Odometric Accuracy for an Autonomous Electric Cart.

In this paper, a study of the odometric system for the autonomous cart Verdino, which is an electric vehicle based on a golf cart, is presented. A mathematical model of the odometric system is derived from cart movement equations, and is used to compute the vehicle position and orientation. The inputs of the system are the odometry encoders, and the model uses the wheels diameter and distance between wheels as parameters. With this model, a least square minimization is made in order to get the nominal best parameters. This model is updated, including a real time wheel diameter measurement improving the accuracy of the results. A neural network model is used in order to learn the odometric model from data. Tests are made using this neural network in several configurations and the results are compared to the mathematical model, showing that the neural network can outperform the first proposed model.

Contrast based circular approximation for accurate and robust optic disc segmentation in retinal images.

A new method for automatic optic disc localization and segmentation is presented. The localization procedure combines vascular and brightness information to provide the best estimate of the optic disc center which is the starting point for the segmentation algorithm. A detection rate of 99.58% and 100% was achieved for the Messidor and ONHSD databases, respectively. A simple circular approximation to the optic disc boundary is proposed based on the maximum average contrast between the inner and outer ring of a circle centered on the estimated location. An average overlap coefficient of 0.890 and 0.865 was achieved for the same datasets, outperforming other state of the art methods. The results obtained confirm the advantages of using a simple circular model under non-ideal conditions as opposed to more complex deformable models.

Fusion of a variable baseline system and a range finder.

One of the greatest difficulties in stereo vision is the appearance of ambiguities when matching similar points from different images. In this article we analyze the effectiveness of using a fusion of multiple baselines and a range finder from a theoretical point of view, focusing on the results of using both prismatic and rotational articulations for baseline generation, and offer a practical case to prove its efficiency on an autonomous vehicle.

Asphalted road temperature variations due to wind turbine cast shadows.

The contribution of this paper is a technique that in certain circumstances allows one to avoid the removal of dynamic shadows in the visible spectrum making use of images in the infrared spectrum. This technique emerged from a real problem concerning the autonomous navigation of a vehicle in a wind farm. In this environment, the dynamic shadows cast by the wind turbines' blades make it necessary to include a shadows removal stage in the preprocessing of the visible spectrum images in order to avoid the shadows being misclassified as obstacles. In the thermal images, dynamic shadows completely disappear, something that does not always occur in the visible spectrum, even when the preprocessing is executed. Thus, a fusion on thermal and visible bands is performed.