João Paulo da Silva Cunha

MPEG-7 Visual Descriptors—Contributions for Automated Feature Extraction in Capsule Endoscopy

Recent advances in miniaturization led to the development of what is now called the endoscopic capsule. This small device is swallowed by a patient and films the whole gastrointestinal tract, allowing the detection of abnormalities. Currently, a doctor typically needs up to two hours to analyze a full exam, so automation is desirable. This paper presents a methodology for measuring the potential of selected visual MPEG-7 descriptors for the task of specific medical event detection such as blood, ulcers. Experiments show that the best results are obtained by the Scalable Color and Homogenous Texture descriptors, especially if only relevant coefficients are used.

Automated Topographic Segmentation and Transit Time Estimation in Endoscopic Capsule Exams

Endoscopic capsule is a recent medical technology with important clinical benefits but suffering from a practical handicap: long exam annotation times. This paper proposes and compares two approaches (Bayesian and support vector machines) that can be used to segment the gastrointestinal tract into its four major topographic areas, allowing the automatic estimation of the clinically relevant gastric and intestinal sections and corresponding transit times. According to medical specialists, this can reduce exam annotation times by up to 12% (15 min). This automatic tool has been integrated into our CapView annotation software that is currently being used by three medical institutions.

Movement quantification in epileptic seizures: a new approach to video-EEG analysis

It is common that epileptic seizures induce uncoordinated movement in a patients body. This movement is a relevant clinical factor in seizure identification. Nevertheless, quantification of this information has not been an object of much attention from the scientific community. In this paper, we present our effort in developing a new approach to the quantification of movement patterns in patients during epileptic seizures. We attach markers at landmark points of a patients body and use a camera and a commercial video-electroencephalogram (EEG) system to synchronously register EEG and video during seizures. Then, we apply image-processing techniques to analyze the video frames and extract the trajectories of those points that represent the course of the quantified movement of different body parts. This information may help clinicians in seizure classification. We describe the framework of our system and a method of analyzing video in order to achieve the proposed goal. Our experimental results show that our method can reflect quantified motion patterns of epileptic seizures, which cannot be accessed by means of traditional visual inspection of video recordings. We were able, for the first time, to quantify the movement of different parts of a convulsive human body in the course of an epileptic seizure. This result represents an enhanced value to clinicians in studying seizures for reaching a diagnosis.

Vital-Jacket ® : A wearable wireless vital signs monitor for patients' mobility in cardiology and sports

The Vital Jacket® (VJ) is a wearable vital signs monitoring system that joins textiles with microelectronics. After several years of development within the university lab, it has been licensed to a start-up company. Its evolutions have focused on cardiology and sports and scaled down from a jacket to a single T-shirt. The VJ manufacturing process has recently been certified to comply with the standards ISO9001 and ISO13485 and the cardiology version was approved as a Medical Device for the European market compliant with the MDD directive 42/93/CE, holding the CE1011 mark. The authors intend to wear VJs during the days of the congress to demonstrate its usefulness in first hand and will exemplify the different scenarios of use of this innovative wearable intelligent garment.

Lateralizing Significance of Quantitative Analysis of Head Movements before Secondary Generalization of Seizures of Patients with Temporal Lobe Epilepsy

Summary:  Purpose: To quantitatively evaluate the lateralizing significance of ictal head movements of patients with temporal lobe epilepsy (TLE).

On-Line Determination of Biomass in a Microalga Bioreactor Using a Novel Computerized Flow Injection Analysis System

A flow injection analysis (FIA) device has been developed, which is able to assay successfully for biomass in a microalga bioreactor. The device is fully computerized and is operated via diluting small aliquots of the culture followed by measuring optical density (OD); this figure is then accurately correlated with biomass, in terms of both cell number and ash‐free dry weight, during the entire culture time. Furthermore, the device is not expensive, is highly versatile, and is easy to operate owing to specifically developed, user‐friendly software. The growth rate and biomass productivity of Pavlova lutheri, cultivated under batch and semicontinuous modes, were monitored as experimental testing model.

Topographic Segmentation and Transit Time Estimation for Endoscopic Capsule Exams

The endoscopic capsule is a recent medical technology with important clinical benefits but suffering from a practical handicap: long exam annotation times. This paper shows how support vector machines can be used to segment the gastrointestinal tract into its four major topographic areas, allowing the automatic estimation of the clinically relevant gastric and intestinal transit times. According to medical specialists, this can reduce exam annotation times by up to 12%

Recent studies provide an updated clinical perspective on blue light-filtering IOLs

BackgroundRecent reviews of blue light-filtering intraocular lenses (IOLs) have stated their potential risks for scotopic vision and circadian photoentrainment. Some authors have challenged the rationale for retinal photoprotection that these IOLs might provide. Our objective is to address these issues by providing an updated clinical perspective based on the results of the most recent studies.MethodsThis article evaluates the currently available published papers assessing the potential risks and benefits of blue light-filtering IOLs. It summarizes the results of seven clinical and two computational studies on photoreception, and several studies related to retinal photoprotection, all of which were not available in the previous reviews. These results provide a clinical risk/benefit analysis for an updated review for these IOLs.ResultsMost clinical studies comparing IOLs with and without the blue light-filtering feature have found no difference in clinical performance for; visual acuity, contrast sensitivity, color vision, or glare. For blue light-filtering IOLs, three comparative clinical studies have shown improved contrast sensitivity and glare reduction; but one study, while it showed satisfactory overall color perception, demonstrated some compromise in mesopic comparative blue color discrimination. Comparative results of two recent clinical studies have also shown improved performance for simulated driving under glare conditions and reduced glare disability, better heterochromatic contrast threshold, and faster recovery from photostress for blue light-filtering IOLs. Two computational and five clinical studies found no difference in performance between IOLs with or without blue light-filtration for scotopic vision performance and photo entrainment of the circadian rhythm. The rationale for protection of the pseudophakic retina against phototoxicity is discussed with supporting results of the most recent computational, in-vitro, animal, clinical, and epidemiological investigations.ConclusionsThis analysis provides an updated clinical perspective which suggests the selection of blue light-filtering IOLs for patients of any age, but especially for pediatric and presbyopic lens exchange patients with a longer pseudophakic life. Without clinically substantiated potential risks, these patients should experience the benefit of overall better quality of vision, reduced glare disability at least in some conditions, and better protection against retinal phototoxicity and its associated potential risk for AMD.

What does an epileptiform spike look like in MEG? Comparison between coincident EEG and MEG spikes.

Recent investigations suggest that there are differences between the characteristics of EEG and MEG epileptiform spikes. The authors performed an objective characterization of the morphology of epileptiform spikes recorded simultaneously in both EEG and MEG to determine whether they present the same morphologic characteristics. Based on a stepwise approach, the authors performed a computer analysis of EEG and MEG of a set of coincident epileptiform transients selected by a senior clinical neurophysiologist in recordings of three patients with drug-resistant epilepsy. A computer-based algorithm was applied to extract parameters that could be used to describe quantitatively the morphology of the transients, followed by a statistical comparison over the extracted metrics of the EEG and MEG waveforms. EEG and MEG coincident events were statistically different with respect to several morphologic characteristics, such as duration, sharpness, and shape. The differences found appear to be a consequence of MEG signals not being influenced by volume propagation through the tissues with different conductivities that surround the brain, compared with EEG, and of the different orientation of the underlying dipolar sources. The results indicate that visual inspection of MEG spikes and automatic spike-detector algorithms should use criteria adapted to the specific characteristics of the MEG, and not simply those used on conventional EEG.

Connectivity patterns of pallidal DBS electrodes in focal dystonia: A diffusion tensor tractography study

Deep brain stimulation (DBS) of the internal pallidal segment (GPi: globus pallidus internus) is gold standard treatment for medically intractable dystonia, but detailed knowledge of mechanisms of action is still not available. There is evidence that stimulation of ventral and dorsal GPi produces opposite motor effects. The aim of this study was to analyse connectivity profiles of ventral and dorsal GPi. Probabilistic tractography was initiated from DBS electrode contacts in 8 patients with focal dystonia and connectivity patterns compared. We found a considerable difference in anterior-posterior distribution of fibres along the mesial cortical sensorimotor areas between the ventral and dorsal GPi connectivity. This finding of distinct GPi connectivity profiles further confirms the clinical evidence that the ventral and dorsal GPi belong to different functional and anatomic motor subsystems. Their involvement could play an important role in promoting clinical DBS effects in dystonia.