A. Mendez Zorrilla

Melanomas non-invasive diagnosis application based on the ABCD rule and pattern recognition image processing algorithms

In this paper an automated dermatological tool for the parameterization of melanomas is presented. The system is based on the standard ABCD Rule and dermatological Pattern Recognition protocols. On the one hand, a complete stack of algorithms for the asymmetry, border, color, and diameter parameterization were developed. On the other hand, three automatic algorithms for digital image processing have been developed in order to detect the appropriate patterns. These allow one to calculate certain quantitative features based on the aspect and inner patterns of the melanoma using simple-operation algorithms, in order to minimize response time. The database used consists of 160 500 x 500-pixel RGB images (20 images per pattern) cataloged by dermatologists, and the results have turned out to be successful according to assessment by medical experts. While the ABCD algorithms are mathematically reliable, the proposed algorithms for pattern recognition produced a remarkable rate of globular, reticular, and blue veil Pattern recognition, with an average above 85% of accuracy. It thus proves to be a reliable system when performing a diagnosis.

A serious game to improve human relationships in patients with neuro-psychological disorders

The project described in this paper consists of designing and implementing a multimedia application within the framework of Serious Games. The main aim is to analyze the behavior and to promote certain social skills (conversation, negotiation…) of people with Neurological development Disabilities. The treatment has been planned at three levels. Each level treats a characteristic related to socialization, integration and the expression of feelings. For this purpose, various scenarios have been described (the city, the school and the home) and the user has to pass the test related to social situations. To interact and play this game, people (children and teenagers in this approach) use the Wiimote, chosen due to its simplicity and usability. The results produced by the game have been saved in a database to be analyzed by the instructors at a later date. Not only technological results have been analyzed, but the opinions of users and specialists taking part in the applications validation and piloting have also been taken into account.

Autism Spectrum Disorder children interaction skills measurement using computer games

This paper describes a work in progress focused on establishing an adapted serious game which is used to evaluate the social competences in children with Autism Spectrum Disorder (ASD) between 5 and 8 years old. This type of children has difficulties to interact with other people. Objective measurements obtained by the eye tracker and the serious game demonstrate the differences between ASD children and control children in eye fixation time, or the reaction time, among others. The use of serious games therapy is an attractive option to improve skills and measure the evolution in children with ASD.

Helping children with Intellectual Disability to understand healthy eating habits with an IPad based serious game

The Project described by means of this article consists on the design and implementation of an application within the field of the serious games. A game aimed at instilling healthy eating habits to children/adolescents with ID. For the accomplishment of this project some multi-touch platforms (IPad) were used, given the good reception by people with ID towards the use of new technologies. The application is based on a set of games with different functionalities and aims, which include a piece of advices for the eating process. Furthermore, a pet has been designed with the aim of making the application more attractive in the interest of motivation. The results obtained after the tests carried out with real users were positive and encouraging. The users felt confortable when using the application and some improvements were applied base don the feedback provided by professional instructors and by the children themselves.

Skin cancer parameterisation algorithm based on epiluminiscence image processing

In this paper a digital system for enhancing the diagnosis of skin cancer is presented. The algorithm is based on the standard ABCD dermatologic protocol, and on the measurements of contours and surfaces of some specific areas into the mole image captured by epiluminiscence techniques. Automatic algorithms of digital image processing have been developed in order to detect the appropriate segmentation of the images of suspected moles. This allows one to calculate some quantitative features based on the external contour using the Isodata Algorithm. In addition, other features are found based on the internal contours segmented using color heterogeneity criteria. These small internal moles help the diagnosis of the skin cancer to extract information about propagation and irregularities. The database used consists of 65 images already catalogued by dermatologists and the results are successful according to the assessment of medical experts.

Dyslexia diagnosis in reading stage though the use of games at school

Proposed paper presents the design and development of a set of games intended for the diagnosis of dyslexia in children at the reading stage. Dyslexia is a problem for reading and writing and high rates of academic failure are associated with it if it is not diagnosed and treated correctly. The system proposed here intends to improve and facilitate the task of diagnosis by implementing traditional tests in a set of games, so that the child loses the notion of being under evaluation. Moreover, this platform provides specialists with specific objective information that enables them to produce a correct diagnosis, as well as allowing them to check the childrens progress after undergoing therapy.

Vocal folds paralysis study using a pre-processing stage of Gabor filtering and Chan-Vese segmentation

This paper describes the methodology proposed by the authors to diagnose vocal folds paralysis automatically using vocal folds stroboscopic images. Previously, a segmentation stage is necessary to obtain correctly and quickly the glottal space from healthy and pathological vocal folds video sequences captured by the laryngoscope. The designed segmentation method combines Gabor filtering and Chan-Vese algorithm. To evaluate the quality of the segmentation algorithms some parameters have been measured: the segmentation of the region of interest, the frames incorrectly segmented (in %) and the number of iterations used by the designed algorithm (in %). This study is specifically focused on measuring the opening angles in healthy and vocal folds with paralysis. This kind of parameters help the specialist to express a diagnosis based on something more robust than the observation of medical images. It shows a great advance in design, and in the nearby future, a complete method to diagnose vocal folds pathologies.

Corrective algorithm for esophageal voice cycle detection

In this paper a corrective solution for more accurate esophageal voice cycle marks detection is presented. While the algorithm developed in a previous work adapts the MDVP voice period marks to esophageal voice, it shows lacks when analyzing unsteady |a| vowel samples and with high levels of noise. The proposed solution is aimed to iteratively correct the parameters (n min and threshold) used in the previous algorithm. The corrective system filters the noise of voice recordings and then uses the output of the previous algorithm to calculate the most reliable fundamental frequency, based on the most stable part of the given signal. The results were acquired by comparing the pitch values of the previous algorithm with and without the proposed solution and the calculating the error against the real value. The corrective solution presents a considerable improvement in the accuracy of the voice cycle detection algorithm by reducing the standard deviation of the error dataset from 4.591 to 0.593 and the mean error value from 2.459 down to 0.370. Furthermore, it reduces up to a 54% all errors above 1%.

Pathological vocal folds diagnosis using modified active contour models

This paper presents the study of vocal videostroboscopic videos to detect morphological pathologies using an active contour segmentation and objective measurements. The ad-hoc designed active contour algorithm permits to obtain a robust and fast segmentation using vocal folds images in RGB format. In this work, we have employed connected component analysis as a post-processing tool. After the segmentation process the image is analyzed and the pathology can be localized automatically and we can extract some features of each fold (such as the size of the polyp or cyst, the glottal space, the position…).

Kalman filter predictions applied to glottal closure instant detection

Given the importance of the voice in our daily lives, any study focused on its pathologies and the way of detecting and treating them nimbly is of common interest. This research work focuses on the search for an image processing solution to help otolaryngologist to detect glottal closure instant by using Kalman filters based on stroboscopic videos. This solution will allow to prevent the irregularities in the images and the subsequent measuring errors, caused by different pathologies, both organic and functional. The results show that the prediction of the Kalman filter aids in the motion detection, but, above all, at the point at which very rough transitions are produced in the measurements, that is to say, when the glottal closure instant is produced. The results are encrypted and embedded into a digital image using an invisible watermarking technique (LSB) in order to ensure the privacy, confidentiality and integrity of the results when they are transmitted.