Renato da Veiga Guadagnin

Breast cancer image assessment using an adaptative network-based fuzzy inference system

In Brazil breast cancer is the foremost cause of fatality by cancer for women. Given that the causes are unidentified, it cannot be prevented. Mammography is one of the most reliable exams for breast cancer detection and it is based on image analysis by radiologists. Early detection is the key issue for breast cancer control and computer-aided diagnosis system can help ra diologists in detection and diagnosing breast abnormalities. Hybrid neuro-fuzzy systems are suitable for pattern recognition tasks and therefore useful for medical diagnosis support through pattern identification in mammographic images. This study presents an Adaptative Network-based Fuzzy Inference System (ANFIS) that classifies the mammographic images calcification region of interest as benign or malign and provides an important tool for breast cancer image assessment. The ANFIS model, utilized in the mammogram region of interest’s classification phase, reached a maximum accuracy rate of 99.75%.

An image mining based approach to detect pressure ulcer stage

Treatment of pressure ulcers (PU) is essentially image dependent, because its surface provides relevant visual information for medical procedures. There is an increasing interest to adapt Information Technology advances for a more effective medical image processing. Artificial Intelligence concerned techniques, say Image Mining, can be very helpful to manage large amount of PU images in order to increase productivity of health professionals and patients life quality. This paper proposes an Image Mining based system for automatic interpretation of tissue and color to support the treatment of patients with PU.

Mensuração de área de úlceras por pressão por meio dos softwares Motic e do AutoCAD

A ulcera por pressao e uma lesao parcial ou total das camadas da pele em determinadas regioes do corpo e seu processo de cicatrizacao pode ser acompanhado por meio de processamento de imagens. A analise da area da ulcera por pressao e relevante para avaliacao da sua evolucao e de sua resposta a procedimentos terapeuticos. Os softwares Motic e AutoCAD® permitem avaliar a area de regioes de uma imagem atraves da marcacao do seu contorno. Valendo-se dessa tecnica, 35 voluntarios determinaram as areas de duas ulceras por pressao grau III pelos dois tipos de software. Concluiu-se que eles apresentam resultados clinicamente concordantes e podem assim ser utilizados para acompanhamento da evolucao da cicatrizacao de ulceras por pressao.Pressure ulcer is a lesion that affects skin layers in some regions of the body and its healing can be followed up using image processing. The analysis of pressure ulcer area is relevant to evaluate its evolution and response to therapeutic procedures. Such areas can be evaluated through contour marking with the softwares Motic and AutoCAD®. In this study 35 volunteers computed areas from two grade III pressure ulcers using these instruments. It was possible to conclude that results are clinically equivalent and so can be considered to follow up healing evolution from pressure ulcers.

Improving image mining through Geoprocessing

Geoprocessing Information Systems (GIS) deal with structured information concerned some geographical localization. So one uses three-dimensional image representation systems in a huge database, where it is possible to insert many data about some interest domain, say, agriculture, economics, industry, demographics and so on. Images are powerful information sources that can soundly support decision making processes. An image can be seen as a set of elements with spatial localization and color. To interpret an image includes deriving clusters and relations between such elements. This article proposes an integration of Geoprocessing and Image Mining to support image based decisions in several domains such as healthcare.

Aferição não-invasiva de úlcera por pressão simulada em modelo plano

That is an quasi-experimental study that aims to improve and make portable an existing method for projecting light points to estimate geometrical properties of a cavity. A computer vision system was developed in order to process input images and calculate volume and depth of a cavity in a plain surface. An error of 1,51% for depth and -10,42% for volume occurred. So this is an adequate method for estimating geometrical properties of cavities with accuracy errors compatible with those errors described in the literature.Estudio casi-Afericao nao-invasiva de ulcera por pressao simulada em modelo planoexperimental, con el objetivo de perfeccionar el sistema de proyeccion de los puntos luminosos de un metodo ya existente, volviendolo portatil, y verificar la acuracia de ese nuevo sistema. El estudio realizado a traves del desarrollo de um sistema de fotografia digitalizada y procesada por la vision computacional en un modelo de superficie llana. Los resultados mostraron um error de 1,51% para la profundidad y de -10,42% para el volumen, concluyendo ser metodo adecuado para la evaluacion de los descriptos em la literatura.

MIDAS – Mammographic Image Database for Automated Analysis

Fabiano Fernandes1, Rodrigo Bonifacio2, Lourdes Brasil3, Renato Guadagnin4 and Janice Lamas5 1Instituto Federal de Brasilia, 2Computer Science Department, University of Brasilia, 3Post-Graduate Program in Biomedical Engineering, University of Brasilia at Gama 4Post-Graduate Program in Knowledge Management and Information Technology, Catholic University of Brasilia, 5Janice Lamas Radiology Clinic Brazil

Area evaluation using image processing tools: An applied study to pressure ulcer monitoring

Monitoring of pressure ulcer (PU) healing process is essentially based on image analysis. Geometrical, texture and color features enable decisions about therapeutic procedures to be adopted. A PU emerges when a soft tissue is compressed. Its area is a geometrical features that can be non4nvasively, through image processing, evaluated and is an important indicator of healing evolution. Softwares Motic and AutoCAD allow evaluating area from image regions through computational contour marking. Using this technique, areas from two grade III PUs were evaluated by 35 volunteers. A statistical comparison between them showed that they are equivalent for clinical purposes, allowing, therefore, an improved accompaniment of the evolution of the healing process of PUs.

Basic ideas to support pressure ulcers treatment by means of image mining

A Pressure ulcer (PU) occurs in a significant amount of patients that must remain in bed without movements for long periods. To improve its treatment in order to increase patient life quality and to reduce medical healthcare is yet a challenge. It seems to be helpful to search for medical decision making information in both PU images features and in data concerning patient life so far. Once suitably stored such information sets data and image mining procedures are supposed to be able to allow inferences and finding of patient clusters. Is seems to be also possible computationally to generate a PU grade inference that will help medical experts to accomplish therapeutic procedures. Current research efforts with such purposes are here presented.

Hyperspectral images classification based on KLT

We propose an approach, based on KLT—Karhunen-Loève Transform, in order to automatically classify hyperspectral images. We used an AVIRIS image with 224 bands taken from the surroundings of Alto Paraiso City, on Goias State, in the middle of Brazil. Our approach performs dimensionality reduction, using only the eigenvectors with the highest eigenvalues, generating an eigenspace of low dimension. We also consider the spectral signatures of each class we work with. The classification is done finding the shortest Euclidean distance among the primitives of the new images and the primitives of the classes. We built a thematic map with 4 different classes.

An approach to provide visual information to support skin wounds therapy

Availability of visual information means an effective way to improve specialized work in quite different areas. They enable reality modeling, a faster context analysis, a more successful search for problem solutions, an objective oriented decision making, as well as important elements for instructional processes. Avisual model is a simulation form that stimulate insights, say, creative answers to yet open questions and derivation of yet not imagined possible facts concerning a studied reality. Visual features of human body are highly relevant as basic information for a variety of decisions on activities in health domain. Through mechanisms of user-friendly interface one can promptly access and eventually perform adjustments. One can achieve better life quality and greater efficiency in health service from state as well. This paper describes an approach towards a visualization process of skin lesions, including features recognition for therapeutic processes and relevant decisions, with experimental validation.