Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2012
License: CC BY NC ND
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2013
License: CC BY NC ND
versions View all 2 versions
addClaim

Reconocimiento automático de melanomas mediante técnicas de visión por ordenador y reconocimiento de patrones

Authors: Asunción Batugo, Gertrudis Katerin;

Reconocimiento automático de melanomas mediante técnicas de visión por ordenador y reconocimiento de patrones

Abstract

El objetivo de este Proyecto Fin de Carrera consiste en clasificar cualquier lesión sospechosa de ser melanoma entre dos grupos. Un grupo correspondiente a las lesiones con cáncer de piel de tipo no melanoma, es decir, lesiones benignas y el otro grupo correspondiente a las lesiones con cáncer de piel de tipo melanoma, es decir, lesiones malignas. Para entender cómo se forman y detectan los melanomas y conocer el tratamiento necesario que se debe aplicar en caso de poseer melanomas, se presenta una breve introducción al melanoma. Dado lo importante que es detectar el melanoma a tiempo, en este proyecto se propone realizar la clasificación mediante métodos de visión por ordenador, es decir, gracias a imágenes digitales. Para ello, se capturan y digitalizan las lesiones gracias a un dermatoscopio manual, que al ser digital, permite añadir una cámara digital. Además, el software empleado para acondicionar y analizar las imágenes digitales capturadas es el software de Matlab. Este software permite crear un programa automático y sencillo que maneja las imágenes. Los principales pasos del programa desarrollado son: · El acondicionamiento y la segmentación (con preprocesado y postprocesado), que consisten en manipular la imagen matemáticamente, de forma que la lesión resulte separada de la piel sana. · La extracción de características, que consiste en determinar los parámetros a partir de la imagen de la lesión y de la segmentación de la misma, basándose en características que definen a los melanomas y que siguen la regla ABCD de la dermatoscopía (Asimetría, Borde, Color y Diferencias estructurales). · La clasificación de las lesiones, que consiste en determinar si una lesión es un melanoma o no, a partir de las características extraídas previamente. En este documento se mencionan numerosos métodos para realizar cada uno de los pasos anteriores. Pero se exponen y detallan: el método de captura, la digitalización, el acondicionamiento, la segmentación, la extracción de características y la clasificación escogidos para aplicarse en una serie de lesiones que forman nuestra base de datos y de los cuales obtenemos unos resultados que son mostrados y explicados al final de la memoria. Posteriormente, se exponen unas breves conclusiones y trabajos futuros y finalmente, se muestra el presupuesto que costaría llevar a cabo este proyecto. ______________________________________________________________________________________________________________________________ The aim of this Thesis or PhD is to classify any suspicious lesion between two groups. One of them corresponds to cancer lesions of non – melanoma skin, called benign pigmented lesions and the other group corresponds to lesions of skin cancer melanoma, called malignant melanomas or melanomas. In order to understand how melanomas are formed and detected, and also to know the treatment that is necessary to be applied in case of having melanomas, it is presented a brief introduction to melanoma. Detect an early melanoma is very important, so in this project, it is intended to make the classification by computer vision methods, i.e. by digital images. For this purpose, the lesions are captured and digitalized through a digital manual dermatoscope adding a digital camera. In addition, the software used to improve the conditions and to analyze the digital images is Matlab, because this software allows creating a simple automatic program that handles images. The main steps of the developed program are: · Conditioning and segmentation (with preprocessing and postprocessing), in these steps the program manipulate the image mathematically, so that the result is an image where lesion is separated from healthy skin. · The feature extraction, in this step the program determines parameters from the image and the segmentation of the lesion, based on characteristics that define melanomas. These characteristics are in the ABCD rule of dermatoscopy (Asymmetry, Border, Color and texture). · The classification of lesions, in this step it is determined whether a lesion is a melanoma or not, from the previously extracted features. This document mentions several methods for each of the above steps. But are presented and detailed: the method of capture, digitalization, conditioning, segmentation, feature extraction and classification chosen to apply in a set of lesions that are our database and they give us a results which are shown and explained at the end of the memory. Finally, it is presented some brief conclusions and future works and as a final point of this document, it is shown the budget that would cost to develop this project. Ingeniería Técnica en Electrónica

Country
Spain
Related Organizations
Keywords

Dermatoscopio, Electrónica, Proceso de imágenes, Visión por ordenador, Melanoma

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 36
    download downloads 78
  • 36
    views
    78
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
36
78
Green
Related to Research communities
Cancer Research