Characterization of border structure using Fractal Dimension in melanomas
There are many characteristics that differentiate normal moles (nevi) from melanomas. One of them is their boundary irregularity, which can be quantified using Fractal Dimension. In this work, fractal dimension of normal moles and melanoma was computed using the box counting method. These measuremen...
Guardado en:
Publicado: |
2010
|
---|---|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814244_v_n_p4088_Carbonetto http://hdl.handle.net/20.500.12110/paper_97814244_v_n_p4088_Carbonetto |
Aporte de: |
id |
paper:paper_97814244_v_n_p4088_Carbonetto |
---|---|
record_format |
dspace |
spelling |
paper:paper_97814244_v_n_p4088_Carbonetto2023-06-08T16:37:23Z Characterization of border structure using Fractal Dimension in melanomas Automatic Detection Boundary irregularities Box-counting method Medicine Partial discharges Fractal dimension article fractal analysis human melanoma pathology skin tumor Fractals Humans Melanoma Skin Neoplasms There are many characteristics that differentiate normal moles (nevi) from melanomas. One of them is their boundary irregularity, which can be quantified using Fractal Dimension. In this work, fractal dimension of normal moles and melanoma was computed using the box counting method. These measurements were used to train a linear decoder in order to predict the pathology. The average performance to discriminate normal moles from melanomas reached 85% giving some insights about the power of the fractal dimension as a candidate for automatic detection and diagnosis. © 2010 IEEE. 2010 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814244_v_n_p4088_Carbonetto http://hdl.handle.net/20.500.12110/paper_97814244_v_n_p4088_Carbonetto |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
Automatic Detection Boundary irregularities Box-counting method Medicine Partial discharges Fractal dimension article fractal analysis human melanoma pathology skin tumor Fractals Humans Melanoma Skin Neoplasms |
spellingShingle |
Automatic Detection Boundary irregularities Box-counting method Medicine Partial discharges Fractal dimension article fractal analysis human melanoma pathology skin tumor Fractals Humans Melanoma Skin Neoplasms Characterization of border structure using Fractal Dimension in melanomas |
topic_facet |
Automatic Detection Boundary irregularities Box-counting method Medicine Partial discharges Fractal dimension article fractal analysis human melanoma pathology skin tumor Fractals Humans Melanoma Skin Neoplasms |
description |
There are many characteristics that differentiate normal moles (nevi) from melanomas. One of them is their boundary irregularity, which can be quantified using Fractal Dimension. In this work, fractal dimension of normal moles and melanoma was computed using the box counting method. These measurements were used to train a linear decoder in order to predict the pathology. The average performance to discriminate normal moles from melanomas reached 85% giving some insights about the power of the fractal dimension as a candidate for automatic detection and diagnosis. © 2010 IEEE. |
title |
Characterization of border structure using Fractal Dimension in melanomas |
title_short |
Characterization of border structure using Fractal Dimension in melanomas |
title_full |
Characterization of border structure using Fractal Dimension in melanomas |
title_fullStr |
Characterization of border structure using Fractal Dimension in melanomas |
title_full_unstemmed |
Characterization of border structure using Fractal Dimension in melanomas |
title_sort |
characterization of border structure using fractal dimension in melanomas |
publishDate |
2010 |
url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814244_v_n_p4088_Carbonetto http://hdl.handle.net/20.500.12110/paper_97814244_v_n_p4088_Carbonetto |
_version_ |
1768543920597237760 |