Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems
Computer-Aided Systems can assist differentiation and classification of breast benign and malignant lesions enhanced the performance of breast cancer diagnosis. Breast lesions are strongly correlated with their shape: benign lesions present regular shape, although malignant lesions tend to present i...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Escola Superior de Tecnologia da Saúde de Lisboa
2015-12-01
|
Series: | Saúde & Tecnologia |
Subjects: | |
Online Access: | https://web.estesl.ipl.pt/ojs/index.php/ST/article/view/984 |
id |
doaj-a4c9dbd85864410cac23f888fa53217a |
---|---|
record_format |
Article |
spelling |
doaj-a4c9dbd85864410cac23f888fa53217a2020-11-25T00:55:42ZengEscola Superior de Tecnologia da Saúde de LisboaSaúde & Tecnologia1646-97042015-12-01011283310.25758/s&t.v0i11.984994Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systemsAna Catarina Perre0Luís Freire1Clínica ECO4-Ultrasonografia Diagnóstica em Benedita; Área Científica de Radiologia, Escola Superior de Saúde Dr. Lopes Dias, Instituto Politécnico de Castelo BrancoÁrea Científica de Física, Escola Superior de Tecnologia da Saúde de Lisboa, Instituto Politécnico de LisboaComputer-Aided Systems can assist differentiation and classification of breast benign and malignant lesions enhanced the performance of breast cancer diagnosis. Breast lesions are strongly correlated with their shape: benign lesions present regular shape, although malignant lesions tend to present irregular shape. Therefore, the use of quantitative measures, such as fractal dimension (FD), can help characterizing the smoothness or the roughness of lesion shape. The main purpose of this work is to assess if the concomitant use of FD measure (contour FD) with a proposed FD measure (area FD) can improve the classification of lesions according to the BIRADS (Breast Imaging Reporting and Data System) scale and lesion type. Both FD measures were calculated through the box-counting method, directly from manually segmented lesions, and after applying a region growing/erosion algorithm. The last FD measure is based on the normalized difference between the FD measures before and after application of region growing/erosion algorithm. Results indicate that the contour FD is a useful measure in the differentiation of lesions according to the BIRADS scale and type, although, in some situations, errors occur. The combined use of contour FD with the four proposed FD measures can improve the classification of lesions.https://web.estesl.ipl.pt/ojs/index.php/ST/article/view/984mamografia, CAD, dimensão fractal, cancro de mama |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ana Catarina Perre Luís Freire |
spellingShingle |
Ana Catarina Perre Luís Freire Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems Saúde & Tecnologia mamografia, CAD, dimensão fractal, cancro de mama |
author_facet |
Ana Catarina Perre Luís Freire |
author_sort |
Ana Catarina Perre |
title |
Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems |
title_short |
Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems |
title_full |
Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems |
title_fullStr |
Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems |
title_full_unstemmed |
Assessment of mammographic lesions characterization with CAD (Computer-Aided Diagnosis) systems |
title_sort |
assessment of mammographic lesions characterization with cad (computer-aided diagnosis) systems |
publisher |
Escola Superior de Tecnologia da Saúde de Lisboa |
series |
Saúde & Tecnologia |
issn |
1646-9704 |
publishDate |
2015-12-01 |
description |
Computer-Aided Systems can assist differentiation and classification of
breast benign and malignant lesions enhanced the performance of breast cancer diagnosis. Breast lesions are strongly correlated with their shape: benign lesions present regular shape, although malignant lesions tend to present irregular shape. Therefore, the use of quantitative measures, such as fractal dimension (FD), can help characterizing the smoothness or the roughness of lesion shape. The main purpose of this work is to assess if the concomitant use of FD measure (contour FD) with a proposed FD measure (area FD) can improve the classification of lesions according to the BIRADS (Breast Imaging Reporting and Data System) scale and lesion type. Both FD measures were calculated through the
box-counting method, directly from manually segmented lesions, and after applying a region growing/erosion algorithm. The last FD measure is based on the normalized difference between the FD measures before and after application of region growing/erosion algorithm. Results indicate that the contour FD is a useful measure in the differentiation of
lesions according to the BIRADS scale and type, although, in some situations, errors occur. The combined use of contour FD with the four proposed FD measures can improve the classification of lesions. |
topic |
mamografia, CAD, dimensão fractal, cancro de mama |
url |
https://web.estesl.ipl.pt/ojs/index.php/ST/article/view/984 |
work_keys_str_mv |
AT anacatarinaperre assessmentofmammographiclesionscharacterizationwithcadcomputeraideddiagnosissystems AT luisfreire assessmentofmammographiclesionscharacterizationwithcadcomputeraideddiagnosissystems |
_version_ |
1725229846873767936 |