An approach to edge detection in medical imaging through histogram analysis and morphological gradient
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Universidad del Valle
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876481945533153280 |
|---|---|
| author | Carlos V. Niño-Rondón |
| author_facet | Carlos V. Niño-Rondón |
| contents | An approach to edge detection in medical imaging through histogram analysis and morphological gradient Carlos V. Niño-Rondón Diego A. Castellano-Carvajal Sergio A. Castro-Casadiego Byron Medina-Delgado Dinael Guevara-Ibarra Ingeniería mammography edge detection Image processing computerized tomography Computer aided diagnosis Edge detection takes importance in image processing systems for computer-aided diagnosis, where sharp changes in pixel intensity are analyzed to obtain fast and accurate information about regions of interest to the specialist. A method for feature enhancement and edge detection in medical images was developed using image processing by analyzing the pixel distribution histogram and morphological gradient operation. Images from the MINI MIAS dataset and the COVID-CT dataset were used. The method is based on image processing and is applied to mammography and chest CT images, where blur filtering steps are accompanied by morphological gradient filtering, in addition to obtaining the threshold for edge detection by analyzing the point of maximum pixel concentration according to the distribution histogram. The processing is presented in a graphical user interface developed in Python language. The method is validated by comparison with other edge detection techniques such as the Canny Algorithm, and with deep learning methods such as Holistically-Nested Edge Detection. The proposed method improves image quality in both mammograms and CT scans compared to other techniques. It also presents the best performance considering internal and external edge detection, as well as an average response time of 1.054 seconds and 2.63 % of Central Processing Unit requirement. The developed system is presented as a support tool for use in computer-aided diagnosis processes due to its high efficiency in edge detection. 2022 artículo científico 0123-3033 https://www.redalyc.org/articulo.oa?id=291374362005 https://www.redalyc.org/journal/2913/291374362005/ https://www.redalyc.org/journal/2913/291374362005/html/ https://www.redalyc.org/journal/2913/291374362005/291374362005.epub https://www.redalyc.org/journal/2913/291374362005/movil 10.25100/iyc.v24i2.11352 en http://www.redalyc.org/revista.oa?id=2913 Ingeniería y Competitividad application/pdf Universidad del Valle Ingeniería y Competitividad (Colombia) Num.2 Vol.24 |
| format | Artículo científico |
| id | redalyc_291374362005 |
| institution | Redalyc |
| language | en |
| publishDate | 2022 |
| publisher | Universidad del Valle |
| spellingShingle | An approach to edge detection in medical imaging through histogram analysis and morphological gradient Carlos V. Niño-Rondón Ingeniería mammography edge detection Image processing computerized tomography Computer aided diagnosis An approach to edge detection in medical imaging through histogram analysis and morphological gradient Carlos V. Niño-Rondón Diego A. Castellano-Carvajal Sergio A. Castro-Casadiego Byron Medina-Delgado Dinael Guevara-Ibarra Ingeniería mammography edge detection Image processing computerized tomography Computer aided diagnosis Edge detection takes importance in image processing systems for computer-aided diagnosis, where sharp changes in pixel intensity are analyzed to obtain fast and accurate information about regions of interest to the specialist. A method for feature enhancement and edge detection in medical images was developed using image processing by analyzing the pixel distribution histogram and morphological gradient operation. Images from the MINI MIAS dataset and the COVID-CT dataset were used. The method is based on image processing and is applied to mammography and chest CT images, where blur filtering steps are accompanied by morphological gradient filtering, in addition to obtaining the threshold for edge detection by analyzing the point of maximum pixel concentration according to the distribution histogram. The processing is presented in a graphical user interface developed in Python language. The method is validated by comparison with other edge detection techniques such as the Canny Algorithm, and with deep learning methods such as Holistically-Nested Edge Detection. The proposed method improves image quality in both mammograms and CT scans compared to other techniques. It also presents the best performance considering internal and external edge detection, as well as an average response time of 1.054 seconds and 2.63 % of Central Processing Unit requirement. The developed system is presented as a support tool for use in computer-aided diagnosis processes due to its high efficiency in edge detection. 2022 artículo científico 0123-3033 https://www.redalyc.org/articulo.oa?id=291374362005 https://www.redalyc.org/journal/2913/291374362005/ https://www.redalyc.org/journal/2913/291374362005/html/ https://www.redalyc.org/journal/2913/291374362005/291374362005.epub https://www.redalyc.org/journal/2913/291374362005/movil 10.25100/iyc.v24i2.11352 en http://www.redalyc.org/revista.oa?id=2913 Ingeniería y Competitividad application/pdf Universidad del Valle Ingeniería y Competitividad (Colombia) Num.2 Vol.24 |
| title | An approach to edge detection in medical imaging through histogram analysis and morphological gradient |
| topic | Ingeniería mammography edge detection Image processing computerized tomography Computer aided diagnosis |
| url | https://www.redalyc.org/articulo.oa?id=291374362005 https://www.redalyc.org/journal/2913/291374362005/ https://www.redalyc.org/journal/2913/291374362005/html/ https://www.redalyc.org/journal/2913/291374362005/291374362005.epub https://www.redalyc.org/journal/2913/291374362005/movil |