A proposal to measure the similarity between retinal vessel segmentations images
Introduction: We propose a novel approach for the assessment of the similarity of retinal vessel segmentation images that is based on linking the standard performance metrics of a segmentation algorithm, with the actual structural properties of the images through the fractal dimension. Method: We a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad De La Salle Bajío
2019-05-01
|
| Series: | Nova Scientia |
| Subjects: | |
| Online Access: | http://novascientia.delasalle.edu.mx/ojs/index.php/Nova/article/view/1872 |
| _version_ | 1818904783365341184 |
|---|---|
| author | Marco A. Escobar José R. Guzmán Sepúlveda Jorge R. Parra Michel Rafael Guzmán Cabrera |
| author_facet | Marco A. Escobar José R. Guzmán Sepúlveda Jorge R. Parra Michel Rafael Guzmán Cabrera |
| author_sort | Marco A. Escobar |
| collection | DOAJ |
| description | Introduction: We propose a novel approach for the assessment of the similarity of retinal vessel segmentation images that is based on linking the standard performance metrics of a segmentation algorithm, with the actual structural properties of the images through the fractal dimension.
Method: We apply our methodology to compare the vascularity extracted by automatic segmentation against manually segmented images.
Results: We demonstrate that the strong correlation between the standard metrics and fractal dimension is preserved regardless of the size of the subimages analyzed.
Discussion or Conclusion: We show that the fractal dimension is correlated to the segmentation algorithm’s performance and therefore it can be used as a comparison metric. |
| first_indexed | 2024-12-19T21:12:55Z |
| format | Article |
| id | doaj.art-c6bdae62817d4fb1b7faf36dae778a15 |
| institution | Directory Open Access Journal |
| issn | 2007-0705 |
| language | English |
| last_indexed | 2024-12-19T21:12:55Z |
| publishDate | 2019-05-01 |
| publisher | Universidad De La Salle Bajío |
| record_format | Article |
| series | Nova Scientia |
| spelling | doaj.art-c6bdae62817d4fb1b7faf36dae778a152022-12-21T20:05:27ZengUniversidad De La Salle BajíoNova Scientia2007-07052019-05-01112210.21640/ns.v11i22.1872A proposal to measure the similarity between retinal vessel segmentations imagesMarco A. Escobar0José R. Guzmán Sepúlveda1Jorge R. Parra Michel2Rafael Guzmán Cabrera3Universidad de la Salle BajioUniversity of Central FloridaUniversidad De La Salle BajíoUniversidad de GuanajuatoIntroduction: We propose a novel approach for the assessment of the similarity of retinal vessel segmentation images that is based on linking the standard performance metrics of a segmentation algorithm, with the actual structural properties of the images through the fractal dimension. Method: We apply our methodology to compare the vascularity extracted by automatic segmentation against manually segmented images. Results: We demonstrate that the strong correlation between the standard metrics and fractal dimension is preserved regardless of the size of the subimages analyzed. Discussion or Conclusion: We show that the fractal dimension is correlated to the segmentation algorithm’s performance and therefore it can be used as a comparison metric.http://novascientia.delasalle.edu.mx/ojs/index.php/Nova/article/view/1872image processingsegmentationfractal dimensionsimilarity measurementretinal vesselvascularity |
| spellingShingle | Marco A. Escobar José R. Guzmán Sepúlveda Jorge R. Parra Michel Rafael Guzmán Cabrera A proposal to measure the similarity between retinal vessel segmentations images Nova Scientia image processing segmentation fractal dimension similarity measurement retinal vessel vascularity |
| title | A proposal to measure the similarity between retinal vessel segmentations images |
| title_full | A proposal to measure the similarity between retinal vessel segmentations images |
| title_fullStr | A proposal to measure the similarity between retinal vessel segmentations images |
| title_full_unstemmed | A proposal to measure the similarity between retinal vessel segmentations images |
| title_short | A proposal to measure the similarity between retinal vessel segmentations images |
| title_sort | proposal to measure the similarity between retinal vessel segmentations images |
| topic | image processing segmentation fractal dimension similarity measurement retinal vessel vascularity |
| url | http://novascientia.delasalle.edu.mx/ojs/index.php/Nova/article/view/1872 |
| work_keys_str_mv | AT marcoaescobar aproposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT joserguzmansepulveda aproposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT jorgerparramichel aproposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT rafaelguzmancabrera aproposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT marcoaescobar proposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT joserguzmansepulveda proposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT jorgerparramichel proposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages AT rafaelguzmancabrera proposaltomeasurethesimilaritybetweenretinalvesselsegmentationsimages |