Computer-Aided Glaucoma Diagnosis Using Stochastic Watershed Transformation on Single Fundus Images
Uloženo v:
| Název: | Computer-Aided Glaucoma Diagnosis Using Stochastic Watershed Transformation on Single Fundus Images |
|---|---|
| Autoři: | Díaz-Pinto, Andrés Yesid, Morales, Sandra, Naranjo Ornedo, Valeriana, Navea, Amparo |
| Přispěvatelé: | Escuela Técnica Superior de Ingeniería de Telecomunicación, Departamento de Matemática Aplicada, Departamento de Comunicaciones, Escuela Técnica Superior de Ingeniería Aeroespacial y Diseño Industrial, Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Nvidia, Generalitat Valenciana, European Commission, Repositorio Institucional de la Universitat Politècnica de València Riunet, Producción Científica UCH 2019, UCH. Departamento de Medicina y Cirugía |
| Zdroj: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia Universitat Politècnica de València (UPV) instname CEU Repositorio Institucional Fundación Universitaria San Pablo CEU (FUSPCEU) Journal of Medical Imaging and Health Informatics |
| Informace o vydavateli: | American Scientific Publishers, 2019. |
| Rok vydání: | 2019 |
| Témata: | Ojos - Enfermedades - Diagnóstico - Modelos matemáticos, Fundus Images, Glaucoma - Diagnosis - Mathematical models, Stochastic Watershed, TEORIA DE LA SEÑAL Y COMUNICACIONES, Glaucoma - Diagnóstico - Modelos matemáticos, Glaucoma, Eye - Diseases - Diagnosis - Mathematical models, CDR, ISNT rule, 3. Good health |
| Popis: | Glaucoma is a chronic eye disease and one of the major causes of permanent blindness. Since it does not show initial symptoms, early diagnosis is important to limit its progression. This paper presents an automatic optic nerve characterization algorithm for glaucoma diagnosis based only on retinal fundus images. For optic cup segmentation, we used a new method based on the stochastic watershed transformation applied on the YIQ colour space to extract clinical indicators such as the Cup/Disc ratio, the area Cup/Disc ratio and the ISNT rule. Afterwards, an assessment between normal and glaucomatous fundus images is performed. The proposed algorithm was evaluated on 6 different (private and public) databases containing 723 images (377 normal and 346 glaucomatous images) which achieved a specificity and sensitivity of 0.674 and 0.675, respectively. Moreover, an F-score of 0.770 was obtained when evaluating this method on the publicly available database Drishti-GS1. A comparison of the proposed work with other state-of-the-art methods demonstrates the robustness of the proposed algorithm; because it was tested using images from different databases with high variability, which is a common issue in this area. Additional comparisons with existing works for cup segmentation, that use the publicly available database Drishti-GS1, are also presented in this paper. |
| Druh dokumentu: | Article |
| Popis souboru: | application/pdf |
| Jazyk: | English |
| ISSN: | 2156-7018 |
| DOI: | 10.1166/jmihi.2019.2721 |
| DOI: | 10.13039/501100000780 |
| DOI: | 10.13039/501100003359 |
| Přístupová URL adresa: | https://repositorioinstitucional.ceu.es/bitstream/10637/11659/1/Computer-aided_Diaz_JMIHI_2019.pdf https://riunet.upv.es/handle/10251/126176 http://doi.org/10.1166/jmihi.2019.2721 https://riunet.upv.es/handle/10251/126176 https://www.ingentaconnect.com/content/asp/jmihi/2019/00000009/00000006/art00001 https://repositorioinstitucional.ceu.es/handle/10637/11659 https://dblp.uni-trier.de/db/journals/jmihi/jmihi9.html#Diaz-PintoMNN19 https://repositorioinstitucional.ceu.es/bitstream/10637/11659/1/Computer-aided_Diaz_JMIHI_2019.pdf https://hdl.handle.net/10251/126176 https://doi.org/10.1166/jmihi.2019.2721 |
| Rights: | CC BY NC ND URL: http://rightsstatements.org/vocab/InC/1.0/ |
| Přístupové číslo: | edsair.doi.dedup.....e2109ccc0d5f576c9032cd2b4765b060 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Glaucoma is a chronic eye disease and one of the major causes of permanent blindness. Since it does not show initial symptoms, early diagnosis is important to limit its progression. This paper presents an automatic optic nerve characterization algorithm for glaucoma diagnosis based only on retinal fundus images. For optic cup segmentation, we used a new method based on the stochastic watershed transformation applied on the YIQ colour space to extract clinical indicators such as the Cup/Disc ratio, the area Cup/Disc ratio and the ISNT rule. Afterwards, an assessment between normal and glaucomatous fundus images is performed. The proposed algorithm was evaluated on 6 different (private and public) databases containing 723 images (377 normal and 346 glaucomatous images) which achieved a specificity and sensitivity of 0.674 and 0.675, respectively. Moreover, an F-score of 0.770 was obtained when evaluating this method on the publicly available database Drishti-GS1. A comparison of the proposed work with other state-of-the-art methods demonstrates the robustness of the proposed algorithm; because it was tested using images from different databases with high variability, which is a common issue in this area. Additional comparisons with existing works for cup segmentation, that use the publicly available database Drishti-GS1, are also presented in this paper. |
|---|---|
| ISSN: | 21567018 |
| DOI: | 10.1166/jmihi.2019.2721 |