Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets
Glaucoma detection is an important task, as this disease can affect the optic nerve, and this could lead to blindness. This can be prevented with early diagnosis, periodic controls, and treatment so that it can be stopped and prevent visual loss. Usually, the detection of glaucoma is carried out thr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/18/2237 |
| _version_ | 1829092012648824832 |
|---|---|
| author | José E. Valdez-Rodríguez Edgardo M. Felipe-Riverón Hiram Calvo |
| author_facet | José E. Valdez-Rodríguez Edgardo M. Felipe-Riverón Hiram Calvo |
| author_sort | José E. Valdez-Rodríguez |
| collection | DOAJ |
| description | Glaucoma detection is an important task, as this disease can affect the optic nerve, and this could lead to blindness. This can be prevented with early diagnosis, periodic controls, and treatment so that it can be stopped and prevent visual loss. Usually, the detection of glaucoma is carried out through various examinations such as tonometry, gonioscopy, pachymetry, etc. In this work, we carry out this detection by using images obtained through retinal cameras, in which we can observe the state of the optic nerve. This work addresses an accurate diagnostic methodology based on Convolutional Neural Networks (CNNs) to classify these optical images. Most works require a large number of images to train their CNN architectures, and most of them use the whole image to perform the classification. We will use a small dataset containing 366 examples to train the proposed CNN architecture and we will only focus on the analysis of the optic disc by extracting it from the full image, as this is the element that provides the most information about glaucoma. We experiment with different RGB channels and their combinations from the optic disc, and additionally, we extract depth information. We obtain accuracy values of 0.945, by using the GB and the full RGB combination, and 0.934 for the grayscale transformation. Depth information did not help, as it limited the best accuracy value to 0.934. |
| first_indexed | 2024-03-10T07:28:23Z |
| format | Article |
| id | doaj.art-cedced8055644641bd34b4723a64c8a0 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T07:28:23Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-cedced8055644641bd34b4723a64c8a02023-11-22T14:05:21ZengMDPI AGMathematics2227-73902021-09-01918223710.3390/math9182237Optic Disc Preprocessing for Reliable Glaucoma Detection in Small DatasetsJosé E. Valdez-Rodríguez0Edgardo M. Felipe-Riverón1Hiram Calvo2Centro de Investigación en Computación, Instituto Politécnico Nacional, Mexico City 07738, MexicoCentro de Investigación en Computación, Instituto Politécnico Nacional, Mexico City 07738, MexicoCentro de Investigación en Computación, Instituto Politécnico Nacional, Mexico City 07738, MexicoGlaucoma detection is an important task, as this disease can affect the optic nerve, and this could lead to blindness. This can be prevented with early diagnosis, periodic controls, and treatment so that it can be stopped and prevent visual loss. Usually, the detection of glaucoma is carried out through various examinations such as tonometry, gonioscopy, pachymetry, etc. In this work, we carry out this detection by using images obtained through retinal cameras, in which we can observe the state of the optic nerve. This work addresses an accurate diagnostic methodology based on Convolutional Neural Networks (CNNs) to classify these optical images. Most works require a large number of images to train their CNN architectures, and most of them use the whole image to perform the classification. We will use a small dataset containing 366 examples to train the proposed CNN architecture and we will only focus on the analysis of the optic disc by extracting it from the full image, as this is the element that provides the most information about glaucoma. We experiment with different RGB channels and their combinations from the optic disc, and additionally, we extract depth information. We obtain accuracy values of 0.945, by using the GB and the full RGB combination, and 0.934 for the grayscale transformation. Depth information did not help, as it limited the best accuracy value to 0.934.https://www.mdpi.com/2227-7390/9/18/2237glaucomaconvolutional neural networksmedical-diagnosis methodoptic disc |
| spellingShingle | José E. Valdez-Rodríguez Edgardo M. Felipe-Riverón Hiram Calvo Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets Mathematics glaucoma convolutional neural networks medical-diagnosis method optic disc |
| title | Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets |
| title_full | Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets |
| title_fullStr | Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets |
| title_full_unstemmed | Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets |
| title_short | Optic Disc Preprocessing for Reliable Glaucoma Detection in Small Datasets |
| title_sort | optic disc preprocessing for reliable glaucoma detection in small datasets |
| topic | glaucoma convolutional neural networks medical-diagnosis method optic disc |
| url | https://www.mdpi.com/2227-7390/9/18/2237 |
| work_keys_str_mv | AT joseevaldezrodriguez opticdiscpreprocessingforreliableglaucomadetectioninsmalldatasets AT edgardomfeliperiveron opticdiscpreprocessingforreliableglaucomadetectioninsmalldatasets AT hiramcalvo opticdiscpreprocessingforreliableglaucomadetectioninsmalldatasets |