Digital fundus image quality assessment
Diabetic retinopathy (DR) is a disease caused by complications of diabetes. It starts asymptomatically and can end in blindness. To detect it, doctors use special fundus cameras that allow them to register images of the retina in the visible range of the spectrum. On these images one can see feature...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Belarusian National Technical University
2022-01-01
|
| Series: | Sistemnyj Analiz i Prikladnaâ Informatika |
| Subjects: | |
| Online Access: | https://sapi.bntu.by/jour/article/view/535 |
| _version_ | 1797873691640463360 |
|---|---|
| author | V. V. Starovoitov Y. I. Golub M. M. Lukashevich |
| author_facet | V. V. Starovoitov Y. I. Golub M. M. Lukashevich |
| author_sort | V. V. Starovoitov |
| collection | DOAJ |
| description | Diabetic retinopathy (DR) is a disease caused by complications of diabetes. It starts asymptomatically and can end in blindness. To detect it, doctors use special fundus cameras that allow them to register images of the retina in the visible range of the spectrum. On these images one can see features, which determine the presence of DR and its grade. Researchers around the world are developing systems for the automated analysis of fundus images. At present, the level of accuracy of classification of diseases caused by DR by systems based on machine learning is comparable to the level of qualified medical doctors.The article shows variants for representation of the retina in digital images by different cameras. We define the task to develop a universal approach for the image quality assessment of a retinal image obtained by an arbitrary fundus camera. It is solved in the first block of any automated retinal image analysis system. The quality assessment procedure is carried out in several stages. At the first stage, it is necessary to perform binarization of the original image and build a retinal mask. Such a mask is individual for each image, even among the images recorded by one camera. For this, a new universal retinal image binarization algorithm is proposed. By analyzing result of the binarization, it is possible to identify and remove imagesoutliers, which show not the retina, but other objects. Further, the problem of no-reference image quality assessment is solved and images are classified into two classes: satisfactory and unsatisfactory for analysis. Contrast, sharpness and possibility of segmentation of the vascular system on the retinal image are evaluated step by step. It is shown that the problem of no-reference image quality assessment of an arbitrary fundus image can be solved.Experiments were performed on a variety of images from the available retinal image databases. |
| first_indexed | 2024-04-10T01:19:09Z |
| format | Article |
| id | doaj.art-04d132d686234d5f8d83c3e9d09a8f21 |
| institution | Directory Open Access Journal |
| issn | 2309-4923 2414-0481 |
| language | English |
| last_indexed | 2024-04-10T01:19:09Z |
| publishDate | 2022-01-01 |
| publisher | Belarusian National Technical University |
| record_format | Article |
| series | Sistemnyj Analiz i Prikladnaâ Informatika |
| spelling | doaj.art-04d132d686234d5f8d83c3e9d09a8f212023-03-13T09:47:42ZengBelarusian National Technical UniversitySistemnyj Analiz i Prikladnaâ Informatika2309-49232414-04812022-01-0104253810.21122/2309-4923-2021-4-25-38401Digital fundus image quality assessmentV. V. Starovoitov0Y. I. Golub1M. M. Lukashevich2Объединенный институт проблем информатики Национальной академии наук БеларусиОбъединенный институт проблем информатики Национальной академии наук БеларусиБелорусский государственный университет информатики и радиоэлектроникиDiabetic retinopathy (DR) is a disease caused by complications of diabetes. It starts asymptomatically and can end in blindness. To detect it, doctors use special fundus cameras that allow them to register images of the retina in the visible range of the spectrum. On these images one can see features, which determine the presence of DR and its grade. Researchers around the world are developing systems for the automated analysis of fundus images. At present, the level of accuracy of classification of diseases caused by DR by systems based on machine learning is comparable to the level of qualified medical doctors.The article shows variants for representation of the retina in digital images by different cameras. We define the task to develop a universal approach for the image quality assessment of a retinal image obtained by an arbitrary fundus camera. It is solved in the first block of any automated retinal image analysis system. The quality assessment procedure is carried out in several stages. At the first stage, it is necessary to perform binarization of the original image and build a retinal mask. Such a mask is individual for each image, even among the images recorded by one camera. For this, a new universal retinal image binarization algorithm is proposed. By analyzing result of the binarization, it is possible to identify and remove imagesoutliers, which show not the retina, but other objects. Further, the problem of no-reference image quality assessment is solved and images are classified into two classes: satisfactory and unsatisfactory for analysis. Contrast, sharpness and possibility of segmentation of the vascular system on the retinal image are evaluated step by step. It is shown that the problem of no-reference image quality assessment of an arbitrary fundus image can be solved.Experiments were performed on a variety of images from the available retinal image databases.https://sapi.bntu.by/jour/article/view/535диабетическая ретинопатиясетчаткацифровое изображениеоценка качества изображенийраспределение вейбулла |
| spellingShingle | V. V. Starovoitov Y. I. Golub M. M. Lukashevich Digital fundus image quality assessment Sistemnyj Analiz i Prikladnaâ Informatika диабетическая ретинопатия сетчатка цифровое изображение оценка качества изображений распределение вейбулла |
| title | Digital fundus image quality assessment |
| title_full | Digital fundus image quality assessment |
| title_fullStr | Digital fundus image quality assessment |
| title_full_unstemmed | Digital fundus image quality assessment |
| title_short | Digital fundus image quality assessment |
| title_sort | digital fundus image quality assessment |
| topic | диабетическая ретинопатия сетчатка цифровое изображение оценка качества изображений распределение вейбулла |
| url | https://sapi.bntu.by/jour/article/view/535 |
| work_keys_str_mv | AT vvstarovoitov digitalfundusimagequalityassessment AT yigolub digitalfundusimagequalityassessment AT mmlukashevich digitalfundusimagequalityassessment |