Automatic Detection of Microaneurysms in OCT Images Using Bag of Features

Overview

Journal Comput Math Methods Med

Publisher Hindawi

Specialty Medical Informatics

Date 2024 Sep 16

PMID 39279986

Authors

Elahe Sadat Kazeminasab

Ramin Almasi

Bijan Shoushtarian

Ehsan Golkar

Hossein Rabbani

Affiliations

Soon will be listed here.

Abstract

Diabetic retinopathy (DR) caused by diabetes occurs as a result of changes in the retinal vessels and causes visual impairment. Microaneurysms (MAs) are the early clinical signs of DR, whose timely diagnosis can help detecting DR in the early stages of its development. It has been observed that MAs are more common in the inner retinal layers compared to the outer retinal layers in eyes suffering from DR. Optical coherence tomography (OCT) is a noninvasive imaging technique that provides a cross-sectional view of the retina, and it has been used in recent years to diagnose many eye diseases. As a result, this paper attempts to identify areas with MA from normal areas of the retina using OCT images. This work is done using the dataset collected from FA and OCT images of 20 patients with DR. In this regard, firstly fluorescein angiography (FA) and OCT images were registered. Then, the MA and normal areas were separated, and the features of each of these areas were extracted using the Bag of Features (BOF) approach with the Speeded-Up Robust Feature (SURF) descriptor. Finally, the classification process was performed using a multilayer perceptron network. For each of the criteria of accuracy, sensitivity, specificity, and precision, the obtained results were 96.33%, 97.33%, 95.4%, and 95.28%, respectively. Utilizing OCT images to detect MAs automatically is a new idea, and the results obtained as preliminary research in this field are promising.

References

Mateen M, Safdar Malik T, Hayat S, Hameed M, Sun S, Wen J . Deep Learning Approach for Automatic Microaneurysms Detection. Sensors (Basel). 2022; 22(2). PMC: 8781897. DOI: 10.3390/s22020542. View

Eftekhari N, Pourreza H, Masoudi M, Ghiasi-Shirazi K, Saeedi E . Microaneurysm detection in fundus images using a two-step convolutional neural network. Biomed Eng Online. 2019; 18(1):67. PMC: 6542103. DOI: 10.1186/s12938-019-0675-9. View

Cheng S, Leng T . Noninvasive detection of microaneurysms in diabetic retinopathy by swept-source optical coherence tomography. Clin Ophthalmol. 2016; 10:1791-1795. PMC: 5033498. DOI: 10.2147/OPTH.S115016. View

Govindarajan S, Swaminathan R . Analysis of Tuberculosis in Chest Radiographs for Computerized Diagnosis using Bag of Keypoint Features. J Med Syst. 2019; 43(4):87. DOI: 10.1007/s10916-019-1222-8. View

Rosas-Romero R, Martinez-Carballido J, Hernandez-Capistran J, Uribe-Valencia L . A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images. Comput Med Imaging Graph. 2015; 44:41-53. DOI: 10.1016/j.compmedimag.2015.07.001. View

Alsaih K, Lemaitre G, Rastgoo M, Massich J, Sidibe D, Meriaudeau F . Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images. Biomed Eng Online. 2017; 16(1):68. PMC: 5463338. DOI: 10.1186/s12938-017-0352-9. View

Bhimavarapu U, Battineni G . Automatic Microaneurysms Detection for Early Diagnosis of Diabetic Retinopathy Using Improved Discrete Particle Swarm Optimization. J Pers Med. 2022; 12(2). PMC: 8878235. DOI: 10.3390/jpm12020317. View

Wang H, Chhablani J, Freeman W, Chan C, Kozak I, Bartsch D . Characterization of diabetic microaneurysms by simultaneous fluorescein angiography and spectral-domain optical coherence tomography. Am J Ophthalmol. 2012; 153(5):861-867.e1. PMC: 3331899. DOI: 10.1016/j.ajo.2011.10.005. View

Schwartz D, Fingler J, Kim D, Zawadzki R, Morse L, Park S . Phase-variance optical coherence tomography: a technique for noninvasive angiography. Ophthalmology. 2013; 121(1):180-187. PMC: 4190463. DOI: 10.1016/j.ophtha.2013.09.002. View

10.

Spencer T, Olson J, McHardy K, Sharp P, Forrester J . An image-processing strategy for the segmentation and quantification of microaneurysms in fluorescein angiograms of the ocular fundus. Comput Biomed Res. 1996; 29(4):284-302. DOI: 10.1006/cbmr.1996.0021. View

11.

de Carlo T, Romano A, Waheed N, Duker J . A review of optical coherence tomography angiography (OCTA). Int J Retina Vitreous. 2016; 1:5. PMC: 5066513. DOI: 10.1186/s40942-015-0005-8. View

12.

Marmor M, Ravin J . Fluorescein angiography: insight and serendipity a half century ago. Arch Ophthalmol. 2011; 129(7):943-8. DOI: 10.1001/archophthalmol.2011.160. View

13.

Yamada Y, Suzuma K, Fujikawa A, Kumagami T, Kitaoka T . Imaging of laser-photocoagulated diabetic microaneurysm with spectral domain optical coherence tomography. Retina. 2013; 33(4):726-31. DOI: 10.1097/IAE.0b013e3182753960. View

14.

Parravano M, De Geronimo D, Scarinci F, Querques L, Virgili G, Simonett J . Diabetic Microaneurysms Internal Reflectivity on Spectral-Domain Optical Coherence Tomography and Optical Coherence Tomography Angiography Detection. Am J Ophthalmol. 2017; 179:90-96. DOI: 10.1016/j.ajo.2017.04.021. View

15.

Jeba Derwin D, Priestly Shan B, Jeba Singh O . Hybrid multi-kernel SVM algorithm for detection of microaneurysm in color fundus images. Med Biol Eng Comput. 2022; 60(5):1377-1390. DOI: 10.1007/s11517-022-02534-y. View

16.

Kohner E, Stratton I, Aldington S, Turner R, Matthews D . Microaneurysms in the development of diabetic retinopathy (UKPDS 42). UK Prospective Diabetes Study Group. Diabetologia. 1999; 42(9):1107-12. DOI: 10.1007/s001250051278. View

17.

Rabbani H, Allingham M, Mettu P, Cousins S, Farsiu S . Fully automatic segmentation of fluorescein leakage in subjects with diabetic macular edema. Invest Ophthalmol Vis Sci. 2015; 56(3):1482-92. PMC: 4347309. DOI: 10.1167/iovs.14-15457. View

18.

Cree M, Olson J, McHardy K, Sharp P, Forrester J . A fully automated comparative microaneurysm digital detection system. Eye (Lond). 1997; 11 ( Pt 5):622-8. DOI: 10.1038/eye.1997.166. View

19.

Wang Z, Li X, Yao M, Li J, Jiang Q, Yan B . A new detection model of microaneurysms based on improved FC-DenseNet. Sci Rep. 2022; 12(1):950. PMC: 8770497. DOI: 10.1038/s41598-021-04750-2. View

20.

Pereira C, Veiga D, Mahdjoub J, Guessoum Z, Goncalves L, Ferreira M . Using a multi-agent system approach for microaneurysm detection in fundus images. Artif Intell Med. 2014; 60(3):179-88. DOI: 10.1016/j.artmed.2013.12.005. View