Abstract
Retinal microaneurysm (MA) is the initial symptom of diabetic retinopathy (DR). The automatic detection of MA is helpful to assist doctors in diagnosis and treatment. Previous algorithms focused on the features of the target itself; however, the local structural features of the target and background are also worth exploring. To achieve MA detection, an efficient local structure awareness-based retinal MA detection with the multi-feature combination (LSAMFC) is proposed in this paper. We propose a novel local structure feature called a ring gradient descriptor (RGD) to describe the structural differences between an object and its surrounding area. Then, a combination of RGD with the salience and texture features is used by a Gradient Boosting Decision Tree (GBDT) for candidate classification. We evaluate our algorithm on two public datasets, i.e., the e-ophtha MA dataset and retinopathy online challenge (ROC) dataset. The experimental results show that the performance of the trained model significantly improved after combining traditional features with RGD, and the area under the receiver operating characteristic curve (AUC) values in the test results of the datasets e-ophtha MA and ROC increased from 0.9615 to 0.9751 and from 0.9066 to 0.9409, respectively.
Highlights
The number of diabetes patients worldwide is gradually increasing and, with the progression of diabetes, patients may develop diabetic retinopathy (DR), which may eventually cause vision loss or even blindness [1]
MA is the initial symptom of DR, and the early identification and timely treatment of retinal MA can prevent further progression of DR
Color fundus images are the primary way ophthalmologists assess retinal lesions, they judge whether the retina is normal and the grade of DR by visually observing whether there are microaneurysms, hard exudations, soft exudations, hemorrhages, and neovessels in the color fundus images [2]
Summary
The number of diabetes patients worldwide is gradually increasing and, with the progression of diabetes, patients may develop DR, which may eventually cause vision loss or even blindness [1]. MA is the initial symptom of DR, and the early identification and timely treatment of retinal MA can prevent further progression of DR. It is of great medical significance to realize the automatic detection of MA and assist doctors in the diagnosis of retinal lesions through computer technology. Color fundus images are the primary way ophthalmologists assess retinal lesions, they judge whether the retina is normal and the grade of DR by visually observing whether there are microaneurysms, hard exudations, soft exudations, hemorrhages, and neovessels in the color fundus images [2]. Due to factors, such as the environment and equipment, color fundus images often have different brightness, contrast, and color. Artificial detection of MA is time-consuming, with low accuracy, and leads to ophthalmologist fatigue. Many researchers have studied the automatic detection of MA
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
