Abstract: Tear film unstable is one of the major features of dry eye syndrome. One diagnostic method is fluorescein tear film break-up time test, this test is limited by its subjective and necessity to use manually reading the fluorescent image to identify the break-up area and thus variable result. The previously study use a deep convolution neural network to perform an automatic method to detect the fluorescent tear film break-up detection. However, the method is complex and required a lots of computer power. In this study we use a real time data segmentation method You only look once (YOLO) to screen the tear film break up pattern in real time mater. We demonstrate that YOLO is effective method and comparatively fast for recognition and localization in fluorescent tear film break up test. Experimental verification proves their high detection ability, location precision and real time processing speed using modern graphics processing unit.

• Publication Date: 21-Jul-2019
• DOI: 10.15224/978-1-63248-172-6-02
• Views: 0
• Downloads: 0

Abstract: In modern medical field detecting nipping is done manually by ophthalmologists to detect hypertension of a patient. This is mainly done by the doctor using a gonioscope or by examines a fundus image of the patient. This proceeding may takes extensive amount of time and when the ophthalmologist has large number of patients to examine, this can be frustrating. In this review I discuss how this process can be automated under the supervision of an expert so that when the ophthalmologist receives the fundus image of a patient, he will get data of that patient that if he has hypertension symptoms in his fundus or not. With an assisting tool like this the efficiency of a typical fundus examine process can be increased in an exponential rate. A system like this will also open more and more ways to other approaches regarding same methods and technologies.

• Publication Date: 21-Jul-2019
• DOI: 10.15224/978-1-63248-172-6-03
• Views: 0
• Downloads: 0