A novel methodology for vessel extraction from retinal fundus image and detection of neovascularization
- PDF / 5,467,721 Bytes
- 18 Pages / 439.642 x 666.49 pts Page_size
- 117 Downloads / 188 Views
A novel methodology for vessel extraction from retinal fundus image and detection of neovascularization Sayan Das1
· Nilanjana Dutta Roy2 · Arindam Biswas3 · Sanjoy Kumar Saha1
Received: 6 April 2020 / Revised: 11 August 2020 / Accepted: 16 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Vessel extraction from the retinal fundus images plays a significant role in ophthalmologic disease diagnosis. Proliferative Diabetic Retinopathy (PDR) is the ultimate stage of Diabetic Retinopathy where proliferation of new and fragile blood vessels grow in human retina. These new blood vessels often show a tendency to rupture which further leads to severe damage of human eye. Neovascularization at the disk (NVD) and elsewhere (NVE) are the two general categories of PDR. So, disease diagnosis at the early stage by detecting the newly generated thin vessels demands utmost importance. Literature witness that most of the existing works emphasised on detecting only NVD. The goal of this work is to detect NVD along with NVE, as both the stages are equally devastating. The disease detection requires the extraction of vessels for subsequent analysis. A novel vessel extraction methodology has been proposed here which is capable of extracting the thick and thin vessels for further analysis. The experimental results have been tested and verified with two publicly available datasets of retinal fundus images, DRIVE and STARE. Finally, experiment for NVD and NVE detection has been carried out with DIARET-DB1 data-set. Comparison of performance with some other state-of-the-works shows superiority of the proposed methodology. Keywords Retinal fundus images · Blood vessel segmentation · NVD and NVE detection
1 Introduction Blood vessels are the predominant and most stable structures appearing in the retina [11]. Automatic blood vessel extraction from retinal fundus images is essential for the diagnosis Sayan Das
[email protected] 1
Department of Computer Science and Engineering, Jadavpur University, Kolkata, West Bengal, India
2
Department of Computer Science and Engineering, Institute of Engineering & Management, Kolkata, West Bengal, India
3
Department of Information Technology, Indian Institute of Engineering Science & Technology, Shibpur, Howrah, India
Multimedia Tools and Applications
of several ophthalmic diseases. Features like change in diameter of retinal blood vessels, branching angles of the vessels, play as important diagnostic indicator of various disorders like Glaucoma [13, 33, 35], Diabetic Retinopathy [21, 23, 38] and Hypertension [36, 51]. Abnormal narrowing of retinal blood vessels indicates the early stages of Glaucoma. Diabetic Retinopathy is a common disease for patients suffering from diabetes for a long time. Severity level of it sometimes may extend to the formation of tiny and fragile blood vessels which are abnormal in nature. Hence, it is necessary to segment the vessels from the retinal fundus image to gather useful information regarding these diseases.
Data Loading...
