Upload Code
loading-left
loading loading loading
loading-right

Loading

Profile
No self-introduction
codes (2)
Retinal fundus image segmentation and measurement
no vote
Application background Diabetic retinopathy (DR) is one of the most important complications of diabetes mellitus, which causes serious damages in the retina, consequently visual loss and sometimes blindness if necessary medical treatment is not applied on time. One of the difficulties in this illness is that the patient with diabetes mellitus requires a continuous screening for early detection. So far, numerous methods have been proposed by researchers to automate the detection process of DR in retinal fundus images. In this paper, we developed an alternative simple approach to detect DR. This method was built on the inverse segmentation method, which we suggested before to detect Age Related Macular Degeneration (ARMDs).
10101136
2016-08-23
0
1
Retinal vascular ssegmentation based on level set
no vote
Application background Retina lvessels play an import an trole inthe diagnostic procedure o fretinopathy.Accurate segmentation of retinalvessels is crucial for pathological analysis.Inthispaper,weproposeanewretinalvessel segmentation methodbasedonlevelsetandregiongrowing.Firstly,aretinalvesselimageis preprocessedbythecontrast-limitedadaptivehistogramequalizationanda2DGaborwaveletto enhance thevessels.Then,ananisotropic diffusion filter is used to smooththeimageandpreservevessel boundaries. Finally,theregiongrowingmethodandaregion-basedactivecontourmodelwithlevelset implementation areappliedtoextractretinalvessels,andtheirresultsarecombinedtoachievethe final segmentation. ComparisonsareconductedonthepubliclyavailableDRIVEandSTAREdatabasesusing three differentmeasurements.Experimentalresultsshowthattheproposedmethodreachesanaverage accuracy of94.77%ontheDRIVEdatabaseand95.09%ontheSTAREdatabase.
10101136
2016-08-23
0
1
No more~