Joshua, AONelwamondo, Fulufhelo VMabuza-Hocquet, Gugulethu P2019-03-262019-03-262019-01Joshua, A.O., Nelwamondo, F.V. and Mabuza-Hocquet, G.P. 2019. Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images. 2019 Southern African Universities Power Engineering Conference, Central University of Technology, Free State Bloemfontein, South Africa, 28-30 January 2019, pp. 183-187978-1-7281-0369-3http://hdl.handle.net/10204/10856Due to copyright restrictions, the attached pdf contains the accepted version of the published paper. Please consult the publisher's website for access to the published version.Glaucoma has been attributed to be the leading cause of blindness in the world second only to diabetic retinopathy. About 66.8 million people in the world have glaucoma and about 6.7 million are suffering from blindness as a result of glaucoma. A cause of glaucoma is the enlargement of the optic cup such that it occupies the optic disc area. Hence, the estimation of optic Cup to Disc ratio (CDR) is a valuable tool in diagnosing glaucoma. The CDR can be obtained by segmenting the optic cup and optic disc from the fundus image. In this work, an improved U-net Convolutional Neural Network (CNN) architecture was used to segment the optic disc and the optic cup from the fundus image. The dataset used was obtained from the DRISHTI-GS database and the RIM-ONE v.3. The proposed pipeline and architecture outperforms existing techniques on Optic Disc (OD) and Optic Cup (OC) segmentation on the Dice-score metric and prediction time.enRetinal fundus imageGlaucomaOptic disc segmentationCup to disc ratioImage segmentationConference PresentationJoshua, A., Nelwamondo, F. V., & Mabuza-Hocquet, G. P. (2019). Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images. IEEE. http://hdl.handle.net/10204/10856Joshua, AO, Fulufhelo V Nelwamondo, and Gugulethu P Mabuza-Hocquet. "Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images." (2019): http://hdl.handle.net/10204/10856Joshua A, Nelwamondo FV, Mabuza-Hocquet GP, Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images; IEEE; 2019. http://hdl.handle.net/10204/10856 .TY - Conference Presentation AU - Joshua, AO AU - Nelwamondo, Fulufhelo V AU - Mabuza-Hocquet, Gugulethu P AB - Glaucoma has been attributed to be the leading cause of blindness in the world second only to diabetic retinopathy. About 66.8 million people in the world have glaucoma and about 6.7 million are suffering from blindness as a result of glaucoma. A cause of glaucoma is the enlargement of the optic cup such that it occupies the optic disc area. Hence, the estimation of optic Cup to Disc ratio (CDR) is a valuable tool in diagnosing glaucoma. The CDR can be obtained by segmenting the optic cup and optic disc from the fundus image. In this work, an improved U-net Convolutional Neural Network (CNN) architecture was used to segment the optic disc and the optic cup from the fundus image. The dataset used was obtained from the DRISHTI-GS database and the RIM-ONE v.3. The proposed pipeline and architecture outperforms existing techniques on Optic Disc (OD) and Optic Cup (OC) segmentation on the Dice-score metric and prediction time. DA - 2019-01 DB - ResearchSpace DP - CSIR KW - Retinal fundus image KW - Glaucoma KW - Optic disc segmentation KW - Cup to disc ratio KW - Image segmentation LK - https://researchspace.csir.co.za PY - 2019 SM - 978-1-7281-0369-3 T1 - Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images TI - Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images UR - http://hdl.handle.net/10204/10856 ER -