ResearchSpace

The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection

Show simple item record

dc.contributor.author Afolabi, OJ
dc.contributor.author Mabuza-Hocquet, Gugulethu P
dc.contributor.author Nelwamondo, Fulufhelo V
dc.contributor.author Paul, BS
dc.date.accessioned 2021-07-13T17:11:57Z
dc.date.available 2021-07-13T17:11:57Z
dc.date.issued 2021-03
dc.identifier.citation Afolabi, O., Mabuza-Hocquet, G.P., Nelwamondo, F.V. & Paul, B. 2021. The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection. <i>IEEE Access, 9.</i> http://hdl.handle.net/10204/12048 en_ZA
dc.identifier.issn 2169-3536
dc.identifier.uri DOI: 10.1109/ACCESS.2021.3068204
dc.identifier.uri http://hdl.handle.net/10204/12048
dc.description.abstract Glaucoma has been credited to be the foremost cause of preventable loss of sight in the world second only to cataract. Its effect on the eye is usually irreversible and can only be prevented by early detection. In this paper, we developed a glaucoma detection technique. This technique includes a modified U-Net model called ‘U-Net lite’ and an extreme gradient boost (XGB) algorithm. The novel U-Net lite model is designed to have fewer parameters than the original U-Net model. The U-Net lite’s parameters are 40 times fewer than the original U-Net model which makes the proposed model faster and cheaper to train. The proposed model is utilized to segment both the optic cup and the optic disc from the fundus images. The extreme gradient boost algorithm is utilized to analyze extracted features from segmented optic cups and discs and hence detect glaucoma. The proposed U-Net lite model was both trained and tested on the DRIONS, DRISHTI-GS, RIM-ONE V2 and the RIM-ONE V3 databases. When tested for optic disc segmentation on the four databases, the model achieved the following average dice-scores: 0.96 on RIM-ONE V3, 0.97 on RIM-ONE V2, 0.96 on DRIONS, and 0.97 on DRISHTI-GS. The XGB algorithm achieved an accuracy of 88.6% and an AUC-ROC of 93.6 % in detecting glaucoma from the RIM-ONE V3 and DRISHTI-GS database. The proposed glaucoma detection technique achieves a state-of-the-art accuracy and is useful for observing structural changes in an optic cup and optic disc. en_US
dc.format Fulltext en_US
dc.language.iso en en_US
dc.relation.uri https://ieeexplore.ieee.org/document/9383215 en_US
dc.source IEEE Access, 9 en_US
dc.subject Fundus image en_US
dc.subject Glaucoma en_US
dc.subject Segmentation en_US
dc.subject U-Net en_US
dc.subject Extreme Gradient Boost en_US
dc.subject XGB en_US
dc.title The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection en_US
dc.type Article en_US
dc.description.pages 47411-47424 en_US
dc.description.note This work is licensed under a Creative Commons Attribution 4.0 License en_US
dc.description.cluster Defence and Security en_US
dc.description.cluster Next Generation Enterprises & Institutions
dc.description.impactarea Optronic Sensor Systems en_US
dc.description.impactarea Directorate
dc.identifier.apacitation Afolabi, O., Mabuza-Hocquet, G. P., Nelwamondo, F. V., & Paul, B. (2021). The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection. <i>IEEE Access, 9</i>, http://hdl.handle.net/10204/12048 en_ZA
dc.identifier.chicagocitation Afolabi, OJ, Gugulethu P Mabuza-Hocquet, Fulufhelo V Nelwamondo, and BS Paul "The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection." <i>IEEE Access, 9</i> (2021) http://hdl.handle.net/10204/12048 en_ZA
dc.identifier.vancouvercitation Afolabi O, Mabuza-Hocquet GP, Nelwamondo FV, Paul B. The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection. IEEE Access, 9. 2021; http://hdl.handle.net/10204/12048. en_ZA
dc.identifier.ris TY - Article AU - Afolabi, OJ AU - Mabuza-Hocquet, Gugulethu P AU - Nelwamondo, Fulufhelo V AU - Paul, BS AB - Glaucoma has been credited to be the foremost cause of preventable loss of sight in the world second only to cataract. Its effect on the eye is usually irreversible and can only be prevented by early detection. In this paper, we developed a glaucoma detection technique. This technique includes a modified U-Net model called ‘U-Net lite’ and an extreme gradient boost (XGB) algorithm. The novel U-Net lite model is designed to have fewer parameters than the original U-Net model. The U-Net lite’s parameters are 40 times fewer than the original U-Net model which makes the proposed model faster and cheaper to train. The proposed model is utilized to segment both the optic cup and the optic disc from the fundus images. The extreme gradient boost algorithm is utilized to analyze extracted features from segmented optic cups and discs and hence detect glaucoma. The proposed U-Net lite model was both trained and tested on the DRIONS, DRISHTI-GS, RIM-ONE V2 and the RIM-ONE V3 databases. When tested for optic disc segmentation on the four databases, the model achieved the following average dice-scores: 0.96 on RIM-ONE V3, 0.97 on RIM-ONE V2, 0.96 on DRIONS, and 0.97 on DRISHTI-GS. The XGB algorithm achieved an accuracy of 88.6% and an AUC-ROC of 93.6 % in detecting glaucoma from the RIM-ONE V3 and DRISHTI-GS database. The proposed glaucoma detection technique achieves a state-of-the-art accuracy and is useful for observing structural changes in an optic cup and optic disc. DA - 2021-03 DB - ResearchSpace DP - CSIR J1 - IEEE Access, 9 KW - Fundus image KW - Glaucoma KW - Segmentation KW - U-Net KW - Extreme Gradient Boost KW - XGB LK - https://researchspace.csir.co.za PY - 2021 SM - 2169-3536 T1 - The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection TI - The use of U-Net lite and Extreme Gradient Boost (XGB) for glaucoma detection UR - http://hdl.handle.net/10204/12048 ER - en_ZA
dc.identifier.worklist 24664 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record