Kawther Taibouni1, Yasmina Chenoune2, Alexandra Miere3, Donato Colantuono4, Eric Souied5, Eric Petit6. 1. Université Paris-Est, LISSI (EA 3956), UPEC, F-94010, Vitry-sur-Seine, France. Electronic address: kawther.taibouni@univ-paris-est.fr. 2. ESME Sudria Research Lab, 40 rue du Docteur Roux, 75015, Paris, France; Université Paris-Est, LISSI (EA 3956), UPEC, F-94010, Vitry-sur-Seine, France. Electronic address: yasmina.chenoune@esme.fr. 3. Université Paris-Est, LISSI (EA 3956), UPEC, F-94010, Vitry-sur-Seine, France; Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, 40, Avenue de Verdun, 94000, Créteil, France. Electronic address: alexandramiere@gmail.com. 4. Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, 40, Avenue de Verdun, 94000, Créteil, France. Electronic address: colantuono.donato88@gmail.com. 5. Department of Ophthalmology, Centre Hospitalier Intercommunal de Créteil, 40, Avenue de Verdun, 94000, Créteil, France. Electronic address: esouied@hotmail.com. 6. Université Paris-Est, LISSI (EA 3956), UPEC, F-94010, Vitry-sur-Seine, France. Electronic address: petit@u-pec.fr.
Abstract
OBJECTIVES: To report the design of an automated quantification algorithm for choroidal neovascularization (CNV) in the context of neovascular age-related macular degeneration (AMD), based on Optical Coherence Tomography Angiography (OCTA) images. MATERIAL AND METHODS: In this study, 54 patients (mean age 75.80 ± 14.29 years) with neovascular AMD (type 1 and type 2 CNV) were included retrospectively and separated into two groups (Group 1-24 images; Group 2-30 images), according to the lesion topology. All patients underwent a 3 × 3 mm OCTA examination (AngioVue, Optovue, Freemont, California). The proposed algorithm is based on segmentation and enhancement methods including Frangi filter, Gabor wavelets and Fuzzy-C-Means Classification. Our results were compared to the manual quantifications given by the embedded quantification software "AngioAnalytics". RESULTS: Automated CNV segmentation and quantification of three neovascular AMD biomarkers: the total vascular area (TVA), the total area (TA) and the vascular density (VD) were possible in all cases. Automated versus manual quantification comparison revealed a statistically significant difference for TVA and VD measurements for both groups (p = 0.00036 for Group 1 TVA, p < 0.0001 for Group 1 VD and Group 2 TVA and VD). The difference in TA measurements was not significant in Group 2 (p = 0.143). Bland-Altman analysis revealed low inter-method bias for TA measurements and higher bias for TVA and VD. CONCLUSION: This paper presents a method for segmenting and quantifying CNV that constitutes a valid option for clinicians. Complementary validations have to be carried out to compare our method's accuracy to "AngioAnalytics".
OBJECTIVES: To report the design of an automated quantification algorithm for choroidal neovascularization (CNV) in the context of neovascular age-related macular degeneration (AMD), based on Optical Coherence Tomography Angiography (OCTA) images. MATERIAL AND METHODS: In this study, 54 patients (mean age 75.80 ± 14.29 years) with neovascular AMD (type 1 and type 2 CNV) were included retrospectively and separated into two groups (Group 1-24 images; Group 2-30 images), according to the lesion topology. All patients underwent a 3 × 3 mm OCTA examination (AngioVue, Optovue, Freemont, California). The proposed algorithm is based on segmentation and enhancement methods including Frangi filter, Gabor wavelets and Fuzzy-C-Means Classification. Our results were compared to the manual quantifications given by the embedded quantification software "AngioAnalytics". RESULTS: Automated CNV segmentation and quantification of three neovascular AMD biomarkers: the total vascular area (TVA), the total area (TA) and the vascular density (VD) were possible in all cases. Automated versus manual quantification comparison revealed a statistically significant difference for TVA and VD measurements for both groups (p = 0.00036 for Group 1 TVA, p < 0.0001 for Group 1 VD and Group 2 TVA and VD). The difference in TA measurements was not significant in Group 2 (p = 0.143). Bland-Altman analysis revealed low inter-method bias for TA measurements and higher bias for TVA and VD. CONCLUSION: This paper presents a method for segmenting and quantifying CNV that constitutes a valid option for clinicians. Complementary validations have to be carried out to compare our method's accuracy to "AngioAnalytics".
Authors: Gavrielle R Untracht; Rolando S Matos; Nikolaos Dikaios; Mariam Bapir; Abdullah K Durrani; Teemapron Butsabong; Paola Campagnolo; David D Sampson; Christian Heiss; Danuta M Sampson Journal: PLoS One Date: 2021-12-09 Impact factor: 3.240
Authors: Simrat K Sodhi; Austin Pereira; Jonathan D Oakley; John Golding; Carmelina Trimboli; Daniel B Russakoff; Netan Choudhry Journal: PLoS One Date: 2022-02-14 Impact factor: 3.240
Authors: K Matthew McKay; Zhongdi Chu; Joon-Bom Kim; Alex Legocki; Xiao Zhou; Meng Tian; Marion R Munk; Ruikang K Wang; Kathryn L Pepple Journal: Am J Ophthalmol Date: 2021-06-06 Impact factor: 5.258