Automated quantification of choroidal neovascularization on Optical Coherence Tomography Angiography images

• Published in: Computers in biology and medicine Vol. 114; p. 103450
• Main Authors: Taibouni, Kawther, Chenoune, Yasmina, Miere, Alexandra, Colantuono, Donato, Souied, Eric, Petit, Eric
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2019; Elsevier Limited; Elsevier
• Subjects: Age; Age related diseases; Age-related macular degeneration; Algorithms; Angiography; Automation; Bias; Biomarkers; Choroidal neovascularization; Conflicts of interest; Eye diseases; Image processing; Image segmentation; Internal Medicine; Life Sciences; Macular degeneration; Medical imaging; Methods; Morlet wavelet; Noise; Optical Coherence Tomography; Optical Coherence Tomography Angiography; Other; Standard deviation; Statistical analysis; Tomography; Topology; Vascular segmentation; Vascularization; Vessel enhancement filtering; Vessel enhancement filtering; Optical Coherence Tomography Angiography; Choroidal neovascularization; Age-related macular degeneration; Vascular segmentation
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.103450

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. 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”. 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. 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”. •Automated CNV segmentation using enhancement filters and Fuzzy-C-Means.•Two segmentation algorithms adapted to the lesions topologies.•Quantification of three biomarkers of neovascular AMD on OCTA images.•Comparison to AngioVue software measures, the new gold standard in OCTA imaging.•Comparable results to expert delineation are achieved for the total area measure.