K Matthew McKay1, Zhongdi Chu2, Joon-Bom Kim1, Alex Legocki1, Xiao Zhou2, Meng Tian3, Marion R Munk3, Ruikang K Wang4, Kathryn L Pepple5. 1. Department of Ophthalmology, University of Washington, Seattle, Washington, USA. 2. Departments of Ophthalmology and Bioengineering, University of Washington, Seattle, Washington, USA. 3. Department of Ophthalmology and Bern Photographic Reading Center, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland. 4. Department of Ophthalmology, University of Washington, Seattle, Washington, USA; Departments of Ophthalmology and Bioengineering, University of Washington, Seattle, Washington, USA. 5. Department of Ophthalmology, University of Washington, Seattle, Washington, USA. Electronic address: kpepple@uw.edu.
Abstract
PURPOSE: To validate a custom algorithm for automated identification and quantification of clinically relevant inflammatory choriocapillaris (CC) lesions from en face swept-source optical coherence tomography (SS-OCTA) images. DESIGN: Observational case series. METHODS: Twenty eyes of 14 patients with posterior uveitis were imaged. The machine-generated en face OCTA CC slabs were exported to a computing platform, where a custom algorithm performed unsupervised lesion boundary delineation and area quantification. Lesions identified by the algorithm (AG) were compared to those identified by 2 masked human graders (HG1 and HG2), using the Sørensen-Dice coefficient (DSC) and intraclass correlation coefficient (ICC). Intragrader and intravisit reliability were determined by coefficient of variation (CV) and DSC. RESULTS: The AG demonstrated excellent agreement with both HGs in determination of lesion area (HG1 vs AG ICC 0.92, 95% CI 0.81-0.97, HG2 vs AG ICC 0.91, 95% CI 0.78-0.97). The AG demonstrated good spatial overlap (DSC ≥0.70) with both HGs in 14 of 20 (70%) eyes and at least 1 HG in 16 of 20 (80%) eyes. Poor spatial overlap (DSC between 0.31 and 0.69) was associated with the presence of a choroidal neovascular membrane and low-contrast lesion boundaries. Intravisit repeatability for the AG was superior to both HGs (CV 2.6% vs >5%). CONCLUSION: This custom algorithm demonstrated a high degree of agreement with HGs in identification of inflammatory CC lesions and outperformed HGs in reproducibility. Automated CC lesion delineation will support the development of objective and quantitative biomarker of disease activity in patients with posterior uveitis.
PURPOSE: To validate a custom algorithm for automated identification and quantification of clinically relevant inflammatory choriocapillaris (CC) lesions from en face swept-source optical coherence tomography (SS-OCTA) images. DESIGN: Observational case series. METHODS: Twenty eyes of 14 patients with posterior uveitis were imaged. The machine-generated en face OCTA CC slabs were exported to a computing platform, where a custom algorithm performed unsupervised lesion boundary delineation and area quantification. Lesions identified by the algorithm (AG) were compared to those identified by 2 masked human graders (HG1 and HG2), using the Sørensen-Dice coefficient (DSC) and intraclass correlation coefficient (ICC). Intragrader and intravisit reliability were determined by coefficient of variation (CV) and DSC. RESULTS: The AG demonstrated excellent agreement with both HGs in determination of lesion area (HG1 vs AG ICC 0.92, 95% CI 0.81-0.97, HG2 vs AG ICC 0.91, 95% CI 0.78-0.97). The AG demonstrated good spatial overlap (DSC ≥0.70) with both HGs in 14 of 20 (70%) eyes and at least 1 HG in 16 of 20 (80%) eyes. Poor spatial overlap (DSC between 0.31 and 0.69) was associated with the presence of a choroidal neovascular membrane and low-contrast lesion boundaries. Intravisit repeatability for the AG was superior to both HGs (CV 2.6% vs >5%). CONCLUSION: This custom algorithm demonstrated a high degree of agreement with HGs in identification of inflammatory CC lesions and outperformed HGs in reproducibility. Automated CC lesion delineation will support the development of objective and quantitative biomarker of disease activity in patients with posterior uveitis.
Authors: Polina Astroz; Alexandra Miere; Sarah Mrejen; Rim Sekfali; Eric H Souied; Camille Jung; Sylvia Nghiem-Buffet; Salomon Y Cohen Journal: Retina Date: 2018-02 Impact factor: 4.256
Authors: Kathryn L Pepple; Zhongdi Chu; Jessica Weinstein; Marion R Munk; Russell N Van Gelder; Ruikang K Wang Journal: JAMA Ophthalmol Date: 2018-11-01 Impact factor: 7.389
Authors: Kelly H Zou; Simon K Warfield; Aditya Bharatha; Clare M C Tempany; Michael R Kaus; Steven J Haker; William M Wells; Ferenc A Jolesz; Ron Kikinis Journal: Acad Radiol Date: 2004-02 Impact factor: 3.173
Authors: Qinqin Zhang; Fang Zheng; Elie H Motulsky; Giovanni Gregori; Zhongdi Chu; Chieh-Li Chen; Chunxia Li; Luis de Sisternes; Mary Durbin; Philip J Rosenfeld; Ruikang K Wang Journal: Invest Ophthalmol Vis Sci Date: 2018-01-01 Impact factor: 4.799
Authors: Sook-Lei Liew; Julia M Anglin; Nick W Banks; Matt Sondag; Kaori L Ito; Hosung Kim; Jennifer Chan; Joyce Ito; Connie Jung; Nima Khoshab; Stephanie Lefebvre; William Nakamura; David Saldana; Allie Schmiesing; Cathy Tran; Danny Vo; Tyler Ard; Panthea Heydari; Bokkyu Kim; Lisa Aziz-Zadeh; Steven C Cramer; Jingchun Liu; Surjo Soekadar; Jan-Egil Nordvik; Lars T Westlye; Junping Wang; Carolee Winstein; Chunshui Yu; Lei Ai; Bonhwang Koo; R Cameron Craddock; Michael Milham; Matthew Lakich; Amy Pienta; Alison Stroud Journal: Sci Data Date: 2018-02-20 Impact factor: 6.444