June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Biomarker assessment for CNV development prediction in multifocal choroiditis (MFC) and punctate inner choroidopathy (PIC): A large, longitudinal, multicenter study on patients with MFC and PIC using an artificial intelligence-based OCT fluid and biomarker detector
Author Affiliations & Notes
  • Lorenzo Ferro Desideri
    Department of Ophthalmology, Inselspital Universitatsspital Bern, Bern, Bern, Switzerland
    Bern Photographic Reading Center, Inselspital, Bern University Hospital, University of Bern, Bern, Bern, Switzerland
  • Mathias Gallardo
    ARTORG Center for Biomedical Engineering, Universitat Bern, Bern, Switzerland
  • Muriel Ott
    Department of Ophthalmology, Inselspital Universitatsspital Bern, Bern, Bern, Switzerland
    Bern Photographic Reading Center, Inselspital, Bern University Hospital, University of Bern, Bern, Bern, Switzerland
  • Ariel Schlaen
    Department of Ophthalmology, Hospital Universitario Austral, Buenos Aires, Argentina (site: HUA), Argentina
  • Debra Goldstein
    Department of Ophthalmology, Northwestern University Feinberg School of Medicine, Chicago, Illinois, United States (site: Northwestern), Illinois, United States
  • H Nida Sen
    Laboratory of Immunology, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States (site: NEI), Maryland, United States
  • Maurizio Battaglia Parodi
    Department of Ophthalmology, Vita-Salute University, San Raffaele Scientific Institute, Milan, Italy, Italy
  • Vita S Dingerkus
    Department of Ophthalmology, City Hospital Zurich, Zurich, Switzerland, Switzerland
  • Yael Sharon
    Department of Ophthalmology, Rabin Medical Center, Faculty of Medicine, Tel Aviv University, Israel, Israel
  • Michal Kramer
    Department of Ophthalmology, Rabin Medical Center, Faculty of Medicine, Tel Aviv University, Israel, Israel
  • Siqing Yu
    Roche Pharma Research and Early Development Ophthalmology, Basel, Switzerland, Switzerland
  • Sandro De Zanet
    RetinAI, Bern, Switzerland, Switzerland
  • Marion Ronit Munk
    Augenarzt Praxisgemeinschaft Gutblick AG, Bern, Bern, Switzerland
    Department of Ophthalmology, Inselspital Universitatsspital Bern, Bern, Bern, Switzerland
  • Footnotes
    Commercial Relationships   Lorenzo Ferro Desideri None; Mathias Gallardo None; Muriel Ott None; Ariel Schlaen None; Debra Goldstein None; H Nida Sen None; Maurizio Parodi None; Vita Dingerkus None; Yael Sharon None; Michal Kramer None; Siqing Yu None; Sandro De Zanet None; Marion Munk None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 314. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Lorenzo Ferro Desideri, Mathias Gallardo, Muriel Ott, Ariel Schlaen, Debra Goldstein, H Nida Sen, Maurizio Battaglia Parodi, Vita S Dingerkus, Yael Sharon, Michal Kramer, Siqing Yu, Sandro De Zanet, Marion Ronit Munk; Biomarker assessment for CNV development prediction in multifocal choroiditis (MFC) and punctate inner choroidopathy (PIC): A large, longitudinal, multicenter study on patients with MFC and PIC using an artificial intelligence-based OCT fluid and biomarker detector. Invest. Ophthalmol. Vis. Sci. 2023;64(8):314.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Secondary choroidal neovascularization (CNV) represents the major cause of vision loss in idiopathic MFC and PIC. This study assessed potential biomarkers on OCT to predict the development of CNV using an artificial intelligence (AI)- based software.

Methods : In this multicenter, longitudinal retrospective study, sequential OCTs of MFC and PIC patients were analyzed by an AI-software (Discovery® OCT Biomarker Detector, RetinAI AG, Switzerland). Different morphological biomarkers, volumes of different fluid and lesion compartments as well as layer thicknesses were assessed and AI-based segmentation was manually corrected for all OCT scans, as needed. Data were compared between MFC and PIC and between eyes with and without CNV development. Regression analyses and ML approaches were used to identify the predictive biomarkers for CNV development.

Results : Overall 88 patients were included (PIC: n=55, MFC: n=33, females=66, mean age=47.9 (± 11.8 SD)). The mean follow-up (F/U) period was 5.7± 1.3 yrs and the average spherical equivalent (SE) in the study population was -3,85±4.92 diopters (D). The mean baseline Snellen best-corrected visual acuity (BCVA) was 0.94± 0.48 and did not significantly change during F/U (last F/U visit 0.96 ± 0.47, p=0.66). During the F/U, respectively 67.3 % of the patients with PIC and 60.6 % with MFC developed CNV (p=0.000). The average chorioretinal lesion volumes were significantly larger in MFC compared to PIC (192.8 ± 231 nL vs. 45.8±100.6 nL, p≤ 0.001). Eyes developing CNV had significantly greater lesion volumes than patients without CNV both in PIC and MFC at baseline (126.1 nL ± 18.5 vs 12.0 nL ± 3.0, p=0.001) and during the F/U period (125.0± 37.9 nL vs 9.4±3.1 nL, p≤ 0.001).

Conclusions : Lesion volume is an important predictive biomarker for future secondary CNV development in eyes with PIC or MFC. This finding highlights the importance of evaluation of OCT volumetric data in both the diagnostic and prognostic processes in patients with MFC/PIC.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Comparison of the prevalence between patients CNV+ and patients CNV- in PIC and MFC subgroups

Comparison of the prevalence between patients CNV+ and patients CNV- in PIC and MFC subgroups

 

Average lesion size in patients CNV+ and patients CNV-

Average lesion size in patients CNV+ and patients CNV-

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×