Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Novel quantitative analysis of anterior chamber inflammation based on a deep learning model using anterior segment optical coherence tomography images for diagnosis and precise assessment of intraocular inflammatory diseases
Author Affiliations & Notes
  • Ye Dai
    Sun Yat-Sen University Zhongshan Ophthalmic Center State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China
  • Wei Chi
    Sun Yat-Sen University Zhongshan Ophthalmic Center State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China
  • Footnotes
    Commercial Relationships   Ye Dai State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Resea, Code P (Patent); Wei Chi State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Resea, Code P (Patent)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5542. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ye Dai, Wei Chi; Novel quantitative analysis of anterior chamber inflammation based on a deep learning model using anterior segment optical coherence tomography images for diagnosis and precise assessment of intraocular inflammatory diseases. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5542.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : This study aimed to develop an automated system for quantitatively analysing anterior chamber (AC) inflammation on different types of anterior segment optical coherence tomography (AS-OCT) images, including swept source OCT and spectral domain OCT images.

Methods : A prospective, observational study collected 243 subjects with active uveitis (263 eyes), inactive uveitis (79 eyes) and controls (85 eyes) who underwent three types (CASIA 1, CASIA 2 and Visante) of AS-OCT and routine ocular examinations. An automated analysis system based on a deep learning model was used to measure parameters, including hyperreflective dots and the aqueous-to-air relative intensity (ARI) index, representing AC cells and flares, respectively, on AS-OCT images. Receiver operating characteristic (ROC) curves of these parameters for active uveitis diagnosis were generated.

Results : Significant (p<0.0001) correlations were found between the clinical Standardization of Uveitis Nomenclature (SUN) grade and the hyperreflective dots (r=0.808, 0.854 and 0.823) and ARI index (r=0.727, 0.715 and 0.788) detected by the automated analysis system on the three types of AS-OCT images. Additionally, significant (p<0.0001) correlations (r=0.943, 0.953 and 0.881) between manually and automatedly detected hyperreflective dots were found on the three types of AS-OCT images. According to ROC curve analysis, both the ARI index and the number of hyperreflective dots generated by the proposed automated system were good indicators for the diagnosis of active uveitis, with the latter outperforming the former.

Conclusions : This study provided a novel, convenient and precise tool for the diagnosis and objective evaluation of anterior chamber inflammation in eyes and offering guidance to clinicians who have different levels of experience in providing appropriate treatments.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

×
×

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.

×