Nl-Fr

View abstract

This abstract is assigned to session 3 - Free Papers I - Infectious Uveitis
Presentation preference Oral presentation
TitleAutomated lesion segmentation and quantification for prediction of paradoxical worsening in patients with Tubercular serpiginous-like choroiditis
PurposeTo develop and evaluate a fully automated pipeline that analyzes color fundus images in patients with TB SLC for prediction of PW.
Methods Retrospective study, patients with TB SLC with a follow-up of 9 months after initiation of ATT were included. A fully automated custom-designed pipeline developed after confirming reliability using Bland-Altman plots and intraclass correlation coefficient (ICC), the pipeline was deployed for all patients. Two automatic thresholding algorithms were applied and quantitative metrics were compared between PW+ and PW- groups using non-parametric tests and logistic regression model to assess binary classification performance.
ResultsThe study included 139 patients (139 eyes; 92 M and 47 F; mean age: 44.8 ± 11.3 Yrs) with TB SLC. The PW+ group had significantly higher mean lesion area (p=0.0152), mean pixel intensity (p=0.0181), and integrated pixel intensity (p<0.0001) compared to the PW- group. Using a sensitivity optimized threshold cut-off for mean pixel intensity, an area under the curve of 0.87 was achieved (sensitivity: 96.80% and specificity: 72.09%).
ConclusionAutomated calculation of lesion metrics such as mean pixel intensity and segmented area in TB SLC is a novel approach with good repeatability in predicting PW during the follow-up.
Conflict of interestNo
Authors 1
Last nameDANGI
Initials of first name(s)M
DepartmentAdvanced Eye Centre, Post Graduate Institute of Medical Education and Research
CityChandigarh
CountryIndia
Authors 2
Last nameKALRA
Initials of first name(s)G
DepartmentCole Eye Institute , Cleveland Clinic,
CityOhio
CountryUnited States
Authors 3
Last nameAGARWAL
Initials of first name(s)A
DepartmentEye Institute, Cleveland Clinic Abu Dhabi
CityAbu Dhabhi
CountryUnited Arab Emirates
Authors 4
Last nameMARCHESE
Initials of first name(s)A
Department San Raffaele Scientific Institute
CityMilan
CountryItaly
Authors 5
Last nameBANSAL
Initials of first name(s)R
DepartmentAEC, PGIMER
CityChandigarh
CountryIndia
Authors 6
Last nameGUPTA
Initials of first name(s)V
DepartmentAEC, PGIMER
CityChandigarh
CountryIndia