Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis

To develop and evaluate a fully automated pipeline that analyzes color fundus images in patients with tubercular serpiginous-like choroiditis (TB SLC) for prediction of paradoxical worsening (PW). In this retrospective study, patients with TB SLC with a follow-up of 9 months after initiation of anti...

Full description

Saved in:
Bibliographic Details
Main Authors: Kalra, Gagan, Agarwal, Aniruddha, Marchese, Alessandro, Agrawal, Rupesh, Bansal, Reema, Gupta, Vishali
Other Authors: Lee Kong Chian School of Medicine (LKCMedicine)
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/163279
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-163279
record_format dspace
spelling sg-ntu-dr.10356-1632792023-03-05T16:52:55Z Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis Kalra, Gagan Agarwal, Aniruddha Marchese, Alessandro Agrawal, Rupesh Bansal, Reema Gupta, Vishali Lee Kong Chian School of Medicine (LKCMedicine) Tan Tock Seng Hospital Singapore Eye Research Institute Duke NUS Medical School Science::Medicine Choroiditis Eye Fundus To develop and evaluate a fully automated pipeline that analyzes color fundus images in patients with tubercular serpiginous-like choroiditis (TB SLC) for prediction of paradoxical worsening (PW). In this retrospective study, patients with TB SLC with a follow-up of 9 months after initiation of anti-tubercular therapy were included. A fully automated custom-designed pipeline was developed which was initially tested using 12 baseline color fundus photographs for assessment of repeatability. After confirming reliability using Bland-Altman plots and intraclass correlation coefficient (ICC), the pipeline was deployed for all patients. The images were preprocessed to exclude the optic nerve from the fundus photo using a single-shot trainable WEKA segmentation algorithm. Two automatic thresholding algorithms were applied, and quantitative metrics were generated. These metrics were compared between PW + and PW- groups using non-parametric tests. A logistic regression model was used to predict probability of PW for assessing binary classification performance and receiver operator curves were generated to choose a sensitivity-optimized threshold. The study included 139 patients (139 eyes; 92 males and 47 females; mean age: 44.8 ± 11.3 years) with TB SLC. Pilot analysis of 12 images showed an excellent ICC for measuring the mean area, intensity, and integrated pixel intensity (all ICC > 0.89). 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%). Automated 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. Published version 2022-11-30T02:23:18Z 2022-11-30T02:23:18Z 2022 Journal Article Kalra, G., Agarwal, A., Marchese, A., Agrawal, R., Bansal, R. & Gupta, V. (2022). Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis. Scientific Reports, 12(1), 5392-. https://dx.doi.org/10.1038/s41598-022-09338-y 2045-2322 https://hdl.handle.net/10356/163279 10.1038/s41598-022-09338-y 35354885 2-s2.0-85127257712 1 12 5392 en Scientific Reports © The Author(s) 2022. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Science::Medicine
Choroiditis
Eye Fundus
spellingShingle Science::Medicine
Choroiditis
Eye Fundus
Kalra, Gagan
Agarwal, Aniruddha
Marchese, Alessandro
Agrawal, Rupesh
Bansal, Reema
Gupta, Vishali
Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
description To develop and evaluate a fully automated pipeline that analyzes color fundus images in patients with tubercular serpiginous-like choroiditis (TB SLC) for prediction of paradoxical worsening (PW). In this retrospective study, patients with TB SLC with a follow-up of 9 months after initiation of anti-tubercular therapy were included. A fully automated custom-designed pipeline was developed which was initially tested using 12 baseline color fundus photographs for assessment of repeatability. After confirming reliability using Bland-Altman plots and intraclass correlation coefficient (ICC), the pipeline was deployed for all patients. The images were preprocessed to exclude the optic nerve from the fundus photo using a single-shot trainable WEKA segmentation algorithm. Two automatic thresholding algorithms were applied, and quantitative metrics were generated. These metrics were compared between PW + and PW- groups using non-parametric tests. A logistic regression model was used to predict probability of PW for assessing binary classification performance and receiver operator curves were generated to choose a sensitivity-optimized threshold. The study included 139 patients (139 eyes; 92 males and 47 females; mean age: 44.8 ± 11.3 years) with TB SLC. Pilot analysis of 12 images showed an excellent ICC for measuring the mean area, intensity, and integrated pixel intensity (all ICC > 0.89). 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%). Automated 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.
author2 Lee Kong Chian School of Medicine (LKCMedicine)
author_facet Lee Kong Chian School of Medicine (LKCMedicine)
Kalra, Gagan
Agarwal, Aniruddha
Marchese, Alessandro
Agrawal, Rupesh
Bansal, Reema
Gupta, Vishali
format Article
author Kalra, Gagan
Agarwal, Aniruddha
Marchese, Alessandro
Agrawal, Rupesh
Bansal, Reema
Gupta, Vishali
author_sort Kalra, Gagan
title Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
title_short Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
title_full Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
title_fullStr Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
title_full_unstemmed Automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
title_sort automated lesion segmentation and quantification for prediction of paradoxical worsening in patients with tubercular serpiginous-like choroiditis
publishDate 2022
url https://hdl.handle.net/10356/163279
_version_ 1759858318467137536