Automated photographic analysis of inferior oblique overaction based on deep learning - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan 1;13(1):329-338.
doi: 10.21037/qims-22-467. Epub 2022 Oct 28.

Automated photographic analysis of inferior oblique overaction based on deep learning

Lixia Lou #  1 , Xingru Huang #  2 , Yiming Sun  1 , Jing Cao  1 , Yaqi Wang  3 , Qianni Zhang  2 , Xiajing Tang  1 , Juan Ye  1
Affiliations

Automated photographic analysis of inferior oblique overaction based on deep learning

Lixia Lou et al. Quant Imaging Med Surg. .

Abstract

Background: Inferior oblique overaction (IOOA) is a common ocular motility disorder. This study aimed to propose a novel deep learning-based approach to automatically evaluate the amount of IOOA.

Methods: This prospective study included 106 eyes of 72 consecutive patients attending the strabismus clinic in a tertiary referral hospital. Patients were eligible for inclusion if they were diagnosed with IOOA. IOOA was clinically graded from +1 to +4. Based on photograph in the adducted position, the height difference between the inferior corneal limbus of both eyes was manually measured using ImageJ and automatically measured by our deep learning-based image analysis system with human supervision. Correlation coefficients, Bland-Altman plots and mean absolute deviation (MAD) were analyzed between two different measurements of evaluating IOOA.

Results: There were significant correlations between automated photographic measurements and clinical gradings (Kendall's tau: 0.721; 95% confidence interval: 0.652 to 0.779; P<0.001), between automated and manual photographic measurements [intraclass correlation coefficients (ICCs): 0.975; 95% confidence interval: 0.963 to 0.983; P<0.001], and between two-repeated automated photographic measurements (ICCs: 0.998; 95% confidence interval: 0.997 to 0.999; P<0.001). The biases and MADs were 0.10 [95% limits of agreement (LoA): -0.45 to 0.64] mm and 0.26±0.14 mm between automated and manual photographic measurements, and 0.01 (95% LoA: -0.14 to 0.16) mm and 0.07±0.04 mm between two-repeated automated photographic measurements, respectively.

Conclusions: The automated photographic measurements of IOOA using deep learning technique were in excellent agreement with manual photographic measurements and clinical gradings. This new approach allows objective, accurate and repeatable measurement of IOOA and could be easily implemented in clinical practice using only photographs.

Keywords: Inferior oblique overaction (IOOA); automated image analysis; deep learning.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-22-467/coif). The authors have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
The GAR2U-Net architecture proposed in this study for eye location and eye segmentation. GAR2U-Net, recurrent residual convolutional neural network with global attention gate based on U-net.
Figure 2
Figure 2
The workflow of IOOA measurement using automated photographic method. This image is published with the patient’s consent. IOOA, inferior oblique overaction.
Figure 3
Figure 3
Scatterplots of IOOA measurements using two photographic methods across eyes with different clinical gradings. (A) Measurements using manual photographic method. (B) Measurements using automated photographic method. ***P<0.001 in multiple comparison test. IOOA, inferior oblique overaction.
Figure 4
Figure 4
Scatterplot of two measurements of IOOA. (A) Two measurements using manual and automated photographic methods. (B) Two-repeated automated photographic measurements. IOOA, inferior oblique overaction.
Figure 5
Figure 5
Bland-Altman plots analyzing the agreement between two measurements of IOOA. (A) Agreement between two measurements using manual and automated photographic methods. (B) Agreement between two-repeated automated photographic measurements. Broken lines indicate mean (µ); dotted lines indicate 95% LoA (1.96σ). IOOA, inferior oblique overaction; LoA, limits of agreement.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Caldeira JA. Some clinical characteristics of V-pattern exotropia and surgical outcome after bilateral recession of the inferior oblique muscle: a retrospective study of 22 consecutive patients and a comparison with V-pattern esotropia. Binocul Vis Strabismus Q 2004;19:139-50. - PubMed
    1. Bowling B. Kanski's clinical ophthalmology. Edinburgh: Elsevier, 2016.
    1. Ozsoy E, Gunduz A, Ozturk E. Inferior Oblique Muscle Overaction: Clinical Features and Surgical Management. J Ophthalmol 2019;2019:9713189. 10.1155/2019/9713189 - DOI - PMC - PubMed
    1. Sieck EG, Madabhushi A, Patnaik JL, Jung JL, Lynch AM, Singh JK. Comparison of Different Surgical Approaches to Inferior Oblique Overaction. J Binocul Vis Ocul Motil 2020;70:89-93. 10.1080/2576117X.2020.1776566 - DOI - PubMed
    1. Mohamed AA, Yousef H, Mounir A. Surgical outcomes of inferior oblique muscle weakening procedures for eliminating inferior oblique muscle overaction: a prospective randomized study. Delta J Ophthalmol 2019;20:88-94.