TY - JOUR
T1 - An improved strabismus screening method with combination of meta-learning and image processing under data scarcity
AU - Huang, Xilang
AU - Lee, Sang Joon
AU - Kim, Chang Zoo
AU - Choi, Seon Han
N1 - Funding Information:
This research was supported in part by the Bio & Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean Government (MSIT) under Grant 2019M3E5D1A02070862 and supported in part by the Beginning Independent Researcher Program of the NRF funded by the MSIT under Grant 2019R1G1A1098951. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Publisher Copyright:
© 2022 Huang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2022/8
Y1 - 2022/8
N2 - Purpose Considering the scarcity of normal and strabismic images, this study proposed a method that combines a meta-learning approach with image processing methods to improve the classification accuracy when meta-learning alone is used for screening strabismus. Methods The meta-learning approach was first pre-trained on a public dataset to obtain a well-generalized embedding network to extract distinctive features of images. On the other hand, the image processing methods were used to extract the position features of eye regions (e.g., iris position, corneal light reflex) as supplementary features to the distinctive features. Afterward, principal component analysis was applied to reduce the dimensionality of distinctive features for integration with low-dimensional supplementary features. The integrated features were then used to train a support vector machine classifier for performing strabismus screening. Sixty images (30 normal and 30 strabismus) were used to verify the effectiveness of the proposed method, and its classification performance was assessed by computing the accuracy, specificity, and sensitivity through 5,000 experiments. Results The proposed method achieved a classification accuracy of 0.805 with a sensitivity (correct classification of strabismus) of 0.768 and a specificity (correct classification of normal) of 0.842, whereas the classification accuracy of using meta-learning alone was 0.709 with a sensitivity of 0.740 and a specificity of 0.678. Conclusion The proposed strabismus screening method achieved promising classification accuracy and gained significant accuracy improvement over using meta-learning alone under data scarcity.
AB - Purpose Considering the scarcity of normal and strabismic images, this study proposed a method that combines a meta-learning approach with image processing methods to improve the classification accuracy when meta-learning alone is used for screening strabismus. Methods The meta-learning approach was first pre-trained on a public dataset to obtain a well-generalized embedding network to extract distinctive features of images. On the other hand, the image processing methods were used to extract the position features of eye regions (e.g., iris position, corneal light reflex) as supplementary features to the distinctive features. Afterward, principal component analysis was applied to reduce the dimensionality of distinctive features for integration with low-dimensional supplementary features. The integrated features were then used to train a support vector machine classifier for performing strabismus screening. Sixty images (30 normal and 30 strabismus) were used to verify the effectiveness of the proposed method, and its classification performance was assessed by computing the accuracy, specificity, and sensitivity through 5,000 experiments. Results The proposed method achieved a classification accuracy of 0.805 with a sensitivity (correct classification of strabismus) of 0.768 and a specificity (correct classification of normal) of 0.842, whereas the classification accuracy of using meta-learning alone was 0.709 with a sensitivity of 0.740 and a specificity of 0.678. Conclusion The proposed strabismus screening method achieved promising classification accuracy and gained significant accuracy improvement over using meta-learning alone under data scarcity.
UR - http://www.scopus.com/inward/record.url?scp=85135598638&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0269365
DO - 10.1371/journal.pone.0269365
M3 - Article
C2 - 35930530
AN - SCOPUS:85135598638
VL - 17
JO - PLoS ONE
JF - PLoS ONE
SN - 1932-6203
IS - 8 August
M1 - e0269365
ER -