Cargando…
iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis
Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9862104/ https://www.ncbi.nlm.nih.gov/pubmed/36675327 http://dx.doi.org/10.3390/jcm12020400 |
_version_ | 1784875009858076672 |
---|---|
author | Jin, Kai Yan, Yan Wang, Shuai Yang, Ce Chen, Menglu Liu, Xindi Terasaki, Hiroto Yeo, Tun-Hang Singh, Neha Gulab Wang, Yao Ye, Juan |
author_facet | Jin, Kai Yan, Yan Wang, Shuai Yang, Ce Chen, Menglu Liu, Xindi Terasaki, Hiroto Yeo, Tun-Hang Singh, Neha Gulab Wang, Yao Ye, Juan |
author_sort | Jin, Kai |
collection | PubMed |
description | Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this study aimed to develop a two-stage deep learning (DL) system named iERM to provide accurate automatic grading of ERM for clinical practice. Methods: The iERM was trained based on human segmentation of key features to improve classification performance and simultaneously provide interpretability to the classification results. We developed and tested iERM using a total of 4547 OCT B-Scans of four different commercial OCT devices that were collected from nine international medical centers. Results: As per the results, the integrated network effectively improved the grading performance by 1–5.9% compared with the traditional classification DL model and achieved high accuracy scores of 82.9%, 87.0%, and 79.4% in the internal test dataset and two external test datasets, respectively. This is comparable to retinal specialists whose average accuracy scores are 87.8% and 79.4% in two external test datasets. Conclusion: This study proved to be a benchmark method to improve the performance and enhance the interpretability of the traditional DL model with the implementation of segmentation based on prior human knowledge. It may have the potential to provide precise guidance for ERM diagnosis and treatment. |
format | Online Article Text |
id | pubmed-9862104 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-98621042023-01-22 iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis Jin, Kai Yan, Yan Wang, Shuai Yang, Ce Chen, Menglu Liu, Xindi Terasaki, Hiroto Yeo, Tun-Hang Singh, Neha Gulab Wang, Yao Ye, Juan J Clin Med Article Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this study aimed to develop a two-stage deep learning (DL) system named iERM to provide accurate automatic grading of ERM for clinical practice. Methods: The iERM was trained based on human segmentation of key features to improve classification performance and simultaneously provide interpretability to the classification results. We developed and tested iERM using a total of 4547 OCT B-Scans of four different commercial OCT devices that were collected from nine international medical centers. Results: As per the results, the integrated network effectively improved the grading performance by 1–5.9% compared with the traditional classification DL model and achieved high accuracy scores of 82.9%, 87.0%, and 79.4% in the internal test dataset and two external test datasets, respectively. This is comparable to retinal specialists whose average accuracy scores are 87.8% and 79.4% in two external test datasets. Conclusion: This study proved to be a benchmark method to improve the performance and enhance the interpretability of the traditional DL model with the implementation of segmentation based on prior human knowledge. It may have the potential to provide precise guidance for ERM diagnosis and treatment. MDPI 2023-01-04 /pmc/articles/PMC9862104/ /pubmed/36675327 http://dx.doi.org/10.3390/jcm12020400 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Jin, Kai Yan, Yan Wang, Shuai Yang, Ce Chen, Menglu Liu, Xindi Terasaki, Hiroto Yeo, Tun-Hang Singh, Neha Gulab Wang, Yao Ye, Juan iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title | iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title_full | iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title_fullStr | iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title_full_unstemmed | iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title_short | iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis |
title_sort | ierm: an interpretable deep learning system to classify epiretinal membrane for different optical coherence tomography devices: a multi-center analysis |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9862104/ https://www.ncbi.nlm.nih.gov/pubmed/36675327 http://dx.doi.org/10.3390/jcm12020400 |
work_keys_str_mv | AT jinkai iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT yanyan iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT wangshuai iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT yangce iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT chenmenglu iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT liuxindi iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT terasakihiroto iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT yeotunhang iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT singhnehagulab iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT wangyao iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis AT yejuan iermaninterpretabledeeplearningsystemtoclassifyepiretinalmembranefordifferentopticalcoherencetomographydevicesamulticenteranalysis |