Cargando…

RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning

PURPOSE: The purpose of this study was to develop a deep learning-based fully automated reconstruction and quantification algorithm which automatically delineates the neurites and somas of retinal ganglion cells (RGCs). METHODS: We trained a deep learning-based multi-task image segmentation model, R...

Descripción completa

Detalles Bibliográficos
Autores principales: Ma, Rui, Hao, Lili, Tao, Yudong, Mendoza, Ximena, Khodeiry, Mohamed, Liu, Yuan, Shyu, Mei-Ling, Lee, Richard K.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10166122/
https://www.ncbi.nlm.nih.gov/pubmed/37140906
http://dx.doi.org/10.1167/tvst.12.5.7
_version_ 1785038380265897984
author Ma, Rui
Hao, Lili
Tao, Yudong
Mendoza, Ximena
Khodeiry, Mohamed
Liu, Yuan
Shyu, Mei-Ling
Lee, Richard K.
author_facet Ma, Rui
Hao, Lili
Tao, Yudong
Mendoza, Ximena
Khodeiry, Mohamed
Liu, Yuan
Shyu, Mei-Ling
Lee, Richard K.
author_sort Ma, Rui
collection PubMed
description PURPOSE: The purpose of this study was to develop a deep learning-based fully automated reconstruction and quantification algorithm which automatically delineates the neurites and somas of retinal ganglion cells (RGCs). METHODS: We trained a deep learning-based multi-task image segmentation model, RGC-Net, that automatically segments the neurites and somas in RGC images. A total of 166 RGC scans with manual annotations from human experts were used to develop this model, whereas 132 scans were used for training, and the remaining 34 scans were reserved as testing data. Post-processing techniques removed speckles or dead cells in soma segmentation results to further improve the robustness of the model. Quantification analyses were also conducted to compare five different metrics obtained by our automated algorithm and manual annotations. RESULTS: Quantitatively, our segmentation model achieves average foreground accuracy, background accuracy, overall accuracy, and dice similarity coefficient of 0.692, 0.999, 0.997, and 0.691 for the neurite segmentation task, and 0.865, 0.999, 0.997, and 0.850 for the soma segmentation task, respectively. CONCLUSIONS: The experimental results demonstrate that RGC-Net can accurately and reliably reconstruct neurites and somas in RGC images. We also demonstrate our algorithm is comparable to human manually curated annotations in quantification analyses. TRANSLATIONAL RELEVANCE: Our deep learning model provides a new tool that can trace and analyze the RGC neurites and somas efficiently and faster than manual analysis.
format Online
Article
Text
id pubmed-10166122
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-101661222023-05-09 RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning Ma, Rui Hao, Lili Tao, Yudong Mendoza, Ximena Khodeiry, Mohamed Liu, Yuan Shyu, Mei-Ling Lee, Richard K. Transl Vis Sci Technol Glaucoma PURPOSE: The purpose of this study was to develop a deep learning-based fully automated reconstruction and quantification algorithm which automatically delineates the neurites and somas of retinal ganglion cells (RGCs). METHODS: We trained a deep learning-based multi-task image segmentation model, RGC-Net, that automatically segments the neurites and somas in RGC images. A total of 166 RGC scans with manual annotations from human experts were used to develop this model, whereas 132 scans were used for training, and the remaining 34 scans were reserved as testing data. Post-processing techniques removed speckles or dead cells in soma segmentation results to further improve the robustness of the model. Quantification analyses were also conducted to compare five different metrics obtained by our automated algorithm and manual annotations. RESULTS: Quantitatively, our segmentation model achieves average foreground accuracy, background accuracy, overall accuracy, and dice similarity coefficient of 0.692, 0.999, 0.997, and 0.691 for the neurite segmentation task, and 0.865, 0.999, 0.997, and 0.850 for the soma segmentation task, respectively. CONCLUSIONS: The experimental results demonstrate that RGC-Net can accurately and reliably reconstruct neurites and somas in RGC images. We also demonstrate our algorithm is comparable to human manually curated annotations in quantification analyses. TRANSLATIONAL RELEVANCE: Our deep learning model provides a new tool that can trace and analyze the RGC neurites and somas efficiently and faster than manual analysis. The Association for Research in Vision and Ophthalmology 2023-05-04 /pmc/articles/PMC10166122/ /pubmed/37140906 http://dx.doi.org/10.1167/tvst.12.5.7 Text en Copyright 2023 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
spellingShingle Glaucoma
Ma, Rui
Hao, Lili
Tao, Yudong
Mendoza, Ximena
Khodeiry, Mohamed
Liu, Yuan
Shyu, Mei-Ling
Lee, Richard K.
RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title_full RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title_fullStr RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title_full_unstemmed RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title_short RGC-Net: An Automatic Reconstruction and Quantification Algorithm for Retinal Ganglion Cells Based on Deep Learning
title_sort rgc-net: an automatic reconstruction and quantification algorithm for retinal ganglion cells based on deep learning
topic Glaucoma
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10166122/
https://www.ncbi.nlm.nih.gov/pubmed/37140906
http://dx.doi.org/10.1167/tvst.12.5.7
work_keys_str_mv AT marui rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT haolili rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT taoyudong rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT mendozaximena rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT khodeirymohamed rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT liuyuan rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT shyumeiling rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning
AT leerichardk rgcnetanautomaticreconstructionandquantificationalgorithmforretinalganglioncellsbasedondeeplearning