Cargando…

Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data

Synthetic clinical images could augment real medical image datasets, a novel approach in otolaryngology–head and neck surgery (OHNS). Our objective was to develop a generative adversarial network (GAN) for tympanic membrane images and to validate the quality of synthetic images with human reviewers....

Descripción completa

Detalles Bibliográficos
Autores principales: Suresh, Krish, Cohen, Michael S., Hartnick, Christopher J., Bartholomew, Ryan A., Lee, Daniel J., Crowson, Matthew G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9956018/
https://www.ncbi.nlm.nih.gov/pubmed/36827244
http://dx.doi.org/10.1371/journal.pdig.0000202
_version_ 1784894489799688192
author Suresh, Krish
Cohen, Michael S.
Hartnick, Christopher J.
Bartholomew, Ryan A.
Lee, Daniel J.
Crowson, Matthew G.
author_facet Suresh, Krish
Cohen, Michael S.
Hartnick, Christopher J.
Bartholomew, Ryan A.
Lee, Daniel J.
Crowson, Matthew G.
author_sort Suresh, Krish
collection PubMed
description Synthetic clinical images could augment real medical image datasets, a novel approach in otolaryngology–head and neck surgery (OHNS). Our objective was to develop a generative adversarial network (GAN) for tympanic membrane images and to validate the quality of synthetic images with human reviewers. Our model was developed using a state-of-the-art GAN architecture, StyleGAN2-ADA. The network was trained on intraoperative high-definition (HD) endoscopic images of tympanic membranes collected from pediatric patients undergoing myringotomy with possible tympanostomy tube placement. A human validation survey was administered to a cohort of OHNS and pediatrics trainees at our institution. The primary measure of model quality was the Frechet Inception Distance (FID), a metric comparing the distribution of generated images with the distribution of real images. The measures used for human reviewer validation were the sensitivity, specificity, and area under the curve (AUC) for humans’ ability to discern synthetic from real images. Our dataset comprised 202 images. The best GAN was trained at 512x512 image resolution with a FID of 47.0. The progression of images through training showed stepwise “learning” of the anatomic features of a tympanic membrane. The validation survey was taken by 65 persons who reviewed 925 images. Human reviewers demonstrated a sensitivity of 66%, specificity of 73%, and AUC of 0.69 for the detection of synthetic images. In summary, we successfully developed a GAN to produce synthetic tympanic membrane images and validated this with human reviewers. These images could be used to bolster real datasets with various pathologies and develop more robust deep learning models such as those used for diagnostic predictions from otoscopic images. However, caution should be exercised with the use of synthetic data given issues regarding data diversity and performance validation. Any model trained using synthetic data will require robust external validation to ensure validity and generalizability.
format Online
Article
Text
id pubmed-9956018
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-99560182023-02-25 Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data Suresh, Krish Cohen, Michael S. Hartnick, Christopher J. Bartholomew, Ryan A. Lee, Daniel J. Crowson, Matthew G. PLOS Digit Health Research Article Synthetic clinical images could augment real medical image datasets, a novel approach in otolaryngology–head and neck surgery (OHNS). Our objective was to develop a generative adversarial network (GAN) for tympanic membrane images and to validate the quality of synthetic images with human reviewers. Our model was developed using a state-of-the-art GAN architecture, StyleGAN2-ADA. The network was trained on intraoperative high-definition (HD) endoscopic images of tympanic membranes collected from pediatric patients undergoing myringotomy with possible tympanostomy tube placement. A human validation survey was administered to a cohort of OHNS and pediatrics trainees at our institution. The primary measure of model quality was the Frechet Inception Distance (FID), a metric comparing the distribution of generated images with the distribution of real images. The measures used for human reviewer validation were the sensitivity, specificity, and area under the curve (AUC) for humans’ ability to discern synthetic from real images. Our dataset comprised 202 images. The best GAN was trained at 512x512 image resolution with a FID of 47.0. The progression of images through training showed stepwise “learning” of the anatomic features of a tympanic membrane. The validation survey was taken by 65 persons who reviewed 925 images. Human reviewers demonstrated a sensitivity of 66%, specificity of 73%, and AUC of 0.69 for the detection of synthetic images. In summary, we successfully developed a GAN to produce synthetic tympanic membrane images and validated this with human reviewers. These images could be used to bolster real datasets with various pathologies and develop more robust deep learning models such as those used for diagnostic predictions from otoscopic images. However, caution should be exercised with the use of synthetic data given issues regarding data diversity and performance validation. Any model trained using synthetic data will require robust external validation to ensure validity and generalizability. Public Library of Science 2023-02-24 /pmc/articles/PMC9956018/ /pubmed/36827244 http://dx.doi.org/10.1371/journal.pdig.0000202 Text en © 2023 Suresh et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Suresh, Krish
Cohen, Michael S.
Hartnick, Christopher J.
Bartholomew, Ryan A.
Lee, Daniel J.
Crowson, Matthew G.
Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title_full Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title_fullStr Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title_full_unstemmed Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title_short Generation of synthetic tympanic membrane images: Development, human validation, and clinical implications of synthetic data
title_sort generation of synthetic tympanic membrane images: development, human validation, and clinical implications of synthetic data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9956018/
https://www.ncbi.nlm.nih.gov/pubmed/36827244
http://dx.doi.org/10.1371/journal.pdig.0000202
work_keys_str_mv AT sureshkrish generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata
AT cohenmichaels generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata
AT hartnickchristopherj generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata
AT bartholomewryana generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata
AT leedanielj generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata
AT crowsonmatthewg generationofsynthetictympanicmembraneimagesdevelopmenthumanvalidationandclinicalimplicationsofsyntheticdata