Cargando…
Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases
PURPOSE: The performance of deep learning may fluctuate depending on the imaging devices and settings. Although domain transformation such as CycleGAN for normalizing images is useful, CycleGAN does not use information on the disease classes. Therefore, we propose a semi-supervised CycleGAN with an...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer International Publishing
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8522550/ https://www.ncbi.nlm.nih.gov/pubmed/34661818 http://dx.doi.org/10.1007/s11548-021-02490-2 |
_version_ | 1784585109628780544 |
---|---|
author | Mabu, Shingo Miyake, Masashi Kuremoto, Takashi Kido, Shoji |
author_facet | Mabu, Shingo Miyake, Masashi Kuremoto, Takashi Kido, Shoji |
author_sort | Mabu, Shingo |
collection | PubMed |
description | PURPOSE: The performance of deep learning may fluctuate depending on the imaging devices and settings. Although domain transformation such as CycleGAN for normalizing images is useful, CycleGAN does not use information on the disease classes. Therefore, we propose a semi-supervised CycleGAN with an additional classification loss to transform images suitable for the diagnosis. The method is evaluated by opacity classification of chest CT. METHODS: (1) CT images taken at two hospitals (source and target domains) are used. (2) A classifier is trained on the target domain. (3) Class labels are given to a small number of source domain images for semi-supervised learning. (4) The source domain images are transformed to the target domain. (5) A classification loss of the transformed images with class labels is calculated. RESULTS: The proposed method showed an F-measure of 0.727 in the domain transformation from hospital A to B, and 0.745 in that from hospital B to A, where significant differences are between the proposed method and the other three methods. CONCLUSIONS: The proposed method not only transforms the appearance of the images but also retains the features being important to classify opacities, and shows the best precision, recall, and F-measure. |
format | Online Article Text |
id | pubmed-8522550 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Springer International Publishing |
record_format | MEDLINE/PubMed |
spelling | pubmed-85225502021-10-20 Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases Mabu, Shingo Miyake, Masashi Kuremoto, Takashi Kido, Shoji Int J Comput Assist Radiol Surg Original Article PURPOSE: The performance of deep learning may fluctuate depending on the imaging devices and settings. Although domain transformation such as CycleGAN for normalizing images is useful, CycleGAN does not use information on the disease classes. Therefore, we propose a semi-supervised CycleGAN with an additional classification loss to transform images suitable for the diagnosis. The method is evaluated by opacity classification of chest CT. METHODS: (1) CT images taken at two hospitals (source and target domains) are used. (2) A classifier is trained on the target domain. (3) Class labels are given to a small number of source domain images for semi-supervised learning. (4) The source domain images are transformed to the target domain. (5) A classification loss of the transformed images with class labels is calculated. RESULTS: The proposed method showed an F-measure of 0.727 in the domain transformation from hospital A to B, and 0.745 in that from hospital B to A, where significant differences are between the proposed method and the other three methods. CONCLUSIONS: The proposed method not only transforms the appearance of the images but also retains the features being important to classify opacities, and shows the best precision, recall, and F-measure. Springer International Publishing 2021-10-16 2021 /pmc/articles/PMC8522550/ /pubmed/34661818 http://dx.doi.org/10.1007/s11548-021-02490-2 Text en © CARS 2021 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Original Article Mabu, Shingo Miyake, Masashi Kuremoto, Takashi Kido, Shoji Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title | Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title_full | Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title_fullStr | Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title_full_unstemmed | Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title_short | Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases |
title_sort | semi-supervised cyclegan for domain transformation of chest ct images and its application to opacity classification of diffuse lung diseases |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8522550/ https://www.ncbi.nlm.nih.gov/pubmed/34661818 http://dx.doi.org/10.1007/s11548-021-02490-2 |
work_keys_str_mv | AT mabushingo semisupervisedcycleganfordomaintransformationofchestctimagesanditsapplicationtoopacityclassificationofdiffuselungdiseases AT miyakemasashi semisupervisedcycleganfordomaintransformationofchestctimagesanditsapplicationtoopacityclassificationofdiffuselungdiseases AT kuremototakashi semisupervisedcycleganfordomaintransformationofchestctimagesanditsapplicationtoopacityclassificationofdiffuselungdiseases AT kidoshoji semisupervisedcycleganfordomaintransformationofchestctimagesanditsapplicationtoopacityclassificationofdiffuselungdiseases |