Cargando…

Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping

BACKGROUND: The whole brain is often covered in [(18)F]Fluorodeoxyglucose positron emission tomography ([(18)F]FDG-PET) in oncology patients, but the covered brain abnormality is typically screened by visual interpretation without quantitative analysis in clinical practice. In this study, we aimed t...

Descripción completa

Detalles Bibliográficos
Autores principales: Whi, Wonseok, Choi, Hongyoon, Paeng, Jin Chul, Cheon, Gi Jeong, Kang, Keon Wook, Lee, Dong Soo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8590988/
https://www.ncbi.nlm.nih.gov/pubmed/34778923
http://dx.doi.org/10.1186/s40658-021-00424-0
_version_ 1784599112803418112
author Whi, Wonseok
Choi, Hongyoon
Paeng, Jin Chul
Cheon, Gi Jeong
Kang, Keon Wook
Lee, Dong Soo
author_facet Whi, Wonseok
Choi, Hongyoon
Paeng, Jin Chul
Cheon, Gi Jeong
Kang, Keon Wook
Lee, Dong Soo
author_sort Whi, Wonseok
collection PubMed
description BACKGROUND: The whole brain is often covered in [(18)F]Fluorodeoxyglucose positron emission tomography ([(18)F]FDG-PET) in oncology patients, but the covered brain abnormality is typically screened by visual interpretation without quantitative analysis in clinical practice. In this study, we aimed to develop a fully automated quantitative interpretation pipeline of brain volume from an oncology PET image. METHOD: We retrospectively collected 500 oncologic [(18)F]FDG-PET scans for training and validation of the automated brain extractor. We trained the model for extracting brain volume with two manually drawn bounding boxes on maximal intensity projection images. ResNet-50, a 2-D convolutional neural network (CNN), was used for the model training. The brain volume was automatically extracted using the CNN model and spatially normalized. For validation of the trained model and an application of this automated analytic method, we enrolled 24 subjects with small cell lung cancer (SCLC) and performed voxel-wise two-sample T test for automatic detection of metastatic lesions. RESULT: The deep learning-based brain extractor successfully identified the existence of whole-brain volume, with an accuracy of 98% for the validation set. The performance of extracting the brain measured by the intersection-over-union of 3-D bounding boxes was 72.9 ± 12.5% for the validation set. As an example of the application to automatically identify brain abnormality, this approach successfully identified the metastatic lesions in three of the four cases of SCLC patients with brain metastasis. CONCLUSION: Based on the deep learning-based model, extraction of the brain volume from whole-body PET was successfully performed. We suggest this fully automated approach could be used for the quantitative analysis of brain metabolic patterns to identify abnormalities during clinical interpretation of oncologic PET studies.
format Online
Article
Text
id pubmed-8590988
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Springer International Publishing
record_format MEDLINE/PubMed
spelling pubmed-85909882021-11-24 Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping Whi, Wonseok Choi, Hongyoon Paeng, Jin Chul Cheon, Gi Jeong Kang, Keon Wook Lee, Dong Soo EJNMMI Phys Original Research BACKGROUND: The whole brain is often covered in [(18)F]Fluorodeoxyglucose positron emission tomography ([(18)F]FDG-PET) in oncology patients, but the covered brain abnormality is typically screened by visual interpretation without quantitative analysis in clinical practice. In this study, we aimed to develop a fully automated quantitative interpretation pipeline of brain volume from an oncology PET image. METHOD: We retrospectively collected 500 oncologic [(18)F]FDG-PET scans for training and validation of the automated brain extractor. We trained the model for extracting brain volume with two manually drawn bounding boxes on maximal intensity projection images. ResNet-50, a 2-D convolutional neural network (CNN), was used for the model training. The brain volume was automatically extracted using the CNN model and spatially normalized. For validation of the trained model and an application of this automated analytic method, we enrolled 24 subjects with small cell lung cancer (SCLC) and performed voxel-wise two-sample T test for automatic detection of metastatic lesions. RESULT: The deep learning-based brain extractor successfully identified the existence of whole-brain volume, with an accuracy of 98% for the validation set. The performance of extracting the brain measured by the intersection-over-union of 3-D bounding boxes was 72.9 ± 12.5% for the validation set. As an example of the application to automatically identify brain abnormality, this approach successfully identified the metastatic lesions in three of the four cases of SCLC patients with brain metastasis. CONCLUSION: Based on the deep learning-based model, extraction of the brain volume from whole-body PET was successfully performed. We suggest this fully automated approach could be used for the quantitative analysis of brain metabolic patterns to identify abnormalities during clinical interpretation of oncologic PET studies. Springer International Publishing 2021-11-14 /pmc/articles/PMC8590988/ /pubmed/34778923 http://dx.doi.org/10.1186/s40658-021-00424-0 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Original Research
Whi, Wonseok
Choi, Hongyoon
Paeng, Jin Chul
Cheon, Gi Jeong
Kang, Keon Wook
Lee, Dong Soo
Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title_full Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title_fullStr Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title_full_unstemmed Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title_short Fully automated identification of brain abnormality from whole-body FDG-PET imaging using deep learning-based brain extraction and statistical parametric mapping
title_sort fully automated identification of brain abnormality from whole-body fdg-pet imaging using deep learning-based brain extraction and statistical parametric mapping
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8590988/
https://www.ncbi.nlm.nih.gov/pubmed/34778923
http://dx.doi.org/10.1186/s40658-021-00424-0
work_keys_str_mv AT whiwonseok fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping
AT choihongyoon fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping
AT paengjinchul fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping
AT cheongijeong fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping
AT kangkeonwook fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping
AT leedongsoo fullyautomatedidentificationofbrainabnormalityfromwholebodyfdgpetimagingusingdeeplearningbasedbrainextractionandstatisticalparametricmapping