Cargando…
Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer
Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with mu...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8788419/ https://www.ncbi.nlm.nih.gov/pubmed/35076612 http://dx.doi.org/10.3390/tomography8010011 |
_version_ | 1784639559697432576 |
---|---|
author | Takahashi, Kanae Fujioka, Tomoyuki Oyama, Jun Mori, Mio Yamaga, Emi Yashima, Yuka Imokawa, Tomoki Hayashi, Atsushi Kujiraoka, Yu Tsuchiya, Junichi Oda, Goshi Nakagawa, Tsuyoshi Tateishi, Ukihide |
author_facet | Takahashi, Kanae Fujioka, Tomoyuki Oyama, Jun Mori, Mio Yamaga, Emi Yashima, Yuka Imokawa, Tomoki Hayashi, Atsushi Kujiraoka, Yu Tsuchiya, Junichi Oda, Goshi Nakagawa, Tsuyoshi Tateishi, Ukihide |
author_sort | Takahashi, Kanae |
collection | PubMed |
description | Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future. |
format | Online Article Text |
id | pubmed-8788419 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-87884192022-01-26 Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer Takahashi, Kanae Fujioka, Tomoyuki Oyama, Jun Mori, Mio Yamaga, Emi Yashima, Yuka Imokawa, Tomoki Hayashi, Atsushi Kujiraoka, Yu Tsuchiya, Junichi Oda, Goshi Nakagawa, Tsuyoshi Tateishi, Ukihide Tomography Article Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future. MDPI 2022-01-05 /pmc/articles/PMC8788419/ /pubmed/35076612 http://dx.doi.org/10.3390/tomography8010011 Text en © 2022 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 Takahashi, Kanae Fujioka, Tomoyuki Oyama, Jun Mori, Mio Yamaga, Emi Yashima, Yuka Imokawa, Tomoki Hayashi, Atsushi Kujiraoka, Yu Tsuchiya, Junichi Oda, Goshi Nakagawa, Tsuyoshi Tateishi, Ukihide Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title | Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title_full | Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title_fullStr | Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title_full_unstemmed | Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title_short | Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer |
title_sort | deep learning using multiple degrees of maximum-intensity projection for pet/ct image classification in breast cancer |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8788419/ https://www.ncbi.nlm.nih.gov/pubmed/35076612 http://dx.doi.org/10.3390/tomography8010011 |
work_keys_str_mv | AT takahashikanae deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT fujiokatomoyuki deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT oyamajun deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT morimio deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT yamagaemi deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT yashimayuka deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT imokawatomoki deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT hayashiatsushi deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT kujiraokayu deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT tsuchiyajunichi deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT odagoshi deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT nakagawatsuyoshi deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer AT tateishiukihide deeplearningusingmultipledegreesofmaximumintensityprojectionforpetctimageclassificationinbreastcancer |