Cargando…
MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction
BACKGROUND: Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstr...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8073969/ https://www.ncbi.nlm.nih.gov/pubmed/33902457 http://dx.doi.org/10.1186/s12859-020-03936-1 |
_version_ | 1783684250652901376 |
---|---|
author | Han, Changhee Rundo, Leonardo Murao, Kohei Noguchi, Tomoyuki Shimahara, Yuki Milacski, Zoltán Ádám Koshino, Saori Sala, Evis Nakayama, Hideki Satoh, Shin’ichi |
author_facet | Han, Changhee Rundo, Leonardo Murao, Kohei Noguchi, Tomoyuki Shimahara, Yuki Milacski, Zoltán Ádám Koshino, Saori Sala, Evis Nakayama, Hideki Satoh, Shin’ichi |
author_sort | Han, Changhee |
collection | PubMed |
description | BACKGROUND: Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer’s disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. RESULTS: We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 [Formula: see text] loss—trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones—reconstructs unseen healthy/abnormal scans; (Diagnosis) Average [Formula: see text] loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. CONCLUSIONS: Similar to physicians’ way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans. |
format | Online Article Text |
id | pubmed-8073969 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-80739692021-04-26 MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction Han, Changhee Rundo, Leonardo Murao, Kohei Noguchi, Tomoyuki Shimahara, Yuki Milacski, Zoltán Ádám Koshino, Saori Sala, Evis Nakayama, Hideki Satoh, Shin’ichi BMC Bioinformatics Research BACKGROUND: Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer’s disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. RESULTS: We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 [Formula: see text] loss—trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones—reconstructs unseen healthy/abnormal scans; (Diagnosis) Average [Formula: see text] loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. CONCLUSIONS: Similar to physicians’ way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans. BioMed Central 2021-04-26 /pmc/articles/PMC8073969/ /pubmed/33902457 http://dx.doi.org/10.1186/s12859-020-03936-1 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/) . The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/ (https://creativecommons.org/publicdomain/zero/1.0/) ) applies to the data made available in this article, unless otherwise stated in a credit line to the data. |
spellingShingle | Research Han, Changhee Rundo, Leonardo Murao, Kohei Noguchi, Tomoyuki Shimahara, Yuki Milacski, Zoltán Ádám Koshino, Saori Sala, Evis Nakayama, Hideki Satoh, Shin’ichi MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title | MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title_full | MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title_fullStr | MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title_full_unstemmed | MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title_short | MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction |
title_sort | madgan: unsupervised medical anomaly detection gan using multiple adjacent brain mri slice reconstruction |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8073969/ https://www.ncbi.nlm.nih.gov/pubmed/33902457 http://dx.doi.org/10.1186/s12859-020-03936-1 |
work_keys_str_mv | AT hanchanghee madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT rundoleonardo madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT muraokohei madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT noguchitomoyuki madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT shimaharayuki madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT milacskizoltanadam madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT koshinosaori madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT salaevis madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT nakayamahideki madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction AT satohshinichi madganunsupervisedmedicalanomalydetectionganusingmultipleadjacentbrainmrislicereconstruction |