Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images

Abstract Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have bee...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kazutoshi Ukai, Rashedur Rahman, Naomi Yagi, Keigo Hayashi, Akihiro Maruo, Hirotsugu Muratsu, Syoji Kobashi
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9cb7536b26cf47998aabcaf4303085c6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9cb7536b26cf47998aabcaf4303085c6
record_format dspace
spelling oai:doaj.org-article:9cb7536b26cf47998aabcaf4303085c62021-12-02T17:51:06ZDetecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images10.1038/s41598-021-91144-z2045-2322https://doaj.org/article/9cb7536b26cf47998aabcaf4303085c62021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91144-zhttps://doaj.org/toc/2045-2322Abstract Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%).Kazutoshi UkaiRashedur RahmanNaomi YagiKeigo HayashiAkihiro MaruoHirotsugu MuratsuSyoji KobashiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Kazutoshi Ukai
Rashedur Rahman
Naomi Yagi
Keigo Hayashi
Akihiro Maruo
Hirotsugu Muratsu
Syoji Kobashi
Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
description Abstract Pelvic fracture is one of the leading causes of death in the elderly, carrying a high risk of death within 1 year of fracture. This study proposes an automated method to detect pelvic fractures on 3-dimensional computed tomography (3D-CT). Deep convolutional neural networks (DCNNs) have been used for lesion detection on 2D and 3D medical images. However, training a DCNN directly using 3D images is complicated, computationally costly, and requires large amounts of training data. We propose a method that evaluates multiple, 2D, real-time object detection systems (YOLOv3 models) in parallel, in which each YOLOv3 model is trained using differently orientated 2D slab images reconstructed from 3D-CT. We assume that an appropriate reconstruction orientation would exist to optimally characterize image features of bone fractures on 3D-CT. Multiple YOLOv3 models in parallel detect 2D fracture candidates in different orientations simultaneously. The 3D fracture region is then obtained by integrating the 2D fracture candidates. The proposed method was validated in 93 subjects with bone fractures. Area under the curve (AUC) was 0.824, with 0.805 recall and 0.907 precision. The AUC with a single orientation was 0.652. This method was then applied to 112 subjects without bone fractures to evaluate over-detection. The proposed method successfully detected no bone fractures in all except 4 non-fracture subjects (96.4%).
format article
author Kazutoshi Ukai
Rashedur Rahman
Naomi Yagi
Keigo Hayashi
Akihiro Maruo
Hirotsugu Muratsu
Syoji Kobashi
author_facet Kazutoshi Ukai
Rashedur Rahman
Naomi Yagi
Keigo Hayashi
Akihiro Maruo
Hirotsugu Muratsu
Syoji Kobashi
author_sort Kazutoshi Ukai
title Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
title_short Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
title_full Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
title_fullStr Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
title_full_unstemmed Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images
title_sort detecting pelvic fracture on 3d-ct using deep convolutional neural networks with multi-orientated slab images
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/9cb7536b26cf47998aabcaf4303085c6
work_keys_str_mv AT kazutoshiukai detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT rashedurrahman detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT naomiyagi detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT keigohayashi detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT akihiromaruo detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT hirotsugumuratsu detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
AT syojikobashi detectingpelvicfractureon3dctusingdeepconvolutionalneuralnetworkswithmultiorientatedslabimages
_version_ 1718379301172150272