Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network

Chih Chia Chen, Ting Yu Su, Wei Tse Yang, Tsu Chi Cheng, Yi Fei He, Cheng-Li Lin, Yu-Hua Dean Fang

研究成果: Conference contribution

摘要

In this study, a new computer-aided system was proposed to automatically reconstruct the spine model. The bi-planar EOS X-ray imaging was adopted as the scanning technology, which is capable of a simultaneous capture of bi-planar X-ray images by slot scanning of the whole body using ultra-low radiation doses. High quality and high contrast anteroposterior (AP) and lateral (LAT) X-ray images will be acquired during scanning period and these two radiographs enable a precise three-dimensional reconstruction of vertebrae, pelvis and other parts of the skeletal system. To overcome the timeconsuming issue of spine reconstruction using EOS system, a generative adversarial network (GAN) was applied to reconstruct the entire spine model, which is consist of generator and discriminator and training by unsupervised learning approach. Nowadays, GAN model has already been adopted in the transformation from 2D image to 3D scenes. Therefore, our approach represents a potential alternative for EOS reconstruction while still maintaining a clinically acceptable diagnostic accuracy.

原文English
主出版物標題International Forum on Medical Imaging in Asia 2019
編輯Hiroshi Fujita, Feng Lin, Jong Hyo Kim
發行者SPIE
ISBN(電子)9781510627758
DOIs
出版狀態Published - 2019 一月 1
事件International Forum on Medical Imaging in Asia 2019 - Singapore, Singapore
持續時間: 2019 一月 72019 一月 9

出版系列

名字Proceedings of SPIE - The International Society for Optical Engineering
11050
ISSN(列印)0277-786X
ISSN(電子)1996-756X

Conference

ConferenceInternational Forum on Medical Imaging in Asia 2019
國家Singapore
城市Singapore
期間19-01-0719-01-09

指紋

spine
Spine
Scanning
X rays
scanning
vertebrae
Diagnostic Accuracy
Three-dimensional Reconstruction
X-ray Imaging
pelvis
Unsupervised learning
x rays
discriminators
Discriminators
Generative Models
Unsupervised Learning
slots
learning
Network Model
Dosimetry

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

引用此文

Chen, C. C., Su, T. Y., Yang, W. T., Cheng, T. C., He, Y. F., Lin, C-L., & Fang, Y-H. D. (2019). Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network. 於 H. Fujita, F. Lin, & J. H. Kim (編輯), International Forum on Medical Imaging in Asia 2019 [110500T] (Proceedings of SPIE - The International Society for Optical Engineering; 卷 11050). SPIE. https://doi.org/10.1117/12.2521601
Chen, Chih Chia ; Su, Ting Yu ; Yang, Wei Tse ; Cheng, Tsu Chi ; He, Yi Fei ; Lin, Cheng-Li ; Fang, Yu-Hua Dean. / Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network. International Forum on Medical Imaging in Asia 2019. 編輯 / Hiroshi Fujita ; Feng Lin ; Jong Hyo Kim. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{508d6581ff5144958d2c4e50f893ed9f,
title = "Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network",
abstract = "In this study, a new computer-aided system was proposed to automatically reconstruct the spine model. The bi-planar EOS X-ray imaging was adopted as the scanning technology, which is capable of a simultaneous capture of bi-planar X-ray images by slot scanning of the whole body using ultra-low radiation doses. High quality and high contrast anteroposterior (AP) and lateral (LAT) X-ray images will be acquired during scanning period and these two radiographs enable a precise three-dimensional reconstruction of vertebrae, pelvis and other parts of the skeletal system. To overcome the timeconsuming issue of spine reconstruction using EOS system, a generative adversarial network (GAN) was applied to reconstruct the entire spine model, which is consist of generator and discriminator and training by unsupervised learning approach. Nowadays, GAN model has already been adopted in the transformation from 2D image to 3D scenes. Therefore, our approach represents a potential alternative for EOS reconstruction while still maintaining a clinically acceptable diagnostic accuracy.",
author = "Chen, {Chih Chia} and Su, {Ting Yu} and Yang, {Wei Tse} and Cheng, {Tsu Chi} and He, {Yi Fei} and Cheng-Li Lin and Fang, {Yu-Hua Dean}",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2521601",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Hiroshi Fujita and Feng Lin and Kim, {Jong Hyo}",
booktitle = "International Forum on Medical Imaging in Asia 2019",
address = "United States",

}

Chen, CC, Su, TY, Yang, WT, Cheng, TC, He, YF, Lin, C-L & Fang, Y-HD 2019, Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network. 於 H Fujita, F Lin & JH Kim (編輯), International Forum on Medical Imaging in Asia 2019., 110500T, Proceedings of SPIE - The International Society for Optical Engineering, 卷 11050, SPIE, International Forum on Medical Imaging in Asia 2019, Singapore, Singapore, 19-01-07. https://doi.org/10.1117/12.2521601

Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network. / Chen, Chih Chia; Su, Ting Yu; Yang, Wei Tse; Cheng, Tsu Chi; He, Yi Fei; Lin, Cheng-Li; Fang, Yu-Hua Dean.

International Forum on Medical Imaging in Asia 2019. 編輯 / Hiroshi Fujita; Feng Lin; Jong Hyo Kim. SPIE, 2019. 110500T (Proceedings of SPIE - The International Society for Optical Engineering; 卷 11050).

研究成果: Conference contribution

TY - GEN

T1 - Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network

AU - Chen, Chih Chia

AU - Su, Ting Yu

AU - Yang, Wei Tse

AU - Cheng, Tsu Chi

AU - He, Yi Fei

AU - Lin, Cheng-Li

AU - Fang, Yu-Hua Dean

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this study, a new computer-aided system was proposed to automatically reconstruct the spine model. The bi-planar EOS X-ray imaging was adopted as the scanning technology, which is capable of a simultaneous capture of bi-planar X-ray images by slot scanning of the whole body using ultra-low radiation doses. High quality and high contrast anteroposterior (AP) and lateral (LAT) X-ray images will be acquired during scanning period and these two radiographs enable a precise three-dimensional reconstruction of vertebrae, pelvis and other parts of the skeletal system. To overcome the timeconsuming issue of spine reconstruction using EOS system, a generative adversarial network (GAN) was applied to reconstruct the entire spine model, which is consist of generator and discriminator and training by unsupervised learning approach. Nowadays, GAN model has already been adopted in the transformation from 2D image to 3D scenes. Therefore, our approach represents a potential alternative for EOS reconstruction while still maintaining a clinically acceptable diagnostic accuracy.

AB - In this study, a new computer-aided system was proposed to automatically reconstruct the spine model. The bi-planar EOS X-ray imaging was adopted as the scanning technology, which is capable of a simultaneous capture of bi-planar X-ray images by slot scanning of the whole body using ultra-low radiation doses. High quality and high contrast anteroposterior (AP) and lateral (LAT) X-ray images will be acquired during scanning period and these two radiographs enable a precise three-dimensional reconstruction of vertebrae, pelvis and other parts of the skeletal system. To overcome the timeconsuming issue of spine reconstruction using EOS system, a generative adversarial network (GAN) was applied to reconstruct the entire spine model, which is consist of generator and discriminator and training by unsupervised learning approach. Nowadays, GAN model has already been adopted in the transformation from 2D image to 3D scenes. Therefore, our approach represents a potential alternative for EOS reconstruction while still maintaining a clinically acceptable diagnostic accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85063897588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063897588&partnerID=8YFLogxK

U2 - 10.1117/12.2521601

DO - 10.1117/12.2521601

M3 - Conference contribution

AN - SCOPUS:85063897588

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Forum on Medical Imaging in Asia 2019

A2 - Fujita, Hiroshi

A2 - Lin, Feng

A2 - Kim, Jong Hyo

PB - SPIE

ER -

Chen CC, Su TY, Yang WT, Cheng TC, He YF, Lin C-L 等. Reconstruction of the spine structure with bi-planar x-ray images using the generative adversarial network. 於 Fujita H, Lin F, Kim JH, 編輯, International Forum on Medical Imaging in Asia 2019. SPIE. 2019. 110500T. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2521601