Image correction for cone-beam computed tomography simulator using neural network corrector
In this article, a neural network corrector is proposed to correct the image shift, yielding the degradation of three-dimensional image reconstruction, for each slice captured by cone-beam computed tomography simulator. There are 3 degrees of freedom in tube module of simulator; the central point of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2017-02-01
|
| Series: | Advances in Mechanical Engineering |
| Online Access: | https://doi.org/10.1177/1687814017690476 |
| _version_ | 1818059574329999360 |
|---|---|
| author | Chin-Sheng Chen Cheng-Yi Hsu Shih-Kang Chen Chih-Jer Lin Ching-Hao Hsieh Yi-Hung Liu |
| author_facet | Chin-Sheng Chen Cheng-Yi Hsu Shih-Kang Chen Chih-Jer Lin Ching-Hao Hsieh Yi-Hung Liu |
| author_sort | Chin-Sheng Chen |
| collection | DOAJ |
| description | In this article, a neural network corrector is proposed to correct the image shift, yielding the degradation of three-dimensional image reconstruction, for each slice captured by cone-beam computed tomography simulator. There are 3 degrees of freedom in tube module of simulator; the central point of tube module should be aligned with the central point of detector module to guarantee the accurate image projection. However, the mechanism manufacturing and assembling tolerance will let the above aim cannot be met. Here, a standard kit is made to measure the image shift by 1° step from −10° to 10°. The measure data will be the input training data of proposed neural network corrector, and the corrected translation position will be the output of neural network corrector. The Levenberg–Marquardt learning algorithm adjusts the connected weights and biases of the neural network using a supervised gradient descent method, such that the defined error function can be minimized. To avoid the problem of overfitting and improve the generalized ability of the neural network, Bayesian regularization is added to the Levenberg–Marquardt learning algorithm. After the training of neural network corrector, the different target position commands are fed into the neural network corrector. Then, the corrected data from neural network corrector are fed to be the new position command to verify the image correction performance. Moreover, a phantom kit is made to check the corrected performance of the neural network corrector. Finally, the experimental results verify that the image shift can be reduced by the neural network corrector. |
| first_indexed | 2024-12-10T13:18:41Z |
| format | Article |
| id | doaj.art-fed4839d4eb544c2b2f0c12193f795b9 |
| institution | Directory Open Access Journal |
| issn | 1687-8140 |
| language | English |
| last_indexed | 2024-12-10T13:18:41Z |
| publishDate | 2017-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Advances in Mechanical Engineering |
| spelling | doaj.art-fed4839d4eb544c2b2f0c12193f795b92022-12-22T01:47:25ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402017-02-01910.1177/1687814017690476Image correction for cone-beam computed tomography simulator using neural network correctorChin-Sheng Chen0Cheng-Yi Hsu1Shih-Kang Chen2Chih-Jer Lin3Ching-Hao Hsieh4Yi-Hung Liu5Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, TaiwanGraduate Institute of Automation Technology, National Taipei University of Technology, Taipei, TaiwanGraduate Institute of Automation Technology, National Taipei University of Technology, Taipei, TaiwanGraduate Institute of Automation Technology, National Taipei University of Technology, Taipei, TaiwanSwissray Asia Healthcare Co., Ltd, Taipei, TaiwanDepartment of Mechanical Engineering, National Taipei University of Technology, Taipei, TaiwanIn this article, a neural network corrector is proposed to correct the image shift, yielding the degradation of three-dimensional image reconstruction, for each slice captured by cone-beam computed tomography simulator. There are 3 degrees of freedom in tube module of simulator; the central point of tube module should be aligned with the central point of detector module to guarantee the accurate image projection. However, the mechanism manufacturing and assembling tolerance will let the above aim cannot be met. Here, a standard kit is made to measure the image shift by 1° step from −10° to 10°. The measure data will be the input training data of proposed neural network corrector, and the corrected translation position will be the output of neural network corrector. The Levenberg–Marquardt learning algorithm adjusts the connected weights and biases of the neural network using a supervised gradient descent method, such that the defined error function can be minimized. To avoid the problem of overfitting and improve the generalized ability of the neural network, Bayesian regularization is added to the Levenberg–Marquardt learning algorithm. After the training of neural network corrector, the different target position commands are fed into the neural network corrector. Then, the corrected data from neural network corrector are fed to be the new position command to verify the image correction performance. Moreover, a phantom kit is made to check the corrected performance of the neural network corrector. Finally, the experimental results verify that the image shift can be reduced by the neural network corrector.https://doi.org/10.1177/1687814017690476 |
| spellingShingle | Chin-Sheng Chen Cheng-Yi Hsu Shih-Kang Chen Chih-Jer Lin Ching-Hao Hsieh Yi-Hung Liu Image correction for cone-beam computed tomography simulator using neural network corrector Advances in Mechanical Engineering |
| title | Image correction for cone-beam computed tomography simulator using neural network corrector |
| title_full | Image correction for cone-beam computed tomography simulator using neural network corrector |
| title_fullStr | Image correction for cone-beam computed tomography simulator using neural network corrector |
| title_full_unstemmed | Image correction for cone-beam computed tomography simulator using neural network corrector |
| title_short | Image correction for cone-beam computed tomography simulator using neural network corrector |
| title_sort | image correction for cone beam computed tomography simulator using neural network corrector |
| url | https://doi.org/10.1177/1687814017690476 |
| work_keys_str_mv | AT chinshengchen imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector AT chengyihsu imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector AT shihkangchen imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector AT chihjerlin imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector AT chinghaohsieh imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector AT yihungliu imagecorrectionforconebeamcomputedtomographysimulatorusingneuralnetworkcorrector |