1
|
Yoganathan S, Aouadi S, Ahmed S, Paloor S, Torfeh T, Al-Hammadi N, Hammoud R. Generating synthetic images from cone beam computed tomography using self-attention residual UNet for head and neck radiotherapy. Phys Imaging Radiat Oncol 2023; 28:100512. [PMID: 38111501 PMCID: PMC10726231 DOI: 10.1016/j.phro.2023.100512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Revised: 11/09/2023] [Accepted: 11/09/2023] [Indexed: 12/20/2023] Open
Abstract
Background and purpose Accurate CT numbers in Cone Beam CT (CBCT) are crucial for precise dose calculations in adaptive radiotherapy (ART). This study aimed to generate synthetic CT (sCT) from CBCT using deep learning (DL) models in head and neck (HN) radiotherapy. Materials and methods A novel DL model, the 'self-attention-residual-UNet' (ResUNet), was developed for accurate sCT generation. ResUNet incorporates a self-attention mechanism in its long skip connections to enhance information transfer between the encoder and decoder. Data from 93 HN patients, each with planning CT (pCT) and first-day CBCT images were used. Model performance was evaluated using two DL approaches (non-adversarial and adversarial training) and two model types (2D axial only vs. 2.5D axial, sagittal, and coronal). ResUNet was compared with the traditional UNet through image quality assessment (Mean Absolute Error (MAE), Peak-Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM)) and dose calculation accuracy evaluation (DVH deviation and gamma evaluation (1 %/1mm)). Results Image similarity evaluation results for the 2.5D-ResUNet and 2.5D-UNet models were: MAE: 46±7 HU vs. 51±9 HU, PSNR: 66.6±2.0 dB vs. 65.8±1.8 dB, and SSIM: 0.81±0.04 vs. 0.79±0.05. There were no significant differences in dose calculation accuracy between DL models. Both models demonstrated DVH deviation below 0.5 % and a gamma-pass-rate (1 %/1mm) exceeding 97 %. Conclusions ResUNet enhanced CT number accuracy and image quality of sCT and outperformed UNet in sCT generation from CBCT. This method holds promise for generating precise sCT for HN ART.
Collapse
Affiliation(s)
- S.A. Yoganathan
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Souha Aouadi
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Sharib Ahmed
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Satheesh Paloor
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Tarraf Torfeh
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Noora Al-Hammadi
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| | - Rabih Hammoud
- Department of Radiation Oncology, National Center for Cancer Care & Research (NCCCR), Hamad Medical Corporation, Doha, Qatar
| |
Collapse
|
2
|
Chang Y, Liang Y, Yang B, Qiu J, Pei X, Xu XG. Dosimetric comparison of deformable image registration and synthetic CT generation based on CBCT images for organs at risk in cervical cancer radiotherapy. Radiat Oncol 2023; 18:3. [PMID: 36604687 PMCID: PMC9817400 DOI: 10.1186/s13014-022-02191-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Accepted: 12/27/2022] [Indexed: 01/07/2023] Open
Abstract
OBJECTIVE Anatomical variations existing in cervical cancer radiotherapy treatment can be monitored by cone-beam computed tomography (CBCT) images. Deformable image registration (DIR) from planning CT (pCT) to CBCT images and synthetic CT (sCT) image generation based on CBCT are two methods for improving the quality of CBCT images. This study aims to compare the accuracy of these two approaches geometrically and dosimetrically in cervical cancer radiotherapy. METHODS In this study, 40 paired pCT-CBCT images were collected to evaluate the accuracy of DIR and sCT generation. The DIR method was based on a 3D multistage registration network that was trained with 150 paired pCT-CBCT images, and the sCT generation method was performed based on a 2D cycle-consistent adversarial network (CycleGAN) with 6000 paired pCT-CBCT slices for training. Then, the doses were recalculated with the CBCT, pCT, deformed pCT (dpCT) and sCT images by a GPU-based Monte Carlo dose code, ArcherQA, to obtain DoseCBCT, DosepCT, DosedpCT and DosesCT. Organs at risk (OARs) included small intestine, rectum, bladder, spinal cord, femoral heads and bone marrow, CBCT and pCT contours were delineated manually, dpCT contours were propagated through deformation vector fields, sCT contours were auto-segmented and corrected manually. RESULTS The global gamma pass rate of DosesCT and DosedpCT was 99.66% ± 0.34%, while that of DoseCBCT and DosedpCT was 85.92% ± 7.56% at the 1%/1 mm criterion and a low-dose threshold of 10%. Based on DosedpCT as uniform dose distribution, there were comparable errors in femoral heads and bone marrow for the dpCT and sCT contours compared with CBCT contours, while sCT contours had lower errors in small intestine, rectum, bladder and spinal cord, especially for those with large volume difference of pCT and CBCT. CONCLUSIONS For cervical cancer radiotherapy, the DIR method and sCT generation could produce similar precise dose distributions, but sCT contours had higher accuracy when the difference in planning CT and CBCT was large.
Collapse
Affiliation(s)
- Yankui Chang
- grid.59053.3a0000000121679639School of Nuclear Science and Technology, University of Science and Technology of China, Hefei, China
| | - Yongguang Liang
- grid.506261.60000 0001 0706 7839Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College Hospital, Beijing, China
| | - Bo Yang
- grid.506261.60000 0001 0706 7839Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College Hospital, Beijing, China
| | - Jie Qiu
- grid.506261.60000 0001 0706 7839Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College Hospital, Beijing, China
| | - Xi Pei
- grid.59053.3a0000000121679639School of Nuclear Science and Technology, University of Science and Technology of China, Hefei, China ,Technology Development Department, Anhui Wisdom Technology Co., Ltd., Hefei, China
| | - Xie George Xu
- grid.59053.3a0000000121679639School of Nuclear Science and Technology, University of Science and Technology of China, Hefei, China ,grid.411395.b0000 0004 1757 0085Department of Radiation Oncology, First Affiliated Hospital of University of Science and Technology of China, Hefei, China
| |
Collapse
|
3
|
Dong G, Zhang C, Liang X, Deng L, Zhu Y, Zhu X, Zhou X, Song L, Zhao X, Xie Y. A Deep Unsupervised Learning Model for Artifact Correction of Pelvis Cone-Beam CT. Front Oncol 2021; 11:686875. [PMID: 34350115 PMCID: PMC8327750 DOI: 10.3389/fonc.2021.686875] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2021] [Accepted: 06/25/2021] [Indexed: 11/13/2022] Open
Abstract
Purpose In recent years, cone-beam computed tomography (CBCT) is increasingly used in adaptive radiation therapy (ART). However, compared with planning computed tomography (PCT), CBCT image has much more noise and imaging artifacts. Therefore, it is necessary to improve the image quality and HU accuracy of CBCT. In this study, we developed an unsupervised deep learning network (CycleGAN) model to calibrate CBCT images for the pelvis to extend potential clinical applications in CBCT-guided ART. Methods To train CycleGAN to generate synthetic PCT (sPCT), we used CBCT and PCT images as inputs from 49 patients with unpaired data. Additional deformed PCT (dPCT) images attained as CBCT after deformable registration are utilized as the ground truth before evaluation. The trained uncorrected CBCT images are converted into sPCT images, and the obtained sPCT images have the characteristics of PCT images while keeping the anatomical structure of CBCT images unchanged. To demonstrate the effectiveness of the proposed CycleGAN, we use additional nine independent patients for testing. Results We compared the sPCT with dPCT images as the ground truth. The average mean absolute error (MAE) of the whole image on testing data decreased from 49.96 ± 7.21HU to 14.6 ± 2.39HU, the average MAE of fat and muscle ROIs decreased from 60.23 ± 7.3HU to 16.94 ± 7.5HU, and from 53.16 ± 9.1HU to 13.03 ± 2.63HU respectively. Conclusion We developed an unsupervised learning method to generate high-quality corrected CBCT images (sPCT). Through further evaluation and clinical implementation, it can replace CBCT in ART.
Collapse
Affiliation(s)
- Guoya Dong
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China.,Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Hebei University of Technology, Tianjin, China
| | - Chenglong Zhang
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China.,Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, Hebei University of Technology, Tianjin, China.,Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Xiaokun Liang
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Lei Deng
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Yulin Zhu
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Xuanyu Zhu
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Xuanru Zhou
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Liming Song
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Xiang Zhao
- Department of Radiology, Tianjin Medical University General Hospital, Tianjin, China
| | - Yaoqin Xie
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| |
Collapse
|
4
|
Barateau A, De Crevoisier R, Largent A, Mylona E, Perichon N, Castelli J, Chajon E, Acosta O, Simon A, Nunes JC, Lafond C. Comparison of CBCT-based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning. Med Phys 2020; 47:4683-4693. [PMID: 32654160 DOI: 10.1002/mp.14387] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Revised: 06/16/2020] [Accepted: 06/23/2020] [Indexed: 01/26/2023] Open
Abstract
PURPOSE Anatomical variations occur during head and neck (H&N) radiotherapy treatment. kV cone-beam computed tomography (CBCT) images can be used for daily dose monitoring to assess dose variations owing to anatomic changes. Deep learning methods (DLMs) have recently been proposed to generate pseudo-CT (pCT) from CBCT to perform dose calculation. This study aims to evaluate the accuracy of a DLM and to compare this method with three existing methods of dose calculation from CBCT in H&N cancer radiotherapy. METHODS Forty-four patients received VMAT for H&N cancer (70-63-56 Gy). For each patient, reference CT (Bigbore, Philips) and CBCT images (XVI, Elekta) were acquired. The DLM was based on a generative adversarial network. The three compared methods were: (a) a method using a density to Hounsfield Unit (HU) relation from phantom CBCT image (HU-D curve method), (b) a water-air-bone density assignment method (DAM), and iii) a method using deformable image registration (DIR). The imaging endpoints were the mean absolute error (MAE) and mean error (ME) of HU from pCT and reference CT (CTref ). The dosimetric endpoints were dose discrepancies and 3D gamma analyses (local, 2%/2 mm, 30% dose threshold). Dose discrepancies were defined as the mean absolute differences between DVHs calculated from the CTref and pCT of each method. RESULTS In the entire body, the MAEs and MEs of the DLM, HU-D curve method, DAM, and DIR method were 82.4 and 17.1 HU, 266.6 and 208.9 HU, 113.2 and 14.2 HU, and 95.5 and -36.6 HU, respectively. The MAE obtained using the DLM differed significantly from those of other methods (Wilcoxon, P ≤ 0.05). The DLM dose discrepancies were 7 ± 8 cGy (maximum = 44 cGy) for the ipsilateral parotid gland Dmean and 5 ± 6 cGy (max = 26 cGy) for the contralateral parotid gland mean dose (Dmean ). For the parotid gland Dmean , no significant dose difference was observed between the DLM and other methods. The mean 3D gamma pass rate ± standard deviation was 98.1 ± 1.2%, 91.0 ± 5.3%, 97.9 ± 1.6%, and 98.8 ± 0.7% for the DLM, HU-D method, DAM, and DIR method, respectively. The gamma pass rates and mean gamma results of the HU-D curve method, DAM, and DIR method differed significantly from those of the DLM. CONCLUSIONS For H&N radiotherapy, DIR method and DLM appears as the most appealing CBCT-based dose calculation methods among the four methods in terms of dose accuracy as well as calculation time. Using the DIR method or DLM with CBCT images enables dose monitoring in the parotid glands during the treatment course and may be used to trigger replanning.
Collapse
Affiliation(s)
- Anaïs Barateau
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Renaud De Crevoisier
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Axel Largent
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Eugenia Mylona
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Nicolas Perichon
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Joël Castelli
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Enrique Chajon
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Oscar Acosta
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Antoine Simon
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Jean-Claude Nunes
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| | - Caroline Lafond
- Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France
| |
Collapse
|