ABSTRACT
Objective:To investigate the pseudo-CT generation from cone beam CT (CBCT) by a deep learning method for the clinical need of adaptive radiotherapy.Methods:CBCT data from 74 prostate cancer patients collected by Varian On-Board Imager and their simulated positioning CT images were used for this study. The deformable registration was implemented by MIM software. And the data were randomly divided into the training set ( n=59) and test set ( n=15). U-net, Pix2PixGAN and CycleGAN were employed to learn the mapping from CBCT to simulated positioning CT. The evaluation indexes included mean absolute error (MAE), structural similarity index (SSIM) and peak signal to noise ratio (PSNR), with the deformed CT chosen as the reference. In addition, the quality of image was analyzed separately, including soft tissue resolution, image noise and artifacts, etc. Results:The MAE of images generated by U-net, Pix2PixGAN and CycleGAN were (29.4±16.1) HU, (37.1±14.4) HU and (34.3±17.3) HU, respectively. In terms of image quality, the images generated by U-net and Pix2PixGAN had excessive blur, resulting in image distortion; while the images generated by CycleGAN retained the CBCT image structure and improved the image quality.Conclusion:CycleGAN is able to effectively improve the quality of CBCT images, and has potential to be used in adaptive radiotherapy.
ABSTRACT
Objective:To compare the abilities of different neural networks to generate pseudo-computed tomography (CT) images from magnetic resonance imaging (MRI) images and to explore the feasibility of pseudo-CT for clinical radiotherapy planning.Methods:A total of 29 brain cancer patients with planning CT and diagnostic MRI were selected. 23 of these patients were used for training neural networks and 6 for testing pseudo-CT images. Cycle-consistent generative adversarial network (cycleGAN), contrastive learning for unpaired image-to-image translation (CUT), and improved network denseCUT proposed in this study were applied to generate pseudo-CT images from MRI images. The pseudo-CT images were imported into a clinical treatment planning system to verify the feasibility of applying this method to radiotherapy planning.Results:The comparison between the generated pseudo-CT images and real CT images showed that the mean absolute errors were (72.0±6.9), (72.5±8.0), and (64.6±7.3) HU for the cycleGAN, CUT, and denseCUT, respectively. Meanwhile, the structure similarity indices were 0.91±0.01, 0.91±0.01, and 0.93±0.01, respectively. The peak signal-to-noise ratios were (28.5±0.7), (28.5±0.7), and (29.5±0.7) dB, respectively. The 2%/2 mm γ passing rates were 98.05%, 97.92%, and 98.31% for the cycleGAN, CUT, and denseCUT, respectively.Conclusions:DenseCUT can generate more accurate pseudo-CT images and the pseudo-CT can meet the demand for the dose calculation of IMRT plan.
ABSTRACT
Objective@#To study the effects of different CT values assignment methods on the dose calculation of radiotherapy plan for brain metastases, which will provide a reference for radiotherapy treatment planning based on MR images.@*Methods@#A total of 35 patients treated with radiotherapy for brain metastases were selected, with pre-treatment CT and MR simulated positioning performed at the same day. Based on the simulation CT images, three dimensional conformal radiation therapy (3D-CRT) or intensity modulated radiation therapy (IMRT) plans were calculated as the original plan (Plan1). The CT and MR images were rigidly registered and then the main tissues and organs were delineated on CT and MR images. The average CT values of each tissue and organ were calculated. Three groups of pseudo CT were generated by three CT values assignment methods based on the CT images: whole tissue was assigned 140 HU; cavity, bone and other tissues were assigned -700 HU, 700 HU and 20 HU, respectively; different tissues and organs were assigned corresponding CT values. The dose distribution of Plan1 was recalculated on three groups of pseudo-CT to obtain Plan2, Plan3 and Plan4, respectively. Finally, the dosimetric difference between Plan1 and other plans (including Plan2, Plan3 and Plan4) were compared.@*Results@#The average CT values of bone and cavity were (735.3±68.0) HU and (-723.9±27.0) HU, respectively. The average CT values of soft tissues was mostly distributed from -70 to 70 HU. The dosimetric differences between Plan2, Plan3, Plan4, and Plan1 decreased in turn. The differences of maximum dose of lens were the biggest, which can reach more than 5.0%, 1.5%-2.0% and 1.0%-1.5%, respectively, and the differences of other dose parameters were basically less than 2.0%, 1.2% and 0.8%, respectively. In the pixelwise dosimetric comparison, the areas with more than 1% difference in the local target cases were mainly distributed in the skin near the field. On the other hand, those in the whole brain target cases were mainly distributed at the bone, cavity, bone and soft tissues junction, and the skin near the field. In addition, the dose calculation error of CT value assignment methods in 3D-CRT plan was slightly larger than that in IMRT plan, and that in whole brain target cases were significantly larger than that in local target cases.@*Conclusions@#Different CT value assignment methods have a significant effect on the dose calculation of radiotherapy for brain metastases. When appropriate CT values are given to bone, air cavity and soft tissue, respectively, the deviation of dose calculation can be basically controlled within 1.2%. And by assigning mass CT values to various tissues and organs, the deviation can be further controlled within 0.8%, which can meet the clinical requirements.
ABSTRACT
Objective To study the effects of different CT values assignment methods on the dose calculation of radiotherapy plan for brain metastases,which will provide a reference for radiotherapy treatment planning based on MR images.Methods A total of 35 patients treated with radiotherapy for brain metastases were selected,with pre-treatment CT and MR simulated positioning performed at the same day.Based on the simulation CT images,three dimensional conformal radiation therapy (3D-CRT) or intensity modulated radiation therapy (IMRT) plans were calculated as the original plan (Plan1).The CT and MR images were rigidly registered and then the main tissues and organs were delineated on CT and MR images.The average CT values of each tissue and organ were calculated.Three groups of pseudo CT were generated by three CT values assignment methods based on the CT images:whole tissue was assigned 140 HU;cavity,bone and other tissues were assigned-700 HU,700 HU and 20 HU,respectively;different tissues and organs were assigned corresponding CT values.The dose distribution of Plan1 was recalculated on three groups of pseudo-CT to obtain Plan2,Plan3 and Plan4,respectively.Finally,the dosimetric difference between Plan1 and other plans (including Plan2,Plan3 and Plan4) were compared.Results The average CT values of bone and cavity were (735.3 ± 68.0) HU and (-723.9 ± 27.0) HU,respectively.The average CT values of soft tissues was mostly distributed from-70 to 70 HU.The dosimetric differences between Plan2,Plan3,Plan4,and Plan1 decreased in turn.The differences of maximum dose of lens were the biggest,which can reach more than 5.0％,1.5％-2.0％ and 1.0％-1.5％,respectively,and the differences of other dose parameters were basically less than 2.0％,1.2％and 0.8％,respectively.In the pixelwise dosimetric comparison,the areas with more than 1％ difference in the local target cases were mainly distributed in the skin near the field.On the other hand,those in the whole brain target cases were mainly distributed at the bone,cavity,bone and soft tissues junction,and the skin near the field.In addition,the dose calculation error of CT value assignment methods in 3D-CRT plan was slightly larger than that in IMRT plan,and that in whole brain target cases were significantly larger than that in local target cases.Conclusions Different CT value assignment methods have a significant effect on the dose calculation of radiotherapy for brain metastases.When appropriate CT values are given to bone,air cavity and soft tissue,respectively,the deviation of dose calculation can be basically controlled within 1.2％.And by assigning mass CT values to various tissues and organs,the deviation can be further controlled within 0.8％,which can meet the clinical requirements.
ABSTRACT
Objective An improved method for obtaining pseudo-computed tomography (CT ps) based on ultrasound deformation field.Methods The three-dimensional image data of computed tomography and ultrasound for three postoperative cervical cancer patients were selected,including the CT (CTsim) and ultrasound (USsim) images obtained during the simulated positioning stage,and the cone beam CT (CBCT) and ultrasound images obtained during the positioning verification stage of the treatment one week later.Binary masks of the OROI and OROW were created and applied in ultrasound image registration;thus,the deformation field was obtained.The deformation field was applied to CTsim images and different pseudo-CT images were obtained.Similarities between these pseudo-CT images and those of CBCT were compared,and registration accuracies between pseudo-CT images under different binary masks and CTsim were discussed.Results The averages of the correlation coefficient between pseudo-CT based on OROI,OROW,no binary mask and CBCT were 0.95,0.82 and 0.64 respectively.The average of the normalized mean square Error were 0.12,0.42 and 0.57 respectively.Conclusion The pseudo-CT based on OROI binary mask matches the best with CTsim and achieves the highest similarity with CBCT.