A prior-information-based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer.

OBJECTIVE: Adaptive planning to accommodate anatomic changes during treatment often requires repeated segmentation. In this study, prior patient-specific data was integrateda into a registration-guided multi-channel multi-path (Rg-MCMP) segmentation framework to improve the accuracy of repeated clinical target volume (CTV) segmentation. METHODS: This study was based on CT image datasets for a total of 90 cervical cancer patients who received two courses of radiotherapy. A total of 15 patients were selected randomly as the test set. In the Rg-MCMP segmentation framework, the first-course CT images (CT1) were registered to second-course CT images (CT2) to yield aligned CT images (aCT1), and the CTV in the first course (CTV1) was propagated to yield aligned CTV contours (aCTV1). Then, aCT1, aCTV1, and CT2 were combined as the inputs for 3D U-Net consisting of a channel-based multi-path feature extraction network. The performance of the Rg-MCMP segmentation framework was evaluated and compared with the single-channel single-path model (SCSP), the standalone registration methods, and the registration-guided multi-channel single-path (Rg-MCSP) model. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) were used as the metrics. RESULTS: The average DSC of CTV for the deformable image DIR-MCMP model was found to be 0.892, greater than that of the standalone DIR (0.856), SCSP (0.837), and DIR-MCSP (0.877), which were improvements of 4.2%, 6.6%, and 1.7%, respectively. Similarly, the rigid body DIR-MCMP model yielded an average DSC of 0.875, which exceeded standalone RB (0.787), SCSP (0.837), and registration-guided multi-channel single-path (0.848), which were improvements of 11.2%, 4.5%, and 3.2%, respectively. These improvements in DSC were statistically significant (p < 0.05). CONCLUSION: The proposed Rg-MCMP framework achieved excellent accuracy in CTV segmentation as part of the adaptive radiotherapy workflow.

Prospects for daily online adaptive radiotherapy for cervical cancer: Auto-contouring evaluation and dosimetric outcomes.

BACKGROUND: Training senior radiation therapists as "adapters" to manage influencers and target editing is critical in daily online adaptive radiotherapy (oART) for cervical cancer. The purpose of this study was to evaluate the accuracy and dosimetric outcomes of automatic contouring and identify the key areas for modification. METHODS: A total of 125 oART fractions from five postoperative cervical cancer patients and 140 oART fractions from five uterine cervical cancer patients treated with daily iCBCT-guided oART were enrolled in this prospective study. The same adaptive treatments were replanned using the Ethos automatic contours workflow without manual contouring edits. The clinical target volume (CTV) was subdivided into several separate regions, and the average surface distance dice (ASD), centroid deviation, dice similarity coefficient (DSC), and 95% Hausdorff distance (95% HD) were used to evaluate contouring for the above portions. Dosimetric results from automatic oART plans were compared to supervised oART plans to evaluate target volumes and organs at risk (OARs) dose changes. RESULTS: Overall, the paired CTV had high overlap rates, with an average DSC value greater than 0.75. The uterus had the largest consistency differences, with ASD, centroid deviation, and 95% HD being 2.67 ± 1.79 mm, 17.17 ± 12 mm, and 10.45 ± 5.68 mm, respectively. The consistency differences of the lower nodal CTVleft and nodal CTVright were relatively large, with ASD, centroid deviation, and 95% HD being 0.59 ± 0.53 mm, 3.6 ± 2.67 mm, and 5.41 ± 4.08 mm, and 0.59 ± 0.51 mm, 3.6 ± 2.54 mm, and 4.7 ± 1.57 mm, respectively. The automatic online-adapted plan met the clinical requirements of dosimetric coverage for the target volume and improved the OAR dosimetry. CONCLUSIONS: The accuracy of automatic contouring from the Ethos adaptive platform is considered clinically acceptable for cervical cancer, and the uterus, upper vaginal cuff, and lower nodal CTV are the areas that need to be focused on in training.

Improving synthetic CT accuracy by combining the benefits of multiple normalized preprocesses.

PURPOSE: To investigate the effect of different normalization preprocesses in deep learning on the accuracy of different tissues in synthetic computed tomography (sCT) and to combine their advantages to improve the accuracy of all tissues. METHODS: The cycle-consistent adversarial network (CycleGAN) model was used to generate sCT images from megavolt cone-beam CT (MVCBCT) images. In this study, 2639 head MVCBCT and CT image pairs from 203 patients were collected as a training set, and 249 image pairs from 29 patients were collected as a test set. We normalized the voxel values in images to 0 to 1 or -1 to 1, using two linear and five nonlinear normalization preprocessing methods to obtain seven data sets and compared the accuracy of different tissues in different sCT obtained from training these data. Finally, to combine the advantages of different normalization preprocessing methods, we obtained sCT_Blur by cropping, stitching, and smoothing (OpenCV's cv2.medianBlur, kernel size 5) each group of sCTs and evaluated its image quality and accuracy of OARs. RESULTS: Different normalization preprocesses made sCT more accurate in different tissues. The proposed sCT_Blur took advantage of multiple normalization preprocessing methods, and all tissues are more accurate than the sCT obtained using a single conventional normalization method. Compared with other sCT images, the structural similarity of sCT_Blur versus CT was improved to 0.906 ± 0.019. The mean absolute errors of the CT numbers were reduced to 15.7 ± 4.1 HU, 23.2 ± 7.1 HU, 11.5 ± 4.1 HU, 212.8 ± 104.6 HU, 219.4 ± 35.1 HU, and 268.8 ± 88.8 HU for the oral cavity, parotid, spinal cord, cavity, mandible, and teeth, respectively. CONCLUSION: The proposed approach combined the advantages of several normalization preprocessing methods to improve the accuracy of all tissues in sCT images, which is promising for improving the accuracy of dose calculations based on CBCT images in adaptive radiotherapy.

Innovative integration of augmented reality and optical surface imaging: A coarse-to-precise system for radiotherapy positioning.

BACKGROUND: Traditional methods of radiotherapy positioning have shortcomings such as fragile skin-markers, additional doses, and lack of information integration. Emerging technologies may provide alternatives for the relevant clinical practice. PURPOSE: To propose a noninvasive radiotherapy positioning system integrating augmented reality (AR) and optical surface, and to evaluate its feasibility in clinical workflow. METHODS: AR and structured light-based surface were integrated to implement the coarse-to-precise positioning through two coherent steps, the AR-based coarse guidance and the optical surface-based precise verification. To implement quality assurance, recognition of face and pattern was used for patient authentication, case association, and accessory validation in AR scenes. The holographic images reconstructed from simulation computed tomography (CT) images, guided the initial posture correction by virtual-real alignment. The point clouds of body surface were fused, with the calibration and pose estimation of structured light cameras, and segmented according to the preset regions of interest (ROIs). The global-to-local registration for cross-source point clouds was achieved to calculate couch shifts in six degrees-of-freedom (DoF), which were ultimately transmitted to AR scenes. The evaluation based on phantom and human-body (4 volunteers) included, (i) quality assurance workflow, (ii) errors of both steps and correlation analysis, (iii) receiver operating characteristic (ROC), (iv) distance characteristics of accuracy, and (v) clinical positioning efficiency. RESULTS: The maximum errors in phantom evaluation were 3.4 ± 2.5 mm in Vrt and 1.4 ± 1.0° in Pitch for the coarse guidance step, while 1.6 ± 0.9 mm in Vrt and 0.6 ± 0.4° in Pitch for the precise verification step. The Pearson correlation coefficients between precise verification and cone beam CT (CBCT) results were distributed in the interval [0.81, 0.85]. In ROC analysis, the areas under the curve (AUC) were 0.87 and 0.89 for translation and rotation, respectively. In human body-based evaluation, the errors of thorax and abdomen (T&A) were significantly greater than those of head and neck (H&N) in Vrt (2.6 ± 1.1 vs. 1.7 ± 0.8, p < 0.01), Lng (2.3 ± 1.1 vs. 1.4 ± 0.9, p < 0.01), and Rtn (0.8 ± 0.4 vs. 0.6 ± 0.3, p = 0.01) while relatively similar in Lat (1.8 ± 0.9 vs. 1.7 ± 0.8, p = 0.07). The translation displacement range, after coarse guidance step, required for high accuracy of the optical surface component of the integrated system was 0-42 mm, and the average positioning duration of the integrated system was significantly less than that of conventional workflow (355.7 ± 21.7 vs. 387.7 ± 26.6 s, p < 0.01). CONCLUSIONS: The combination of AR and optical surface has utility and feasibility for patient positioning, in terms of both safety and accuracy.

Dosimetric comparison of deformable image registration and synthetic CT generation based on CBCT images for organs at risk in cervical cancer radiotherapy.

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.

A novel approach for eliminating metal artifacts based on MVCBCT and CycleGAN.

Purpose: To develop a metal artifact reduction (MAR) algorithm and eliminate the adverse effects of metal artifacts on imaging diagnosis and radiotherapy dose calculations. Methods: Cycle-consistent adversarial network (CycleGAN) was used to generate synthetic CT (sCT) images from megavoltage cone beam CT (MVCBCT) images. In this study, there were 140 head cases with paired CT and MVCBCT images, from which 97 metal-free cases were used for training. Based on the trained model, metal-free sCT (sCT_MF) images and metal-containing sCT (sCT_M) images were generated from the MVCBCT images of 29 metal-free cases and 14 metal cases, respectively. Then, the sCT_MF and sCT_M images were quantitatively evaluated for imaging and dosimetry accuracy. Results: The structural similarity (SSIM) index of the sCT_MF and metal-free CT (CT_MF) images were 0.9484, and the peak signal-to-noise ratio (PSNR) was 31.4 dB. Compared with the CT images, the sCT_MF images had similar relative electron density (RED) and dose distribution, and their gamma pass rate (1 mm/1%) reached 97.99% ± 1.14%. The sCT_M images had high tissue resolution with no metal artifacts, and the RED distribution accuracy in the range of 1.003 to 1.056 was improved significantly. The RED and dose corrections were most significant for the planning target volume (PTV), mandible and oral cavity. The maximum correction of Dmean and D50 for the oral cavity reached 90 cGy. Conclusions: Accurate sCT_M images were generated from MVCBCT images based on CycleGAN, which eliminated the metal artifacts in clinical images completely and corrected the RED and dose distributions accurately for clinical application.

OpenKBP-Opt: an international and reproducible evaluation of 76 knowledge-based planning pipelines.

Objective.To establish an open framework for developing plan optimization models for knowledge-based planning (KBP).Approach.Our framework includes radiotherapy treatment data (i.e. reference plans) for 100 patients with head-and-neck cancer who were treated with intensity-modulated radiotherapy. That data also includes high-quality dose predictions from 19 KBP models that were developed by different research groups using out-of-sample data during the OpenKBP Grand Challenge. The dose predictions were input to four fluence-based dose mimicking models to form 76 unique KBP pipelines that generated 7600 plans (76 pipelines × 100 patients). The predictions and KBP-generated plans were compared to the reference plans via: the dose score, which is the average mean absolute voxel-by-voxel difference in dose; the deviation in dose-volume histogram (DVH) points; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models.Main results.The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50-0.62, which indicates that the quality of the predictions was generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better (P< 0.05; one-sided Wilcoxon test) on 18 of 23 DVH points. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans, which satisfied 3.5% more criteria than the set of all dose predictions. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for an inverse planning model.Significance.This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. We found that the best performing models significantly outperformed the reference dose and dose predictions. In the interest of reproducibility, our data and code is freely available.

A Comparison Study Between CNN-Based Deformed Planning CT and CycleGAN-Based Synthetic CT Methods for Improving iCBCT Image Quality.

Purpose: The aim of this study is to compare two methods for improving the image quality of the Varian Halcyon cone-beam CT (iCBCT) system through the deformed planning CT (dpCT) based on the convolutional neural network (CNN) and the synthetic CT (sCT) generation based on the cycle-consistent generative adversarial network (CycleGAN). Methods: A total of 190 paired pelvic CT and iCBCT image datasets were included in the study, out of which 150 were used for model training and the remaining 40 were used for model testing. For the registration network, we proposed a 3D multi-stage registration network (MSnet) to deform planning CT images to agree with iCBCT images, and the contours from CT images were propagated to the corresponding iCBCT images through a deformation matrix. The overlap between the deformed contours (dpCT) and the fixed contours (iCBCT) was calculated for purposes of evaluating the registration accuracy. For the sCT generation, we trained the 2D CycleGAN using the deformation-registered CT-iCBCT slicers and generated the sCT with corresponding iCBCT image data. Then, on sCT images, physicians re-delineated the contours that were compared with contours of manually delineated iCBCT images. The organs for contour comparison included the bladder, spinal cord, femoral head left, femoral head right, and bone marrow. The dice similarity coefficient (DSC) was used to evaluate the accuracy of registration and the accuracy of sCT generation. Results: The DSC values of the registration and sCT generation were found to be 0.769 and 0.884 for the bladder (p < 0.05), 0.765 and 0.850 for the spinal cord (p < 0.05), 0.918 and 0.923 for the femoral head left (p > 0.05), 0.916 and 0.921 for the femoral head right (p > 0.05), and 0.878 and 0.916 for the bone marrow (p < 0.05), respectively. When the bladder volume difference in planning CT and iCBCT scans was more than double, the accuracy of sCT generation was significantly better than that of registration (DSC of bladder: 0.859 vs. 0.596, p < 0.05). Conclusion: The registration and sCT generation could both improve the iCBCT image quality effectively, and the sCT generation could achieve higher accuracy when the difference in planning CT and iCBCT was large.

Clinical application and improvement of a CNN-based autosegmentation model for clinical target volumes in cervical cancer radiotherapy.

OBJECTIVE: Clinical target volume (CTV) autosegmentation for cervical cancer is desirable for radiation therapy. Data heterogeneity and interobserver variability (IOV) limit the clinical adaptability of such methods. The adaptive method is proposed to improve the adaptability of CNN-based autosegmentation of CTV contours in cervical cancer. METHODS: This study included 400 cervical cancer treatment planning cases with CTV delineated by radiation oncologists from three hospitals. The datasets were divided into five subdatasets (80 cases each). The cases in datasets 1, 2, and 3 were delineated by physicians A, B, and C, respectively. The cases in datasets 4 and 5 were delineated by multiple physicians. Dataset 1 was divided into training (50 cases), validation (10 cases), and testing (20 cases) cohorts, and they were used to construct the pretrained model. Datasets 2-5 were regarded as host datasets to evaluate the accuracy of the pretrained model. In the adaptive process, the pretrained model was fine-tuned to measure improvements by gradually adding more training cases selected from the host datasets. The accuracy of the autosegmentation model on each host dataset was evaluated using the corresponding test cases. The Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD_95) were used to evaluate the accuracy. RESULTS: Before and after adaptive improvements, the average DSC values on the host datasets were 0.818 versus 0.882, 0.763 versus 0.810, 0.727 versus 0.772, and 0.679 versus 0.789, which are improvements of 7.82%, 6.16%, 6.19%, and 16.05%, respectively. The average HD_95 values were 11.143 mm versus 6.853 mm, 22.402 mm versus 14.076 mm, 28.145 mm versus 16.437 mm, and 33.034 mm versus 16.441 mm, which are improvements of 37.94%, 37.17%, 41.60%, and 50.23%, respectively. CONCLUSION: The proposed method improved the adaptability of the CNN-based autosegmentation model when applied to host datasets.

Evaluation of deep learning-based auto-segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients.

OBJECTIVE: To evaluate the accuracy of a deep learning-based auto-segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician. METHODS: This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral-head-left, and femoral-head-right. RESULTS: The DSC values of the auto-segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral-head-right (P < 0.05), 0.88 and 0.84 for the femoral-head-left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral-head-right (P > 0.05), 6.17 and 6.31 for the femoral-head-left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto-segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task. CONCLUSION: The auto-segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto-segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.

A method of using deep learning to predict three-dimensional dose distributions for intensity-modulated radiotherapy of rectal cancer.

PURPOSE: To develop and test a three-dimensional (3D) deep learning model for predicting 3D voxel-wise dose distributions for intensity-modulated radiotherapy (IMRT). METHODS: A total of 122 postoperative rectal cancer cases treated by IMRT were considered in the study, of which 100 cases were randomly selected as the training-validating set and the remaining as the testing set. A 3D deep learning model named 3D U-Res-Net_B was constructed to predict 3D dose distributions. Eight types of 3D matrices from CT images, contoured structures, and beam configurations were fed into the independent input channel, respectively, and the 3D matrix of dose distributions was taken as the output to train the 3D model. The obtained 3D model was used to predict new 3D dose distributions. The predicted accuracy was evaluated in two aspects: (a) The dice similarity coefficients (DSCs) of different isodose volumes, the average dose difference of all voxels within the body, and 3%/5 mm global gamma passing rates of organs at risks (OARs) and planned target volume (PTV) were used to address the spatial correspondence between predicted and clinical delivered 3D dose distributions; (b) The dosimetric index (DI) including homogeneity index, conformity index, V50 , V45 for PTV and OARs between predicted and clinical truth were statistically analyzed with the paired-samples t test. The model was also compared with 3D U-Net and the same architecture model without beam configurations input (named as 3D U-Res-Net_O). RESULTS: The 3D U-Res-Net_B model predicted 3D dose distributions accurately. For the 22 testing cases, the average prediction bias ranged from -1.94% to 1.58%, and the overall mean absolute errors (MAEs) was 3.92 ± 4.16%; there was no statistically significant difference for nearly all DIs. The model had a DSCs value above 0.9 for most isodose volumes, and global 3D gamma passing rates varying from 0.81 to 0.90 for PTV and OARs, clearly outperforming 3D U-Res-Net_O and being slightly superior to 3D U-Net. CONCLUSIONS: This study developed a more general deep learning model by considering beam configurations input and achieved an accurate 3D voxel-wise dose prediction for rectal cancer treated by IMRT, a potentially easier clinical implementation for more comprehensive automatic planning.