CBCT-DRRs superior to CT-DRRs for target-tracking applications for pancreatic SBRT.

Objective.In current radiograph-based intra-fraction markerless target-tracking, digitally reconstructed radiographs (DRRs) from planning CTs (CT-DRRs) are often used to train deep learning models that extract information from the intra-fraction radiographs acquired during treatment. Traditional DRR algorithms were designed for patient alignment (i.e.bone matching) and may not replicate the radiographic image quality of intra-fraction radiographs at treatment. Hypothetically, generating DRRs from pre-treatment Cone-Beam CTs (CBCT-DRRs) with DRR algorithms incorporating physical modelling of on-board-imagers (OBIs) could improve the similarity between intra-fraction radiographs and DRRs by eliminating inter-fraction variation and reducing image-quality mismatches between radiographs and DRRs. In this study, we test the two hypotheses that intra-fraction radiographs are more similar to CBCT-DRRs than CT-DRRs, and that intra-fraction radiographs are more similar to DRRs from algorithms incorporating physical models of OBI components than DRRs from algorithms omitting these models.Approach.DRRs were generated from CBCT and CT image sets collected from 20 patients undergoing pancreas stereotactic body radiotherapy. CBCT-DRRs and CT-DRRs were generated replicating the treatment position of patients and the OBI geometry during intra-fraction radiograph acquisition. To investigate whether the modelling of physical OBI components influenced radiograph-DRR similarity, four DRR algorithms were applied for the generation of CBCT-DRRs and CT-DRRs, incorporating and omitting different combinations of OBI component models. The four DRR algorithms were: a traditional DRR algorithm, a DRR algorithm with source-spectrum modelling, a DRR algorithm with source-spectrum and detector modelling, and a DRR algorithm with source-spectrum, detector and patient material modelling. Similarity between radiographs and matched DRRs was quantified using Pearson's correlation and Czekanowski's index, calculated on a per-image basis. Distributions of correlations and indexes were compared to test each of the hypotheses. Distribution differences were determined to be statistically significant when Wilcoxon's signed rank test and the Kolmogorov-Smirnov two sample test returnedp≤ 0.05 for both tests.Main results.Intra-fraction radiographs were more similar to CBCT-DRRs than CT-DRRs for both metrics across all algorithms, with allp≤ 0.007. Source-spectrum modelling improved radiograph-DRR similarity for both metrics, with allp< 10-6. OBI detector modelling and patient material modelling did not influence radiograph-DRR similarity for either metric.Significance.Generating DRRs from pre-treatment CBCT-DRRs is feasible, and incorporating CBCT-DRRs into markerless target-tracking methods may promote improved target-tracking accuracies. Incorporating source-spectrum modelling into a treatment planning system's DRR algorithms may reinforce the safe treatment of cancer patients by aiding in patient alignment.

Deep learning enables MV-based real-time image guided radiation therapy for prostate cancer patients.

Objective. Using MV images for real-time image guided radiation therapy (IGRT) is ideal as it does not require additional imaging equipment, adds no additional imaging dose and provides motion data in the treatment beam frame of reference. However, accurate tracking using MV images is challenging due to low contrast and modulated fields. Here, a novel real-time marker tracking system based on a convolutional neural network (CNN) classifier was developed and evaluated on retrospectively acquired patient data for MV-based IGRT for prostate cancer patients.Approach. MV images, acquired from 29 volumetric modulated arc therapy (VMAT) prostate cancer patients treated in a multi-institutional clinical trial, were used to train and evaluate a CNN-based marker tracking system. The CNN was trained using labelled MV images from 9 prostate cancer patients (35 fractions) with implanted markers. CNN performance was evaluated on an independent cohort of unseen MV images from 20 patients (78 fractions), using a Precision-Recall curve (PRC), area under the PRC plot (AUC) and sensitivity and specificity. The accuracy of the tracking system was evaluated on the same unseen dataset and quantified by calculating mean absolute (±1 SD) and [1st, 99th] percentiles of the geometric tracking error in treatment beam co-ordinates using manual identification as the ground truth.Main results. The CNN had an AUC of 0.99, sensitivity of 98.31% and specificity of 99.87%. The mean absolute geometric tracking error was 0.30 ± 0.27 and 0.35 ± 0.31 mm in the lateral and superior-inferior directions of the MV images, respectively. The [1st, 99th] percentiles of the error were [-1.03, 0.90] and [-1.12, 1.12] mm in the lateral and SI directions, respectively.Significance. The high classification performance on unseen MV images demonstrates the CNN can successfully identify implanted prostate markers. Furthermore, the sub-millimetre accuracy and precision of the marker tracking system demonstrates potential for adaptation to real-time applications.

Evaluation of deep learning based implanted fiducial markers tracking in pancreatic cancer patients.

Real-time target position verification during pancreas stereotactic body radiation therapy (SBRT) is important for the detection of unplanned tumour motions. Fast and accurate fiducial marker segmentation is a Requirement of real-time marker-based verification. Deep learning (DL) segmentation techniques are ideal because they don't require additional learning imaging or prior marker information (e.g., shape, orientation). In this study, we evaluated three DL frameworks for marker tracking applied to pancreatic cancer patient data. The DL frameworks evaluated were (1) a convolutional neural network (CNN) classifier with sliding window, (2) a pretrained you-only-look-once (YOLO) version-4 architecture, and (3) a hybrid CNN-YOLO. Intrafraction kV images collected during pancreas SBRT treatments were used as training data (44 fractions, 2017 frames). All patients had 1-4 implanted fiducial markers. Each model was evaluated on unseen kV images (42 fractions, 2517 frames). The ground truth was calculated from manual segmentation and triangulation of markers in orthogonal paired kV/MV images. The sensitivity, specificity, and area under the precision-recall curve (AUC) were calculated. In addition, the mean-absolute-error (MAE), root-mean-square-error (RMSE) and standard-error-of-mean (SEM) were calculated for the centroid of the markers predicted by the models, relative to the ground truth. The sensitivity and specificity of the CNN model were 99.41% and 99.69%, respectively. The AUC was 0.9998. The average precision of the YOLO model for different values of recall was 96.49%. The MAE of the three models in the left-right, superior-inferior, and anterior-posterior directions were under 0.88 ± 0.11 mm, and the RMSE were under 1.09 ± 0.12 mm. The detection times per frame on a GPU were 48.3, 22.9, and 17.1 milliseconds for the CNN, YOLO, and CNN-YOLO, respectively. The results demonstrate submillimeter accuracy of marker position predicted by DL models compared to the ground truth. The marker detection time was fast enough to meet the requirements for real-time application.

Quantification of the geometric uncertainty when using implanted markers as a surrogate for lung tumor motion.

BACKGROUND: Fiducial markers are used as surrogates for tumor location during radiation therapy treatment. Developments in lung fiducial marker and implantation technology have provided a means to insert markers endobronchially for tracking of lung tumors. This study quantifies the surrogacy uncertainty (SU) when using endobronchially implanted markers as a surrogate for lung tumor position. METHODS: We evaluated SU for 17 patients treated in a prospective electromagnetic-guided MLC tracking trial. Tumor and markers were segmented on all phases of treatment planning 4DCTs and all frames of pretreatment kilovoltage fluoroscopy acquired from lateral and frontal views. The difference in tumor and marker position relative to end-exhale position was calculated as the SU for both imaging methods and the distributions of uncertainties analyzed. RESULTS: The mean (range) tumor motion amplitude in the 4DCT scan was 5.9 mm (1.7-11.7 mm) in the superior-inferior (SI) direction, 2.2 mm (0.9-5.5 mm) in the left-right (LR) direction, and 3.9 mm (1.2-12.9 mm) in the anterior-posterior (AP) direction. Population-based analysis indicated symmetric SU centered close to 0 mm, with maximum 5th/95th percentile values over all axes of -2.0 mm/2.1 mm with 4DCT, and -2.3/1.3 mm for fluoroscopy. There was poor correlation between the SU measured with 4DCT and that measured with fluoroscopy on a per-patient basis. We observed increasing SU with increasing surrogate motion. Based on fluoroscopy analysis, the mean (95% CI) SU was 5% (2%-8%) of the motion magnitude in the SI direction, 16% (6%-26%) of the motion magnitude in the LR direction, and 33% (23%-42%) of the motion magnitude in the AP direction. There was no dependence of SU on marker distance from the tumor. CONCLUSION: We have quantified SU due to use of implanted markers as surrogates for lung tumor motion. Population 95th percentile range are up to 2.3 mm, indicating the approximate contribution of SU to total geometric uncertainty. SU was relatively small compared with the SI motion, but substantial compared with LR and AP motion. Due to uncertainty in estimations of patient-specific SU, it is recommended that population-based margins are used to account for this component of the total geometric uncertainty.