Search

We establish an open framework for developing plan optimization models for knowledge-based planning (KBP) in radiotherapy. Our framework includes reference plans for 100 patients with head-and-neck cancer and high-quality dose predictions from 19 KBP models that were developed by different research groups during the OpenKBP Grand Challenge. The dose predictions were input to four optimization models to form 76 unique KBP pipelines that generated 7600 plans. The predictions and plans were compared to the reference plans via: dose score, which is the average mean absolute voxel-by-voxel difference in dose a model achieved; the deviation in dose-volume histogram (DVH) criterion; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models. The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50 to 0.62, which indicates that the quality of the predictions is generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better (P, 19 pages, 7 tables, 6 figures

Background Adjuvant radiation therapy improves the overall survival and loco-regional control in patients with breast cancer. However, radiation-induced heart disease, which occurs after treatment from incidental radiation exposure to the cardiac organ, is an emerging challenge. This study aimed to generate synthetic contrast-enhanced computed tomography (SCECT) from non-contrast CT (NCT) using deep learning (DL) and investigate its role in contouring cardiac substructures. We also aimed to determine its applicability for a retrospective study on the substructure volume-dose relationship for predicting radiation-induced heart disease. Methods We prepared NCT-CECT cardiac scan pairs of 59 patients. Of these, 35, 4, and 20 pairs were used for training, validation, and testing, respectively. We adopted conditional generative adversarial network as a framework to generate SCECT. SCECT was validated in the following three stages: (1) The similarity between SCECT and CECT was evaluated; (2) Manual contouring was performed on SCECT and CECT with sufficient intervals and based on this, the geometric similarity of cardiac substructures was measured between them; (3) The treatment plan was quantitatively analyzed based on the contours of SCECT and CECT. Results While the mean values (± standard deviation) of the mean absolute error, peak signal-to-noise ratio, and structural similarity index measure between SCECT and CECT were 20.66 ± 5.29, 21.57 ± 1.85, and 0.77 ± 0.06, those were 23.95 ± 6.98, 20.67 ± 2.34, and 0.76 ± 0.07 between NCT and CECT, respectively. The Dice similarity coefficients and mean surface distance between the contours of SCECT and CECT were 0.81 ± 0.06 and 2.44 ± 0.72, respectively. The dosimetry analysis displayed error rates of 0.13 ± 0.27 Gy and 0.71 ± 1.34% for the mean heart dose and V5Gy, respectively. Conclusion Our findings displayed the feasibility of SCECT generation from NCT and its potential for cardiac substructure delineation in patients who underwent breast radiation therapy.

Purpose To study the performance of a proposed deep learning-based autocontouring system in delineating organs at risk (OARs) in breast radiotherapy with a group of experts. Methods Eleven experts from two institutions delineated nine OARs in 10 cases of adjuvant radiotherapy after breast-conserving surgery. Autocontours were then provided to the experts for correction. Overall, 110 manual contours, 110 corrected autocontours, and 10 autocontours of each type of OAR were analyzed. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to compare the degree of agreement between the best manual contour (chosen by an independent expert committee) and each autocontour, corrected autocontour, and manual contour. Higher DSCs and lower HDs indicated a better geometric overlap. The amount of time reduction using the autocontouring system was examined. User satisfaction was evaluated using a survey. Results Manual contours, corrected autocontours, and autocontours had a similar accuracy in the average DSC value (0.88 vs. 0.90 vs. 0.90). The accuracy of autocontours ranked the second place, based on DSCs, and the first place, based on HDs among the manual contours. Interphysician variations among the experts were reduced in corrected autocontours, compared to variations in manual contours (DSC: 0.89–0.90 vs. 0.87–0.90; HD: 4.3–5.8 mm vs. 5.3–7.6 mm). Among the manual delineations, the breast contours had the largest variations, which improved most significantly with the autocontouring system. The total mean times for nine OARs were 37 min for manual contours and 6 min for corrected autocontours. The results of the survey revealed good user satisfaction. Conclusions The autocontouring system had a similar performance in OARs as that of the experts’ manual contouring. This system can be valuable in improving the quality of breast radiotherapy and reducing interphysician variability in clinical practice.

Purpose: This study was conducted to develop a deep learning-based automatic segmentation (DLBAS) model of head and neck organs for radiotherapy (RT) in dogs, and to evaluate the feasibility for delineating the RT planning.Materials and Methods: The segmentation indicated that there were potentially 15 organs at risk (OARs) in the head and neck of dogs. Post-contrast computed tomography (CT) was performed in 90 dogs. The training and validation sets comprised 80 CT data sets, including 20 test sets. The accuracy of the segmentation was assessed using both the Dice similarity coefficient (DSC) and the Hausdorff distance (HD), and by referencing the expert contours as the ground truth. An additional 10 clinical test sets with relatively large displacement or deformation of organs were selected for verification in cancer patients. To evaluate the applicability in cancer patients, and the impact of expert intervention, three methods–HA, DLBAS, and the readjustment of the predicted data obtained via the DLBAS of the clinical test sets (HA_DLBAS)–were compared.Results: The DLBAS model (in the 20 test sets) showed reliable DSC and HD values; it also had a short contouring time of ~3 s. The average (mean ± standard deviation) DSC (0.83 ± 0.04) and HD (2.71 ± 1.01 mm) values were similar to those of previous human studies. The DLBAS was highly accurate and had no large displacement of head and neck organs. However, the DLBAS in the 10 clinical test sets showed lower DSC (0.78 ± 0.11) and higher HD (4.30 ± 3.69 mm) values than those of the test sets. The HA_DLBAS was comparable to both the HA (DSC: 0.85 ± 0.06 and HD: 2.74 ± 1.18 mm) and DLBAS presented better comparison metrics and decreased statistical deviations (DSC: 0.94 ± 0.03 and HD: 2.30 ± 0.41 mm). In addition, the contouring time of HA_DLBAS (30 min) was less than that of HA (80 min).Conclusion: In conclusion, HA_DLBAS method and the proposed DLBAS was highly consistent and robust in its performance. Thus, DLBAS has great potential as a single or supportive tool to the key process in RT planning.

PURPOSE Applications of deep learning (DL) are essential to realizing an effective adaptive radiotherapy (ART) workflow. Despite the promise demonstrated by DL approaches in several critical ART tasks, there remain unsolved challenges to achieve satisfactory generalizability of a trained model in a clinical setting. Foremost among these is the difficulty of collecting a task-specific training dataset with high-quality, consistent annotations for supervised learning applications. In this study, we propose a tailored DL framework for patient-specific performance that leverages the behavior of a model intentionally overfitted to a patient-specific training dataset augmented from the prior information available in an ART workflow-an approach we term Intentional Deep Overfit Learning (IDOL). METHODS Implementing the IDOL framework in any task in radiotherapy consists of two training stages: (1) training a generalized model with a diverse training dataset of N patients, just as in the conventional DL approach, and (2) intentionally overfitting this general model to a small training dataset-specific the patient of interest ( N+1 ) generated through perturbations and augmentations of the available task- and patient-specific prior information to establish a personalized IDOL model. The IDOL framework itself is task-agnostic and is, thus, widely applicable to many components of the ART workflow, three of which we use as a proof of concept here: the autocontouring task on replanning CTs for traditional ART, the MRI super-resolution (SR) task for MRI-guided ART, and the synthetic CT (sCT) reconstruction task for MRI-only ART. RESULTS In the replanning CT autocontouring task, the accuracy measured by the Dice similarity coefficient improves from 0.847 with the general model to 0.935 by adopting the IDOL model. In the case of MRI SR, the mean absolute error (MAE) is improved by 40% using the IDOL framework over the conventional model. Finally, in the sCT reconstruction task, the MAE is reduced from 68 to 22 HU by utilizing the IDOL framework. CONCLUSIONS In this study, we propose a novel IDOL framework for ART and demonstrate its feasibility using three ART tasks. We expect the IDOL framework to be especially useful in creating personally tailored models in situations with limited availability of training data but existing prior information, which is usually true in the medical setting in general and is especially true in ART.

PURPOSE Adjuvant radiotherapy (RT) has been performed to reduce locoregional failure (LRF) following radical cystectomy for locally advanced bladder cancer; however, its efficacy has not been well established. We analyzed the locoregional recurrence patterns of post-radical cystectomy to identify patients who could benefit from adjuvant RT and determine the optimal target volume. MATERIALS AND METHODS We retrospectively reviewed 160 patients with stage ≥ pT3 bladder cancer who were treated with radical cystectomy between January 2006 and December 2015. The impact of pathologic findings, including the stage, lympho-vascular invasion, perineural invasion, margin status, nodal involvement, and the number of nodes removed on failure patterns, was assessed. RESULTS Median follow-up period was 27.7 months. LRF was observed in 55 patients (34.3%), 12 of whom presented with synchronous local and regional failures as the first failure. The most common failure pattern was distant metastasis (40%). Among LRFs, the most common recurrence site was the cystectomy bed (15.6%). Patients with positive resection margins had a significantly higher recurrence rate compared to those without (28% vs. 10%, p=0.004). The pelvic nodal recurrence rate was < 5% in pN0 patients; the rate of recurrence in the external and common iliac nodes was 12.5% in pN+ patients. The rate of recurrence in the common iliac nodes was significantly higher in pN2-3 patients than in pN0-1 patients (15.2% vs. 4.4%, p=0.04). CONCLUSION Pelvic RT could be beneficial especially for those with positive resection margins or nodal involvement after radical cystectomy. Radiation fields should be optimized based on the patient-specific risk factors.

This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (H&amp, N) cancer. One-hundred patients treated with definitive RT were included. Based on 23 organs-at-risk (OARs) manually segmented in initial planning computed tomography (CT), modified FC-DenseNet was trained for DLS: (i) using data obtained from 60 patients, with 20 matched patients in the test set (DLSm), (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were also evaluated via subjective assessment from 26 observers using the Turing test. DLSm achieved better performance than both DLSu and DIR (mean Dice similarity coefficient, 0.83 vs. 0.80 vs. 0.70), mainly for glandular structures, whose volume significantly reduced during RT. Based on subjective measurements, DLS is often perceived as a human (49.2%). Furthermore, DLSm is preferred over DLSu (67.2%) and DIR (96.7%), with a similar rate of required revision to that of manual segmentation (28.0% vs. 29.7%). In conclusion, DLS was effective and preferred over DIR. Additionally, continual DLS training is required for an effective optimization and robustness in personalized adaptive RT.

Background In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients. Methods CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data. Results The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal. Conclusions The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future. Trial registration Retrospectively registered.

Additional file 1. Inter-observer variability and contouring time of three radiation oncologists for manual contours of organs-at-risk and target volumes.

Objective. Owing to the superior soft tissue contrast of MRI, MRI-guided adaptive radiotherapy (ART) is well-suited to managing interfractional changes in anatomy. An MRI-only workflow is desirable, but producing synthetic CT (sCT) data through paired data-driven deep learning (DL) for abdominal dose calculations remains a challenge due to the highly variable presence of intestinal gas. We present the preliminary dosimetric evaluation of our novel approach to sCT reconstruction that is well suited to handling intestinal gas in abdominal MRI-only ART.Approach. We utilize a paired data DL approach enabled by the intensity projection prior, in which well-matching training pairs are created by propagating air from MRI to corresponding CT scans. Evaluations focus on two classes: patients with (1) little involvement of intestinal gas, and (2) notable differences in intestinal gas presence between corresponding scans. Comparisons between sCT-based plans and CT-based clinical plans for both classes are made at the first treatment fraction to highlight the dosimetric impact of the variable presence of intestinal gas.Main results. Class 1 patients (n= 13) demonstrate differences in prescribed dose coverage of the PTV of 1.3 ± 2.1% between clinical plans and sCT-based plans. Mean DVH differences in all structures for Class 1 patients are found to be statistically insignificant. In Class 2 (n= 20), target coverage is 13.3 ± 11.0% higher in the clinical plans and mean DVH differences are found to be statistically significant.Significance. Significant deviations in calculated doses arising from the variable presence of intestinal gas in corresponding CT and MRI scans result in uncertainty in high-dose regions that may limit the effectiveness of adaptive dose escalation efforts. We have proposed a paired data-driven DL approach to sCT reconstruction for accurate dose calculations in abdominal ART enabled by the creation of a clinically unavailable training data set with well-matching representations of intestinal gas.

Objective. Real-time imaging is highly desirable in image-guided radiotherapy, as it provides instantaneous knowledge of patients’ anatomy and motion during treatments and enables online treatment adaptation to achieve the highest tumor targeting accuracy. Due to extremely limited acquisition time, only one or few x-ray projections can be acquired for real-time imaging, which poses a substantial challenge to localize the tumor from the scarce projections. For liver radiotherapy, such a challenge is further exacerbated by the diminished contrast between the tumor and the surrounding normal liver tissues. Here, we propose a framework combining graph neural network-based deep learning and biomechanical modeling to track liver tumor in real-time from a single onboard x-ray projection. Approach. Liver tumor tracking is achieved in two steps. First, a deep learning network is developed to predict the liver surface deformation using image features learned from the x-ray projection. Second, the intra-liver deformation is estimated through biomechanical modeling, using the liver surface deformation as the boundary condition to solve tumor motion by finite element analysis. The accuracy of the proposed framework was evaluated using a dataset of 10 patients with liver cancer. Main results. The results show accurate liver surface registration from the graph neural network-based deep learning model, which translates into accurate, fiducial-less liver tumor localization after biomechanical modeling (Significance. The method demonstrates its potentiality towards intra-treatment and real-time 3D liver tumor monitoring and localization. It could be applied to facilitate 4D dose accumulation, multi-leaf collimator tracking and real-time plan adaptation. The method can be adapted to other anatomical sites as well.

PURPOSE/OBJECTIVE(S) Although radiation-induced cardiac toxicity is an important issue in breast radiation therapy (RT), the dose relationship between cardiac structures and its toxicity has not been fully elucidated, partially because many centers do not routinely administer intravenous (IV) contrast for breast RT, which preclude substructure delineation and detection of potential correlations. In this study, we attempted to generate the synthetic contrast-enhanced CT (CECTsyn) from the non-contrast CT (NCTreal) using deep convolutional neural network (DCNN) and to investigate whether CECTsyn can take a supportive role in case the studies for the cardiac toxicity induced by radiation is needed for the patient whose CECTreal cannot be obtained. MATERIALS/METHODS For this study, 22 NCTreal-CECTreal cardiac scan-pairs have been prepared of which the volume size was ∼512 × 512 × 400 and the resolution was ∼0.75 × 0.75 × 1 mm3 on average. Of the 22 datasets, 13/2/7 were used for training, validation, and testing, respectively. After matching the structure of paired scans using the deformable image registration (DIR), the area near the heart was cropped and used for training the deep learning model. We adopted the modified 2D fully convolution DenseNet (FC-DenseNet) as our backbone and trained it in the conditional generative adversarial network (cGAN) framework. The similarity between CECTsyn and CECTreal was evaluated first, and all NCTreal,CECTsyn, and CECTreal were applied to pre-trained cardiac auto-segmentation models to obtain the substructures of the heart, which is used for dose assessments in each of them. Finally, dose evaluations were conducted on CECTsyn and CECTreal with the dose distributions which are from clinical treatment plans and the manually modified contours of cardiac substructures. RESULTS Firstly, the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM) between CECTsyn and CECTreal were 23.96 and 0.772, whereas those of NCTreal and CECTreal were 22.25and 0.748, respectively. Secondly, the results of applying the pre-trained cardiac auto-segmentation model were obtained, and the dice similarity coefficient (DSC) of CECTsyn was 0.762 on average which is superior to 0.267 of NCTreal and comparable to 0.843 of CECTreal. We could distinguish the L/R ventricles, L/R atriums, left anterior descending artery (LAD), and right coronary artery (RCA) clearly on CECTsyn. Finally, the dose differences between CECTsyn and CECTreal were on average 0.4/2.0 Gy in Dmean and Dmax, and 2.1/1.3/0.6/0.4/0.3/0.1/0.0% in V5 Gy, V10 Gy, V20 Gy, V30 Gy, V40 Gy, V50 Gy, and V60 Gy, respectively. CONCLUSION DCNN model proposed here showed the feasibility of CECTsyn generation from NCTreal and potential for cardiac substructure delineation such as ventricles, atriums, LAD, and RCA on NCTreal for breast RT. Furthermore, it is shown that CECTsyn can play a supportive role when the studies for the radiation-induced cardiac toxicity is needed.

PURPOSE/OBJECTIVE(S) Brain metastases (BM) are the most common intracranial tumors in adults. Benefiting from efficient local control, stereotactic ablative radiotherapy (SABR) is becoming popular in the treatment of BM. Detection and manual delineation of BM are labor-intense processes, and BM are occasionally mistaken for normal brain, especially if volumes are very small. Recently, several efforts have been made to develop automatic detection and segmentation for BM using advanced deep learning (DL) algorithms. In this study, we investigated the efficacy and accuracy of a DL model for the detection and segmentation of BM. MATERIALS/METHODS To train and validate the DL model, magnetic resonance imaging (MRI) for 65 patients and 603 BM were collected and analyzed. Manual contouring for BM was done by a radiation oncologist. We utilized 2.5-dimensional training using a two-dimensional U-Net as the DL architecture to avoid inefficiencies of the three-dimensional architecture. Because of MRI characteristic, we applied N4 bias field correction and gamma correction as pre-processing techniques. Also, we utilized the overlapping patch technique and under-sampling technique to extract small-volume BM from the normal brain that occupies most of the slice. During the training, data augmentations (horizontal flip, vertical flip, random rotation, random blur) were applied on the fly randomly. The detection performance was measured with sensitivity and average false positive rate and the segmentation performance with the Dice coefficient with dilation (DWD) with dilation factor set to a radius of 4 pixels. BMs with volumes 0.04 cc and 49.7% in BM with volumes < 0.04 cc. For all BM, the DWD value was 63%. CONCLUSION Our DL model can detect and segment BM with good performance; it is especially effective even for small-volume BM, suggesting its considerable benefit for gross tumor volume detection and segmentation for stereotactic radiosurgery or SABR.

Purpose/Objective(s) A large inter-physician variation can be seen when delineating organ-at-risks (OARs) for breast radiotherapy. This study aimed to externally validate the performance of deep learning-based auto-contouring system (ACS) for breast radiotherapy. Materials/Methods Eleven experts from two institutions were asked to delineate 9 OARs of 10 cases of breast radiotherapy. Then, auto-contours were provided to the experts for correction. To compare the performance of auto-, corrected-auto-, and experts’ manual contours, Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each contour and the best manual contour were used, where higher DSC and lower HD means better geometric overlap. Results Total mean time for 9 OARs was 37 ± 20 min for manual and 6 ± 5 min for corrected-auto-contours. Among the DSC of experts’ manual contours and an auto-contour, DSC of an auto-contour ranked the second place and HD ranked the first place. Better performance was shown in corrected-auto-contours than in manual contours (median DSC: 0.90 vs. 0.88; median HD: 4.5 vs. 6.5 mm). The inter-physician variations among experts were reduced in corrected-auto-contours, compared with manual contours (DSC range: 0.86–0.90 vs. 0.89–0.90; HD range: 5.1–9.1 mm vs. 4.3–5.7 mm). Among manual OARs, breast contours had the largest variations, which were most significantly improved with an aid of ACS. Conclusion ACS showed at least similar performance in OARs compared with experts’ manual contouring, which anticipates further applications of ACS to target volumes. ACS can be a valuable tool for improving the quality of breast radiotherapy and reducing inter-physician variability in clinical practice.

Background: While atlas segmentation (AS) has proven to be a time-saving and promising method for radiation therapy contouring, optimal methods for its use have not been well-established. Therefore, we investigated the relationship between the size of the atlas patient population and the atlas segmentation auto contouring (AC) performance. Methods: A total of 110 patients' head planning CT images were selected. The mandible and thyroid were selected for this study. The mandibles and thyroids of the patient population were carefully segmented by two skilled clinicians. Of the 110 patients, 100 random patients were registered to 5 different atlas libraries as atlas patients, in groups of 20 to 100, with increments of 20. AS was conducted for each of the remaining 10 patients, either by simultaneous atlas segmentation (SAS) or independent atlas segmentation (IAS). The AS duration of each target patient was recorded. To validate the accuracy of the generated contours, auto contours were compared to manually generated contours (MC) using a volume-overlap-dependent metric, Dice Similarity Coefficient (DSC), and a distance-dependent metric, Hausdorff Distance (HD). Results: In both organs, as the population increased from n = 20 to n = 60, the results showed better convergence. Generally, independent cases produced better performance than simultaneous cases. For the mandible, the best performance was achieved by n = 60 [DSC = 0.92 (0.01) and HD = 6.73 (1.31) mm] and the worst by n = 100 [DSC = 0.90 (0.03) and HD = 10.10 (6.52) mm] atlas libraries. Similar results were achieved with the thyroid; the best performance was achieved by n = 60 [DSC = 0.79 (0.06) and HD = 10.17 (2.89) mm] and the worst by n = 100 [DSC = 0.72 (0.13) and HD = 12.88 (3.94) mm] atlas libraries. Both IAS and SAS showed similar results. Manual contouring of the mandible and thyroid required an average of 1,044 (±170.15) seconds, while AS required an average of 46.4 (±2.8) seconds. Conclusions: The performance of AS AC generally increased as the population of the atlas library increased. However, the performance does not drastically vary in the larger atlas libraries in contrast to the logic that bigger atlas library should lead to better results. In fact, the results do not vary significantly toward the larger atlas library. It is necessary for the institutions to independently research the optimal number of subjects.