Beyond conventional bounds: Surpassing system limits for stereotactic ablative (SAbR) lung radiotherapy using CBCT-based adaptive planning system.

PURPOSE: Online adaptive radiotherapy relies on a high degree of automation to enable rapid planning procedures. The Varian Ethos intelligent optimization engine (IOE) was originally designed for conventional treatments so it is crucial to provide clear guidance for lung SAbR plans. This study investigates using the Ethos IOE together with adaptive-specific optimization tuning structures we designed and templated within Ethos to mitigate inter-planner variability in meeting RTOG metrics for both online-adaptive and offline SAbR plans. METHODS: We developed a planning strategy to automate the generation of tuning structures and optimization. This was validated by retrospective analysis of 35 lung SAbR cases (total 105 fractions) treated on Ethos. The effectiveness of our planning strategy was evaluated by comparing plan quality with-and-without auto-generated tuning structures. Internal target volume (ITV) contour was compared between that drawn from CT simulation and from cone-beam CT (CBCT) at time of treatment to verify CBCT image quality and treatment effectiveness. Planning strategy robustness for lung SAbR was quantified by frequency of plans meeting reference plan RTOG constraints. RESULTS: Our planning strategy creates a gradient within the ITV with maximum dose in the core and improves intermediate dose conformality on average by 2%. ITV size showed no significant difference between those contoured from CT simulation and first fraction, and also trended towards decreasing over course of treatment. Compared to non-adaptive plans, adaptive plans better meet reference plan goals (37% vs. 100% PTV coverage compliance, for scheduled and adapted plans) while improving plan quality (improved GI (gradient index) by 3.8%, CI (conformity index) by 1.7%). CONCLUSION: We developed a robust and readily shareable planning strategy for the treatment of adaptive lung SAbR on the Ethos system. We validated that automatic online plan re-optimization along with the formulated adaptive tuning structures can ensure consistent plan quality. With the proposed planning strategy, highly ablative treatments are feasible on Ethos.

Arginine vasopressin deficiency and conivaptan (a V1a-V2 receptor antagonist) treatment reverses liver damage and fibrosis in rats with chronic portocaval anastomosis.

Arginine vasopressin (AVP) is a naturally occurring hormone synthesized in the hypothalamus. AVP demonstrates pro-fibrotic effects as it stimulates hepatic stellate cells to secrete transforming growth factor-ß (TGF-ß) and collagen. Previous work in liver cirrhotic (CCL4 -induced) hamsters demonstrated that AVP deficiency induced by neurointermediate pituitary lobectomy (NIL) can restore liver function. Therefore, we hypothesized that liver fibrosis would decrease in portocaval anastomosis (PCA) rats, which model chronic liver diseases, when they are treated with the V1a-V2 AVP receptor antagonist conivaptan (CV). In this study, changes in liver histology and gene expression were analysed in five experimental groups: control, PCA, NIL, PCA + NIL and PCA + CV, with NIL surgery or CV treatment administered 8 weeks after PCA surgery. Body weight gain was assessed on a weekly basis, and serum liver function, liver weight and liver glycogen content were assessed following euthanasia. Most PCA-induced phenotypes were reverted to normal levels following AVP-modelled deficiency, though hypoglycemia and ammonium levels remained elevated in the PCA + CV group. Liver histopathological findings showed a significant reversal in collagen content, less fibrosis in the triad and liver septa and increased regenerative nodules. Molecular analyses showed that the expression of fibrogenic genes (TGF-ß and collagen type I) decreased in the PCA + CV group. Our findings strongly suggest that chronic NIL or CV treatment can induce a favourable microenvironment to decrease liver fibrosis and support CV as an alternative treatment for liver fibrosis.

Clinical experience on patient-specific quality assurance for CBCT-based online adaptive treatment plan.

PURPOSE: Ethos CBCT-based adaptive radiotherapy (ART) system can generate an online adaptive plan by re-optimizing the initial reference plan based on the patient anatomy at the treatment. The optimization process is fully automated without any room for human intervention. Due to the change in anatomy, the ART plan can be significantly different from the initial plan in terms of plan parameters such as the aperture shapes and number of monitor units (MUs). In this study, we investigated the feasibility of using calculation-based patient specific QA for ART plans in conjunction with measurement-based and calculation-based QA for initial plans to establish an action level for the online ART patient-specific QA. METHODS: A cohort of 98 cases treated on CBCT-based ART system were collected for this study. We performed measurement-based QA using ArcCheck and calculation-based QA using Mobius for both the initial plan and the ART plan for analysis. For online the ART plan, Mobius calculation was conducted prior to the delivery, while ArcCheck measurement was delivered on the same day after the treatment. We first investigated the modulation factors (MFs) and MU numbers of the initial plans and ART plans, respectively. The γ passing rates of initial and ART plan QA were analyzed. Then action limits were derived for QA calculation and measurement for both initial and online ART plans, respectively, from 30 randomly selected patient cases, and were evaluated using the other 68 patient cases. RESULTS: The difference in MF between initial plan and ART-plan was 12.9% ± 12.7% which demonstrates their significant difference in plan parameters. Based on the patient QA results, pre-treatment calculation and measurement results are generally well aligned with ArcCheck measurement results for online ART plans, illustrating their feasibility as an indicator of failure in online ART QA measurements. Furthermore, using 30 randomly selected patient cases, the γ analysis action limit derived for initial plans and ART plans are 89.6% and 90.4% in ArcCheck QA (2%/2 mm) and are 92.4% and 93.6% in Mobius QA(3%/2 mm), respectively. According to the calculated action limits, the ArcCheck measurements for all the initial and ART plans passed QA successfully while the Mobius calculation action limits flagged seven and four failure cases respectively for initial plans and ART plans, respectively. CONCLUSION: An ART plan can be substantially different from the initial plan, and therefore a separate session of ART plan QA is needed to ensure treatment safety and quality. The pre-treatment QA calculation via Mobius can serve as a reliable indicator of failure in online ART plan QA. However, given that Ethos ART system is still relatively new, ArcCheck measurement of initial plan is still in practice. It may be skipped as we gain more experience and have better understanding of the system.

Predicting treatment plan approval probability for high-dose-rate brachytherapy of cervical cancer using adversarial deep learning.

Objective.Predicting the probability of having the plan approved by the physician is important for automatic treatment planning. Driven by the mathematical foundation of deep learning that can use a deep neural network to represent functions accurately and flexibly, we developed a deep-learning framework that learns the probability of plan approval for cervical cancer high-dose-rate brachytherapy (HDRBT).Approach.The system consisted of a dose prediction network (DPN) and a plan-approval probability network (PPN). DPN predicts organs at risk (OAR)D2ccand CTVD90%of the current fraction from the patient's current anatomy and prescription dose of HDRBT. PPN outputs the probability of a given plan being acceptable to the physician based on the patients anatomy and the total dose combining HDRBT and external beam radiotherapy sessions. Training of the networks was achieved by first training them separately for a good initialization, and then jointly via an adversarial process. We collected approved treatment plans of 248 treatment fractions from 63 patients. Among them, 216 plans from 54 patients were employed in a four-fold cross validation study, and the remaining 32 plans from other 9 patients were saved for independent testing.Main results.DPN predicted equivalent dose of 2 Gy for bladder, rectum, sigmoidD2ccand CTVD90%with a relative error of 11.51% ± 6.92%, 8.23% ± 5.75%, 7.12% ± 6.00%, and 10.16% ± 10.42%, respectively. In a task that differentiates clinically approved plans and disapproved plans generated by perturbing doses in ground truth approved plans by 20%, PPN achieved accuracy, sensitivity, specificity, and area under the curve 0.70, 0.74, 0.65, and 0.74.Significance.We demonstrated the feasibility of developing a novel deep-learning framework that predicts a probability of plan approval for HDRBT of cervical cancer, which is an essential component in automatic treatment planning.

ART2Dose: A comprehensive dose verification platform for online adaptive radiotherapy.

BACKGROUND: Online adaptive radiotherapy (ART) involves the development of adaptable treatment plans that consider patient anatomical data obtained right prior to treatment administration, facilitated by cone-beam computed tomography guided adaptive radiotherapy (CTgART) and magnetic resonance image-guided adaptive radiotherapy (MRgART). To ensure accuracy of these adaptive plans, it is crucial to conduct calculation-based checks and independent verification of volumetric dose distribution, as measurement-based checks are not practical within online workflows. However, the absence of comprehensive, efficient, and highly integrated commercial software for secondary dose verification can impede the time-sensitive nature of online ART procedures. PURPOSE: The main aim of this study is to introduce an efficient online quality assurance (QA) platform for online ART, and subsequently evaluate it on Ethos and Unity treatment delivery systems in our clinic. METHODS: To enhance efficiency and ensure compliance with safety standards in online ART, ART2Dose, a secondary dose verification software, has been developed and integrated into our online QA workflow. This implementation spans all online ART treatments at our institution. The ART2Dose infrastructure comprises four key components: an SQLite database, a dose calculation server, a report generator, and a web portal. Through this infrastructure, file transfer, dose calculation, report generation, and report approval/archival are seamlessly managed, minimizing the need for user input when exporting RT DICOM files and approving the generated QA report. ART2Dose was compared with Mobius3D in pre-clinical evaluations on secondary dose verification for 40 adaptive plans. Additionally, a retrospective investigation was conducted utilizing 1302 CTgART fractions from ten treatment sites and 1278 MRgART fractions from seven treatment sites to evaluate the practical accuracy and efficiency of ART2Dose in routine clinical use. RESULTS: With dedicated infrastructure and an integrated workflow, ART2Dose achieved gamma passing rates that were comparable to or higher than those of Mobius3D. Additionally, it significantly reduced the time required to complete pre-treatment checks by 3-4 min for each plan. In the retrospective analysis of clinical CTgART and MRgART fractions, ART2Dose demonstrated average gamma passing rates of 99.61 ± 0.83% and 97.75 ± 2.54%, respectively, using the 3%/2 mm criteria for region greater than 10% of prescription dose. The average calculation times for CTgART and MRgART were approximately 1 and 2 min, respectively. CONCLUSION: Overall, the streamlined implementation of ART2Dose notably enhances the online ART workflow, offering reliable and efficient online QA while reducing time pressure in the clinic and minimizing labor-intensive work.

Considerations for intensity modulated total body or total marrow and lymphoid irradiation.

We compiled a sampling of the treatment techniques of intensity-modulated total body irradiation, total marrow irradiation and total marrow and lymphoid irradiation utilized by several centers across North America and Europe. This manuscript does not serve as a consensus guideline, but rather is meant to serve as a convenient reference for centers that are considering starting an intensity-modulated program.

Modeling physician's preference in treatment plan approval of stereotactic body radiation therapy of prostate cancer.

Objective.Treatment planning of radiation therapy is a time-consuming task. It is desirable to develop automatic planning approaches to generate plans favorable to physicians. The purpose of this study is to develop a deep learning based virtual physician network (VPN) that models physician's preference on plan approval for prostate cancer stereotactic body radiation therapy (SBRT).Approach.VPN takes one planning target volume (PTV) and eight organs at risk structure images, as well as a dose distribution of a plan seeking approval as input. It outputs a probability of approving the plan, and a dose distribution indicating improvements to the input dose. Due to the lack of unapproved plans in our database, VPN is trained using an adversarial framework. 68 prostate cancer patients who received 45Gyin 5-fraction SBRT were selected in this study, with 60 patients for training and cross validation, and 8 patients for independent testing.Main results.The trained VPN was able to differentiate approved and unapproved plans with Area under the curve 0.97 for testing data. For unapproved plans, after applying VPN's suggested dose improvement, the improved dose agreed with ground truth with relative differences2.03±2.17%for PTVD98%,0.49±0.29%for PTVV95%,3.08±2.24%for penile bulbDmean,3.73±2.20%for rectumV50%,and2.06±1.73%for bladderV50%.Significance.VPN was developed to accurately model a physician's preference on plan approval and to provide suggestions on how to improve the dose distribution.

MR image reconstruction from undersampled data for image-guided radiation therapy using a patient-specific deep manifold image prior.

Introduction: Recent advancements in radiotherapy (RT) have allowed for the integration of a Magnetic Resonance (MR) imaging scanner with a medical linear accelerator to use MR images for image guidance to position tumors against the treatment beam. Undersampling in MR acquisition is desired to accelerate the imaging process, but unavoidably deteriorates the reconstructed image quality. In RT, a high-quality MR image of a patient is available for treatment planning. In light of this unique clinical scenario, we proposed to exploit the patient-specific image prior to facilitate high-quality MR image reconstruction. Methods: Utilizing the planning MR image, we established a deep auto-encoder to form a manifold of image patches of the patient. The trained manifold was then incorporated as a regularization to restore MR images of the same patient from undersampled data. We performed a simulation study using a patient case, a real patient study with three liver cancer patient cases, and a phantom experimental study using data acquired on an in-house small animal MR scanner. We compared the performance of the proposed method with those of the Fourier transform method, a tight-frame based Compressive Sensing method, and a deep learning method with a patient-generic manifold as the image prior. Results: In the simulation study with 12.5% radial undersampling and 15% increase in noise, our method improved peak-signal-to-noise ratio by 4.46dB and structural similarity index measure by 28% compared to the patient-generic manifold method. In the experimental study, our method outperformed others by producing reconstructions of visually improved image quality.

Change in image-guided planning strategies over time impacts oncologic and survival outcomes for intracavitary cervical cancer brachytherapy.

PURPOSE: Intracavitary cervical brachytherapy (BT) has transitioned from a two-dimensional nonvolumetric (NV) dosimetry system to three-dimensional computed tomography (CT) and/or magnetic resonance imaging (MRI)-based planning techniques. The purpose of this study is to retrospectively evaluate the relative improvements in image-guided planning strategies over time with regards to dosimetry, survival, and toxicity. METHODS AND MATERIALS: A single site retrospective review of 95 locally advanced cervical cancer patients treated with concurrent chemoradiation and high dose rate BT from 2009 to 2016 were divided into three BT planning groups: point-A based NV dosimetry using CT imaging (n = 37), CT-based volumetric dosimetry (n = 33), and MRI-based volumetric dosimetry (n = 25). Overall survival (OS), progression free survival (PFS), and pelvic control (PC) at 5 years were plotted using Kaplan-Meier curves. Univariate and multivariate (MVA) cox proportional-hazards models calculated hazard-ratios (HZ). Finally, acute and late grade 3-4 toxicities were compared between the cohorts. RESULTS: Both MRI and CT had significantly less D2cc to bowel (p < 0.001) and sigmoid (p < 0.001) compared to NV-based planning. On MVA, age (<60 vs. ≥60 years) was significant for worse 5-year OS (HZ: 2.48) and PC (HZ: 5.25). MRI, with NV as the reference, had significantly improved 5-year OS (HZ: 0.26), PFS (HZ: 0.34) and PC (HZ: 0.16). There was no significant difference in grade ≥3 toxicities between the cohorts. CONCLUSIONS: CT and MRI-based 3D planning had significantly less D2cc to bowel and sigmoid. MRI-based planning had significant improvement in 5-year OS, PFS, and LC compared to NV on MVA.

Is There Really a Relationship Between Empathy and Aggression? Evidence From Physiological and Self-Report Measures.

A strong relationship between empathy and aggression has traditionally been argued, but a recent meta-analysis showed that this relationship is surprisingly weak. However, none of the studies that were analyzed in the meta-analysis used physiological measures of empathy to assess differences between aggressive and nonaggressive subjects. The present study evaluated the activity of the corrugator and zygomatic muscles, galvanic skin response, and heart rate response to pictures with different social content in 30 aggressive and 30 nonaggressive subjects. Self-report measures of emotion and empathy were also evaluated. The results did not show significant differences in any of the physiological measures of affective empathy or subjective measures of emotion. Significant differences were found only in cognitive empathy, in which nonaggressive subjects had higher scores than aggressive subjects. These results suggest that intervention programs should focus on increasing cognitive empathy and exploring other variables, such as emotional self-regulation and callous-unemotional traits. We also suggest exploring other ways of understanding affective empathy.

Improving efficiency of training a virtual treatment planner network via knowledge-guided deep reinforcement learning for intelligent automatic treatment planning of radiotherapy.

PURPOSE: We previously proposed an intelligent automatic treatment planning framework for radiotherapy, in which a virtual treatment planner network (VTPN) is built using deep reinforcement learning (DRL) to operate a treatment planning system (TPS) by adjusting treatment planning parameters in it to generate high-quality plans. We demonstrated the potential feasibility of this idea in prostate cancer intensity-modulated radiation therapy (IMRT). Despite the success, the process to train a VTPN via the standard DRL approach with an ϵ-greedy algorithm was time-consuming. The required training time was expected to grow with the complexity of the treatment planning problem, preventing the development of VTPN for more complicated but clinically relevant scenarios. In this study, we proposed a novel knowledge-guided DRL (KgDRL) approach that incorporated knowledge from human planners to guide the training process to improve the efficiency of training a VTPN. METHOD: Using prostate cancer IMRT as a test bed, we first summarized a number of rules in the actions of adjusting treatment planning parameters of our in-house TPS. During the training process of VTPN, in addition to randomly navigating the large state-action space, as in the standard DRL approach using the ϵ-greedy algorithm, we also sampled actions defined by the rules. The priority of sampling actions from rules decreased over the training process to encourage VTPN to explore new policy on parameter adjustment that were not covered by the rules. To test this idea, we trained a VTPN using KgDRL and compared its performance with another VTPN trained using the standard DRL approach. Both networks were trained using 10 training patient cases and five additional cases for validation, while another 59 cases were employed for the evaluation purpose. RESULTS: It was found that both VTPNs trained via KgDRL and standard DRL spontaneously learned how to operate the in-house TPS to generate high-quality plans, achieving plan quality scores of 8.82 (±0.29) and 8.43 (±0.48), respectively. Both VTPNs outperformed treatment planning purely based on the rules, which had a plan score of 7.81 (±1.59). VTPN trained with eight episodes using KgDRL was able to perform similar to that trained using DRL with 100 epochs. The training time was reduced from more than a week to ~13 hrs. CONCLUSION: The proposed KgDRL framework was effective in accelerating the training process of a VTPN by incorporating human knowledge, which will facilitate the development of VTPN for more complicated treatment planning scenarios.

Simultaneous needle catheter selection and dwell time optimization for preplanning of high-dose-rate brachytherapy of prostate cancer.

PURPOSE: Needle catheter positions critically affect the quality of treatment plans in prostate cancer high-dose-rate (HDR) brachytherapy. The current standard needle positioning approach is based on human intuition, which cannot guarantee a high-quality plan. This study proposed a method to simultaneously select needle catheter positions and determine dwell time for preplanning of HDR brachytherapy of prostate cancer. METHODS: We formulated the needle catheter selection problem and inverse dwell time optimization problem in a unified framework. In addition to the dose objectives of the planning target volume (PTV) and organs at risk (OARs), the objective function incorporated a group-sparsity term with a needle-specific adaptive weighting scheme to generate high-quality plans with the minimal number of needle catheters. The optimization problem was solved by a fast-iterative shrinkage-thresholding algorithm. For validation purposes, we tested the proposed algorithm on 10 patient cases previously treated at our institution and compared the resulting plans with plans generated using needle catheters selected manually. RESULTS: Compared to the plan with manually selected needle catheters, when normalizing both plans to the same PTV coverage V 100% = 95%, the plans generated by the proposed algorithm reduced median V 125% from 65% to 64%, but increased median V 150% from 35% to 38%, and V 200% from 14% to 16%. All planning objectives were met. All clinically important dosimetric parameters of OARs were reduced. D 1cc of bladder and rectum were reduced from 8.57 Gy to 8.50 Gy and from 7.24 Gy to 6.80 Gy, respectively. D max of urethra was reduced from 15.85 Gy to 15.77 Gy. The median number of selected needle catheters was reduced by two. The computational time for solving the proposed optimization problem was ∼90 s using MATLAB. CONCLUSION: The proposed algorithm was able to generate plans for prostate cancer HDR brachytherapy preplanning with increased median conformity index (0.73-0.77) and slightly lower median homogeneity index (0.64-0.62) with the number of selected needles reduced by two compared to the manual needle selection approach.

Predicting which patients may benefit from the hybrid intracavitary+interstitial needle (IC/IS) applicator for advanced cervical cancer: A dosimetric comparison and toxicity benefit analysis.

PURPOSE: The purpose of this study is to compare the predicted rate of local control and bladder and rectum toxicity rates for image-guided adaptive brachytherapy plans using a tandem and ovoid (T/O) applicator versus using a simulated hybrid intracavitary/interstitial tandem and ring applicator with needles (T/R + N) for patients with locally advanced cervical cancer (LACC). METHODS AND MATERIALS: Patients with ≥ FIGO Stage IIB locally advanced cervical cancer treated with T/O from a single institution were included. Simulated treatment plans were created with a T/R + N applicator for the best high-risk clinical target volume (CTV) coverage and minimal dose to organs at risk. Three-year local control rate was estimated using published dose-volume effect relationships. Next, the high-risk CTV EQD2 D90 of T/R + N plans were calculated, and bladder and rectum toxicity rates were estimated. Analysis was performed in subpatient groups defined based on tumor volume and ratio of maximal and minimal tumor radii (RR) that reflects tumor shape asymmetry. RESULTS: Improvements in predicted local control rate for the T/R + N were 0.8, 4.1, 1.6, and 3.9% for groups with tumor volume <35 cc, ≥35 cc, RR < 2.0, and ≥2.0, respectively, with the latter three being statistically significant. Predicted reductions in Grade 2-4 toxicity rates of bladder and rectum were significant in all groups except bladder toxicity in tumor volume <35 cc, when T/R + N plans were normalized to the same CTV coverage as the T/O plans. Comparing unnormalized T/R + N plans and T/O plans, predicted toxicity reductions were significant in all groups except rectum toxicity in RR ≥ 2.0. Predicted reduction of toxicity rate was larger for patients with large tumor or large tumor RR, although some reductions were relatively small. CONCLUSIONS: Cases with large tumor (volume ≥35 cc) or large tumor asymmetry (RR ≥ 2.0) would probably benefit more from the use of hybrid applicators.

Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-D deep learning approach.

Automatic sigmoid colon segmentation in CT for radiotherapy treatment planning is challenging due to complex organ shape, close distances to other organs, and large variations in size, shape, and filling status. The patient bowel is often not evacuated, and CT contrast enhancement is not used, which further increase problem difficulty. Deep learning (DL) has demonstrated its power in many segmentation problems. However, standard 2-D approaches cannot handle the sigmoid segmentation problem due to incomplete geometry information and 3-D approaches often encounters the challenge of a limited training data size. Motivated by human's behavior that segments the sigmoid slice by slice while considering connectivity between adjacent slices, we proposed an iterative 2.5-D DL approach to solve this problem. We constructed a network that took an axial CT slice, the sigmoid mask in this slice, and an adjacent CT slice to segment as input and output the predicted mask on the adjacent slice. We also considered other organ masks as prior information. We trained the iterative network with 50 patient cases using five-fold cross validation. The trained network was repeatedly applied to generate masks slice by slice. The method achieved average Dice similarity coefficients of 0.82 0.06 and 0.88 0.02 in 10 test cases without and with using prior information.

A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy.

In post-operative radiotherapy for prostate cancer, precisely contouring the clinical target volume (CTV) to be irradiated is challenging, because the cancerous prostate gland has been surgically removed, so the CTV encompasses the microscopic spread of tumor cells, which cannot be visualized in clinical images like computed tomography or magnetic resonance imaging. In current clinical practice, physicians' segment CTVs manually based on their relationship with nearby organs and other clinical information, but this allows large inter-physician variability. Automating post-operative prostate CTV segmentation with traditional image segmentation methods has yielded suboptimal results. We propose using deep learning to accurately segment post-operative prostate CTVs. The model proposed is trained using labels that were clinically approved and used for patient treatment. To segment the CTV, we segment nearby organs first, then use their relationship with the CTV to assist CTV segmentation. To ease the encoding of distance-based features, which are important for learning both the CTV contours' overlap with the surrounding OARs and the distance from their borders, we add distance prediction as an auxiliary task to the CTV network. To make the DL model practical for clinical use, we use Monte Carlo dropout (MCDO) to estimate model uncertainty. Using MCDO, we estimate and visualize the 95% upper and lower confidence bounds for each prediction which informs the physicians of areas that might require correction. The model proposed achieves an average Dice similarity coefficient (DSC) of 0.87 on a holdout test dataset, much better than established methods, such as atlas-based methods (DSC<0.7). The predicted contours agree with physician contours better than medical resident contours do. A reader study showed that the clinical acceptability of the automatically segmented CTV contours is equal to that of approved clinical contours manually drawn by physicians. Our deep learning model can accurately segment CTVs with the help of surrounding organ masks. Because the DL framework can outperform residents, it can be implemented practically in a clinical workflow to generate initial CTV contours or to guide residents in generating these contours for physicians to review and revise. Providing physicians with the 95% confidence bounds could streamline the review process for an efficient clinical workflow as this would enable physicians to concentrate their inspecting and editing efforts on the large uncertain areas.

Operating a treatment planning system using a deep-reinforcement learning-based virtual treatment planner for prostate cancer intensity-modulated radiation therapy treatment planning.

PURPOSE: In the treatment planning process of intensity-modulated radiation therapy (IMRT), a human planner operates the treatment planning system (TPS) to adjust treatment planning parameters, for example, dose volume histogram (DVH) constraints' locations and weights, to achieve a satisfactory plan for each patient. This process is usually time-consuming, and the plan quality depends on planer's experience and available planning time. In this study, we proposed to model the behaviors of human planners in treatment planning by a deep reinforcement learning (DRL)-based virtual treatment planner network (VTPN), such that it can operate the TPS in a human-like manner for treatment planning. METHODS AND MATERIALS: Using prostate cancer IMRT as an example, we established the VTPN using a deep neural network developed. We considered an in-house optimization engine with a weighted quadratic objective function. Virtual treatment planner network was designed to observe an intermediate plan DVHs and decide the action to improve the plan by changing weights and threshold dose in the objective function. We trained the VTPN in an end-to-end DRL process in 10 patient cases. A plan score was used to measure plan quality. We demonstrated the feasibility and effectiveness of the trained VTPN in another 64 patient cases. RESULTS: Virtual treatment planner network was trained to spontaneously learn how to adjust treatment planning parameters to generate high-quality treatment plans. In the 64 testing cases, with initialized parameters, quality score was 4.97 (±2.02), with 9.0 being the highest possible score. Using VTPN to perform treatment planning improved quality score to 8.44 (±0.48). CONCLUSIONS: To our knowledge, this was the first time that intelligent treatment planning behaviors of human planner in external beam IMRT are autonomously encoded in an artificial intelligence system. The trained VTPN is capable of behaving in a human-like way to produce high-quality plans.

Deep-learning assisted automatic digitization of interstitial needles in 3D CT image based high dose-rate brachytherapy of gynecological cancer.

Digitization of interstitial needles is a complicated and tedious process for the treatment planning of 3D CT image based interstitial high dose-rate brachytherapy (HDRBT) of gynecological cancer. We developed a deep-learning assisted auto-digitization method for interstitial needles. The digitization method consisted of two steps. The first step used a deep neural network with a U-net structure to segment all needles from CT images. The second step simultaneously clustered the segmented voxels into different needle groups and generated the needle central trajectories by solving an optimization problem. We evaluated the effectiveness of the developed method in ten interstitial HDRBT patient cases that were not used in the training of the U-net. Average number of needles per case was 20.7. For the segmentation step, average Dice similarity coefficient between automatic and manual segmentation was 0.93. For the digitization step, Hausdorff distance between needle trajectories determined by our method and manually by qualified medical physicists was ~0.71 mm on average and mean difference of tip positions was ~0.63 mm, which were considered acceptable for HDRBT treatment planning. It took ~5 min to complete the digitization process of an interstitial HDRBT case. The achieved accuracy and efficiency made our method clinically attractive.

Deep-learning-assisted automatic digitization of applicators in 3D CT image-based high-dose-rate brachytherapy of gynecological cancer.

PURPOSE: Applicator digitization is one of the most critical steps in 3D high-dose-rate brachytherapy (HDRBT) treatment planning. Motivated by recent advances in deep-learning, we propose a deep-learning-assisted applicator digitization method for 3D CT image-based HDRBT. This study demonstrates its feasibility and potential in gynecological cancer HDRBT. METHODS AND MATERIALS: Our method consisted of two steps. The first step used a U-net to segment applicator regions. We trained the U-net using two-dimensional CT images with a tandem-and-ovoid (T&O) applicator and corresponding applicator mask images. The second step applied a spectral clustering method and a polynomial curve fitting method to extract applicator central paths. We evaluated the accuracy, efficiency, and robustness of our method in different scenarios including other T&O cases that were not used in training, a T&O case scanned with cone-beam CT, and Y-tandem and cylinder-applicator cases. RESULTS: In test cases with a T&O applicator, average 3D Dice similarity coefficient between automatic and manual segmented applicator regions was 0.93. Average distance between tip positions and average Hausdorff distance between applicator channels determined by our method and manually were 0.64 mm and 0.68 mm, respectively. Although trained only using CT images of T&O cases, our tool can also digitize Y-tandem, cylinder applicator, and T&O applicator scanned in cone-beam CT with error of tip position and Hausdorff distance <1 mm. Computation time was ∼15 s per case. CONCLUSIONS: We have developed a deep-learning-assisted applicator digitization tool for 3D CT image-based HDRBT of gynecological cancer. The achieved accuracy, efficiency, and robustness made our tool clinically attractive.

Intelligent inverse treatment planning via deep reinforcement learning, a proof-of-principle study in high dose-rate brachytherapy for cervical cancer.

Inverse treatment planning in radiation therapy is formulated as solving optimization problems. The objective function and constraints consist of multiple terms designed for different clinical and practical considerations. Weighting factors of these terms are needed to define the optimization problem. While a treatment planning optimization engine can solve the optimization problem with given weights, adjusting the weights to yield a high-quality plan is typically performed by a human planner. Yet the weight-tuning task is labor intensive, time consuming, and it critically affects the final plan quality. An automatic weight-tuning approach is strongly desired. The procedure of weight adjustment to improve the plan quality is essentially a decision-making problem. Motivated by the tremendous success in deep learning for decision making with human-level intelligence, we propose a novel framework to adjust the weights in a human-like manner. This study used inverse treatment planning in high-dose-rate brachytherapy (HDRBT) for cervical cancer as an example. We developed a weight-tuning policy network (WTPN) that observes dose volume histograms of a plan and outputs an action to adjust organ weighting factors, similar to the behaviors of a human planner. We trained the WTPN via end-to-end deep reinforcement learning. Experience replay was performed with the epsilon greedy algorithm. After training was completed, we applied the trained WTPN to guide treatment planning of five testing patient cases. It was found that the trained WTPN successfully learnt the treatment planning goals and was able to guide the weight tuning process. On average, the quality score of plans generated under the WTPN's guidance was improved by ~8.5% compared to the initial plan with arbitrarily set weights, and by 10.7% compared to the plans generated by human planners. To our knowledge, this was the first time that a tool was developed to adjust organ weights for the treatment planning optimization problem in a human-like fashion based on intelligence learnt from a training process, which was different from existing strategies based on pre-defined rules. The study demonstrated potential feasibility to develop intelligent treatment planning approaches via deep reinforcement learning.

SPARE: Sparse-view reconstruction challenge for 4D cone-beam CT from a 1-min scan.

PURPOSE: Currently, four-dimensional (4D) cone-beam computed tomography (CBCT) requires a 3-4 min full-fan scan to ensure usable image quality. Recent advancements in sparse-view 4D-CBCT reconstruction have opened the possibility to reduce scan time and dose. The aim of this study is to provide a common framework for systematically evaluating algorithms for 4D-CBCT reconstruction from a 1-min scan. Using this framework, the AAPM-sponsored SPARE Challenge was conducted in 2018 to identify and compare state-of-the-art algorithms. METHODS: A clinically realistic CBCT dataset was simulated using patient CT volumes from the 4D-Lung database. The selected patients had multiple 4D-CT sessions, where the first 4D-CT was used as the prior CT, and the rest were used as the ground truth volumes for simulating CBCT projections. A GPU-based Monte Carlo tool was used to simulate the primary, scatter, and quantum noise signals. A total of 32 CBCT scans of nine patients were generated. Additional qualitative analysis was performed on a clinical Varian and clinical Elekta dataset to validate the simulation study. Participants were blinded from the ground truth, and were given 3 months to apply their reconstruction algorithms to the projection data. The submitted reconstructions were analyzed in terms of root-mean-squared-error (RMSE) and structural similarity index (SSIM) with the ground truth within four different region-of-interests (ROI) - patient body, lungs, planning target volume (PTV), and bony anatomy. Geometric accuracy was quantified as the alignment error of the PTV. RESULTS: Twenty teams participated in the challenge, with five teams completing the challenge. Techniques involved in the five methods included iterative optimization, motion-compensation, and deformation of the prior 4D-CT. All five methods rendered significant reduction in noise and streaking artifacts when compared to the conventional Feldkamp-Davis-Kress (FDK) algorithm. The RMS of the three-dimensional (3D) target registration error of the five methods ranged from 1.79 to 3.00 mm. Qualitative observations from the Varian and Elekta datasets mostly concur with those from the simulation dataset. Each of the methods was found to have its own strengths and weaknesses. Overall, the MA-ROOSTER method, which utilizes a 4D-CT motion model for temporal regularization, had the best and most consistent image quality and accuracy. CONCLUSION: The SPARE Challenge represents the first framework for systematically evaluating state-of-the-art algorithms for 4D-CBCT reconstruction from a 1-min scan. Results suggest the potential for reducing scan time and dose for 4D-CBCT. The challenge dataset and analysis framework are publicly available for benchmarking future reconstruction algorithms.