Development of automated region of interest selection algorithms for surface-guided radiation therapy of breast cancer.

To investigate automation of the preparation of the region of interest (ROI) for surface-guided radiotherapy (SGRT) of the whole breast with two algorithms based on contour anatomies: using the body contour, and using the breast contour. The patient dataset used for modeling consisted of 39 breast cancer patients previously treated with SGRT. The patient's anatomical structures (body and ipsilateral breast) were retrieved from the planning system, and the clinical ROI (cROI) drawn by the planners was retrieved from the SGRT system for comparison. For the body-contour-based algorithm, a convolutional neural network (MobileNet-v2) was utilized to train a synthetic human model dataset to predict body joint locations. With the body joint location knowledge, an automated ROI (aROIbody ) can be created based on: (1) the superior-inferior (S-I) borders defined by the joint locations, (2) the left-right (L-R) borders defined with 3/4 of chest width, and (3) a curation of the ROI to avoid the ipsilateral armpit. For the breast-contour-based algorithm, an aROIbreast was created by first defining the ROI in the S-I direction with the ipsilateral breast boundaries. Other steps are the same as with the body-contour-based algorithm. Among the 39 patients, 24 patients were used to fine-tune the algorithm parameters, and the remaining 15 patients were used to evaluate the quality of the aROIs against the cROIs. A blinded evaluation was performed by three SGRT expert physicists to rate the acceptability and the quality (1-10 scale) of the aROIs and cROIs, and the dice similarity coefficient (DSC) was also calculated to compare the similarity between the aROIs and cROIs. The results showed that the average acceptability was 14/15 (range: 13/15-15/15) for cROIs, 13.3/15 (range: 13/15-14/15) for aROIbody , and 14.6/15 (range: 14/15-15/15) for aROIbreast . The average quality was 7.4 ± 0.8 for cROIs, 8.1 ± 1.2 for aROIbody , and 8.2 ± 0.9 for aROIbreast . The DSC with cROIs was 0.81 ± 0.06 for aROIbody , and 0.83 ± 0.04 for aROIbreast . The ROI creation time was ∼120 s for clinical, 1.3 s for aROIbody , and 1.2 s for aROIbreast . The proposed automated algorithms can improve the ROI compliance with the SGRT protocol, with a shortened preparation time. It is ready to be integrated into the clinical workflow for automated ROI preparation.

TrDosePred: A deep learning dose prediction algorithm based on transformers for head and neck cancer radiotherapy.

BACKGROUND: Intensity-Modulated Radiation Therapy (IMRT) has been the standard of care for many types of tumors. However, treatment planning for IMRT is a time-consuming and labor-intensive process. PURPOSE: To alleviate this tedious planning process, a novel deep learning based dose prediction algorithm (TrDosePred) was developed for head and neck cancers. METHODS: The proposed TrDosePred, which generated the dose distribution from a contoured CT image, was a U-shape network constructed with a convolutional patch embedding and several local self-attention based transformers. Data augmentation and ensemble approach were used for further improvement. It was trained based on the dataset from Open Knowledge-Based Planning Challenge (OpenKBP). The performance of TrDosePred was evaluated with two mean absolute error (MAE) based scores utilized by OpenKBP challenge (i.e., Dose score and DVH score) and compared to the top three approaches of the challenge. In addition, several state-of-the-art methods were implemented and compared to TrDosePred. RESULTS: The TrDosePred ensemble achieved the dose score of 2.426 Gy and the DVH score of 1.592 Gy on the test dataset, ranking at 3rd and 9th respectively in the leaderboard on CodaLab as of writing. In terms of DVH metrics, on average, the relative MAE against the clinical plans was 2.25% for targets and 2.17% for organs at risk. CONCLUSIONS: A transformer-based framework TrDosePred was developed for dose prediction. The results showed a comparable or superior performance as compared to the previous state-of-the-art approaches, demonstrating the potential of transformer to boost the treatment planning procedures.

Evaluating the impact of real-time multicriteria optimizers integrated with interactive plan navigation tools for HDR brachytherapy.

PURPOSE: Currently in high-dose-rate (HDR) brachytherapy planning, manual fine-tuning of an objective function is a common practice. Furthermore, automated planning approaches such as multicriteria optimization (MCO) are still limited to the automatic generation of a single treatment plan. This study aims to quantify planning efficiency gains when using a graphics processing unit-based MCO (gMCO) algorithm combined with a novel graphical user interface (gMCO-GUI) that integrates efficient automated and interactive plan navigation tools. METHODS AND MATERIALS: The gMCO algorithm was used to generate 1000 Pareto optimal plans per case for 379 prostate cases. gMCO-GUI was developed to allow plan navigation through all plans. gMCO-GUI integrates interactive parameter selection tools directly with the optimization algorithm to allow plan navigation. The quality of each plan was evaluated based on the Radiation Treatment Oncology Group 0924 protocol and a more stringent institutional protocol (INSTp). gMCO-GUI allows real-time time display of the dose-volume histogram indices, the dose-volume histogram curves, and the isodose lines during the plan navigation. RESULTS: Over the 379 cases, the fraction of Radiation Treatment Oncology Group 0924 protocol valid plans with target coverage greater than 95% was 90.8%, compared with 66.0% for clinical plans. The fraction of INSTp valid plans with target coverage greater than 95% was 81.8%, compared with 62.3% for clinical plans. The average time to compute 1000 deliverable plans with gMCO was 12.5 s, including the full computation of the 3D dose distributions. CONCLUSIONS: Combining the gMCO algorithm with automated and interactive plan navigation tools resulted in simultaneous gains in both plan quality and planning efficiency.

A GPU-based multi-criteria optimization algorithm for HDR brachytherapy.

Currently in HDR brachytherapy planning, a manual fine-tuning of an objective function is necessary to obtain case-specific valid plans. This study intends to facilitate this process by proposing a patient-specific inverse planning algorithm for HDR prostate brachytherapy: GPU-based multi-criteria optimization (gMCO). Two GPU-based optimization engines including simulated annealing (gSA) and a quasi-Newton optimizer (gL-BFGS) were implemented to compute multiple plans in parallel. After evaluating the equivalence and the computation performance of these two optimization engines, one preferred optimization engine was selected for the gMCO algorithm. Five hundred sixty-two previously treated prostate HDR cases were divided into validation set (100) and test set (462). In the validation set, the number of Pareto optimal plans to achieve the best plan quality was determined for the gMCO algorithm. In the test set, gMCO plans were compared with the physician-approved clinical plans. Our results indicated that the optimization process is equivalent between gL-BFGS and gSA, and that the computational performance of gL-BFGS is up to 67 times faster than gSA. Over 462 cases, the number of clinically valid plans was 428 (92.6%) for clinical plans and 461 (99.8%) for gMCO plans. The number of valid plans with target [Formula: see text] coverage greater than 95% was 288 (62.3%) for clinical plans and 414 (89.6%) for gMCO plans. The mean planning time was 9.4 s for the gMCO algorithm to generate 1000 Pareto optimal plans. In conclusion, gL-BFGS is able to compute thousands of SA equivalent treatment plans within a short time frame. Powered by gL-BFGS, an ultra-fast and robust multi-criteria optimization algorithm was implemented for HDR prostate brachytherapy. Plan pools with various trade-offs can be created with this algorithm. A large-scale comparison against physician approved clinical plans showed that treatment plan quality could be improved and planning time could be significantly reduced with the proposed gMCO algorithm.

A multi-criteria optimization approach for HDR prostate brachytherapy: II. Benchmark against clinical plans.

The current iterative approach to inverse planning of high dose rate treatment planning can be time consuming. The purpose of this two-part study is to streamline the planning process while maintaining plan quality. In this second part, a multi-criteria optimization (MCO) planning algorithm is proposed and benchmarked against a standard planning algorithm. With a set of previously established regression models, a patient-specific valid solution space on the Pareto surface was predicted based on the anchor plans results. Alternative plans generated alongside the partial Pareto front were presented to the planner, and one plan was selected as the MCO plan. The dosimetric parameters results as well as the planning time were compared between the MCO plans and the physician-approved standard plans for 236 prostate cases. Results show that the urethra is better spared with MCO planning than with standard planning (a lower mean urethral D 10 value of 2.25%). The overall MCO plan quality also outperforms the standard plan quality, since MCO planning is able to increase the frequency of clinically acceptable plans meeting all of RTOG criteria simultaneously without any human intervention (from 83.05% to 97.46%). Finally, the average MCO planning time is [Formula: see text] without any interventions of treatment planners. The presented MCO planning algorithm constitutes a robust and automated way to improve treatment quality in brachytherapy.

A multi-criteria optimization approach for HDR prostate brachytherapy: I. Pareto surface approximation.

High dose rate (HDR) brachytherapy planning usually involves an iterative process of refining planning objectives until a clinically acceptable plan is produced. The purpose of this two-part study is to improve current planning practice by designing a novel inverse planning algorithm based on multi-criteria optimization (MCO). In the first part, complete Pareto surfaces were approximated and studied for prostate cases. A Pareto surface approximation algorithm was implemented within the framework of Inverse Planning Simulated Annealing. The Pareto surfaces of 140 prostate cases were approximated with the proposed MCO algorithm. For each case, the Pareto surface was represented by automatically generating 300 Pareto optimal plans, and the clinically acceptable region was identified. Thus, 42 000 Pareto optimal plans were created to characterize Pareto surfaces for all the cases. In addition, the relationship between the clinically acceptable region and four anchor plans was studied. As a result, a set of polynomial regression models was extracted to rapidly predict the clinically acceptable region on the Pareto surface based on anchor plans. Pareto surfaces for HDR brachytherapy prostate cases were well characterized in this study. The proposed regression models may help define the most relevant solution phase space.

The study of external dose rate and retained body activity of patients receiving 131I therapy for differentiated thyroid carcinoma.

Radiation safety is an integral part of targeted radionuclide therapy. The aim of this work was to study the external dose rate and retained body activity as functions of time in differentiated thyroid carcinoma patients receiving 131I therapy. Seventy patients were stratified into two groups: the ablation group (A) and the follow-up group (FU). The patients' external dose rate was measured, and simultaneously, their retained body radiation activity was monitored at various time points. The equations of the external dose rate and the retained body activity, described as a function of hours post administration, were fitted. Additionally, the release time for patients was calculated. The reduction in activity in the group receiving a second or subsequent treatment was more rapid than the group receiving only the initial treatment. Most important, an expeditious method was established to indirectly evaluate the retained body activity of patients by measuring the external dose rate with a portable radiation survey meter. By this method, the calculated external dose rate limits are 19.2, 8.85, 5.08 and 2.32 µSv·h-1 at 1, 1.5, 2 and 3 m, respectively, according to a patient's released threshold level of retained body activity <400 MBq. This study is beneficial for radiation safety decision-making.

Estimating radiation absorbed dose of individuals nearby 131I-treated hyperthyroid patients.

The purpose of this study was to systematically provide a database for estimating radiation dose of individuals nearby (131)I-treated hyperthyroid patients. External dose rates were measured on 48 hyperthyroid patients using a survey meter in front of patients' thyroid glands. The initial measurement was recorded within 30 min post radioiodine administration at 0.3 m, 0.6 m, 1 m, and 2 m. Follow-up measurements were carried out up to 12 d post radioiodine administration. In addition, ambient dose rates of different locations such as wards, patients' washrooms, medical staffs' workplaces, and corridors were also measured. The Na131I treatment dose administered in this study ranged from 74-555 MBq. Significant positive correlation between dose rate at 1 m and the administered dose was found in this study. The normalized external dose rates at 0.3 m were 0.234 µSv h(-1) MBq(-1) at 0.5 h, 0.325 µSv h(-1) MBq(-1) at 4 h, 0.308 µSv h(-1) MBq(-1) at 6 h, 0.301 µSv h(-1) MBq(-1) at 24 h, 0.259 µSv h(-1) MBq(-1) at 48 h, 0.234 µSv h(-1) MBq(-1) at 72 h, 0.224 µSv h(-1) MBq(-1) at 96 h, 0.186 µSv h(-1) MBq(-1) at 120 h, and 0.158 µSv h(-1) MBq(-1) at 144 h, respectively. With these results, the authors estimated radioactive radiation dose for the public and medical staffs near (131)I-treated hyperthyroid patients. This study is beneficial for radiation safety decision-making.