DVH-Based Inverse Planning Using Monte Carlo Dosimetry for LDR Prostate Brachytherapy

Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy

Objective.In brachytherapy, deep learning (DL) algorithms have shown the capability of predicting 3D dose volumes. The reliability and accuracy of such methodologies remain under scrutiny for prospective clinical applications. This study aims to establish fast DL-based predictive dose algorithms for low-dose rate (LDR) prostate brachytherapy and to evaluate their uncertainty and stability.Approach.Data from 200 prostate patients, treated with125I sources, was collected. The Monte Carlo (MC) ground truth dose volumes were calculated with TOPAS considering the interseed effects and an organ-based material assignment. Two 3D convolutional neural networks, UNet and ResUNet TSE, were trained using the patient geometry and the seed positions as the input data. The dataset was randomly split into training (150), validation (25) and test (25) sets. The aleatoric (associated with the input data) and epistemic (associated with the model) uncertainties of the DL models were assessed.Main results.For the full test set, with respect to the MC reference, the predicted prostateD90metric had mean differences of -0.64% and 0.08% for the UNet and ResUNet TSE models, respectively. In voxel-by-voxel comparisons, the average global dose difference ratio in the [-1%, 1%] range included 91.0% and 93.0% of voxels for the UNet and the ResUNet TSE, respectively. One forward pass or prediction took 4 ms for a 3D dose volume of 2.56 M voxels (128 × 160 × 128). The ResUNet TSE model closely encoded the well-known physics of the problem as seen in a set of uncertainty maps. The ResUNet TSE rectum D2cchad the largest uncertainty metric of 0.0042.Significance.The proposed DL models serve as rapid dose predictors that consider the patient anatomy and interseed attenuation effects. The derived uncertainty is interpretable, highlighting areas where DL models may struggle to provide accurate estimations. The uncertainty analysis offers a comprehensive evaluation tool for dose predictor model assessment.

Automatic planning for head and neck seed implant brachytherapy based on deep convolutional neural network dose engine

BACKGROUND

Seed implant brachytherapy (SIBT) is an effective treatment modality for head and neck (H&N) cancers; however, current clinical planning requires manual setting of needle paths and utilizes inaccurate dose calculation algorithms.

PURPOSE

This study aims to develop an accurate and efficient deep convolutional neural network dose engine (DCNN-DE) and an automatic SIBT planning method for H&N SIBT.

METHODS

A cohort of 25 H&N patients who received SIBT was utilized to develop and validate the methods. The DCNN-DE was developed based on 3D-unet model. It takes single seed dose distribution from a modified TG-43 method, the CT image and a novel inter-seed shadow map (ISSM) as inputs, and predicts the dose map of accuracy close to the one from Monte Carlo simulations (MCS). The ISSM was proposed to better handle inter-seed attenuation. The accuracy and efficacy of the DCNN-DE were validated by comparing with other methods taking MCS dose as reference. For SIBT planning, a novel strategy inspired by clinical practice was proposed to automatically generate parallel or non-parallel potential needle paths that avoid puncturing bone and critical organs. A heuristic-based optimization method was developed to optimize the seed positions to meet clinical prescription requirements. The proposed planning method was validated by re-planning the 25 cases and comparing with clinical plans.

RESULTS

The absolute percentage error in the TG-43 calculation for CTV V100 and D90 was reduced from 5.4% and 13.2% to 0.4% and 1.1% with DCNN-DE, an accuracy improvement of 93% and 92%, respectively. The proposed planning method could automatically obtain a plan in 2.5 ± 1.5 min. The generated plans were judged clinically acceptable with dose distribution comparable with those of the clinical plans.

CONCLUSIONS

The proposed method can generate clinically acceptable plans quickly with high accuracy in dose evaluation, and thus has a high potential for clinical use in SIBT.

Embedding expertise knowledge into inverse treatment planning for low-dose-rate brachytherapy of hepatic malignancies

BACKGROUND

Leveraging the precision of its radiation dose distribution and the minimization of postoperative complications, low-dose-rate (LDR) permanent seed brachytherapy is progressively adopted in addressing hepatic malignancies.

PURPOSE

The present study endeavors to devise a sophisticated treatment planning system (TPS) to optimize LDR brachytherapy for hepatic lesions.

METHODS

Our TPS encompasses four integral modules: multi-organ segmentation, seed distribution initialization, puncture pathway selection, and inverse dose planning. By amalgamating an array of deep learning models, the segmentation module proficiently labels 17 discrete abdominal targets within the images. We introduce a knowledge-based seed distribution initialization methodology that discerns the most analogous tumor shape in the reference treatment plan from the knowledge base. Subsequently, the seed distribution from the reference plan is transmuted to the current case, thus establishing seed distribution initialization. Furthermore, we parameterize the puncture needles and seeds, while concurrently constraining the puncture needle angle through the employment of a virtual puncture panel to augment planning algorithm efficiency. We also presented a user interface that includes a range of interactive features, seamlessly integrated with the treatment planning generation function.

RESULTS

The multi-organ segmentation module, which is trained by 50 cases of in-house CT scans and 694 cases of publicly available CT scans, achieved average Dice of 0.80 and Hausdorff distance of 5.2 mm in testing datasets. The results demonstrate that knowledge-based initialization exhibits a marked enhancement in expediting the convergence rate. Our TPS also demonstrates a dominant advantage in dose-volume-histogram criteria and execution time in comparison to commercial TPS.

CONCLUSION

The study proposes an innovative treatment planning system for low-dose-rate permanent seed brachytherapy for hepatic malignancies. We show that the generated treatment plans meet clinical requirement.

Monte Carlo-based optimization of glioma capsule design for enhanced brachytherapy

The use of radiotherapy in tumor treatment has become increasingly prominent and has emerged as one of the main tools for treating malignant tumors. Current radiation therapy for glioma employs 125I seeds for brachytherapy, which cannot be combined with radiotherapy and chemotherapy. To address this limitation, this paper proposes a dual-microcavity capsule structure that integrates radiotherapy and chemotherapy. The Monte Carlo simulation method is used to simulate the structure of the dual-microcavity capsule with a 125I liquid radioactive source. Based on the simulation results, two kinds of dual-microcavity capsule structures are optimized, and the optimized dual-microcavity capsule structure is obtained. Finally, the dosimetric parameters of the two optimized dual-microcavity capsule structures are analyzed and compared with those of other 125I seeds. The optimization tests show that the improved dual-capsule dual-microcavity structure is more effective than the single-capsule dual-microcavity structure. At an activity of 5 mCi, the average absorbed dose rate is 71.2 cGy/h in the center of the optimized dual-capsule dual-microcavity structure and 45.8 cGy/h in the center of the optimized single-capsule dual-microcavity structure. Although the radial dose function and anisotropy function exhibite variations from the data of other 125I seeds, they are generally similar. The absorbed dose rate decreases exponentially with increasing distance from the center of the capsule, which can reduce the damage to the surrounding tissues and organs while increasing the dose. The capsule structure has a better irradiation effect than conventional 125I seeds and can accomplish long-term, stable, low-dose continuous irradiation to form local high-dose radiation therapy for glioma.

DVH-based inverse planning for LDR pancreatic brachytherapy

PURPOSE

Pancreatic cancer is one of the common types of malignant cancer. Low-dose-rate (LDR) brachytherapy has shown great efficacy in curing pancreatic cancer. However, a long preoperative planning time and an insufficient tumor dose are common issues. In this paper, we present and validate a method for inverse planning using simulated annealing (SA) for the treatment of pancreatic cancer.

METHODS

The SA method was used for the inverse planning process. With the help of parallel computation and a quick dose field estimation algorithm. This method allowed inverse planning to be performed quickly. A novel length-control method was used to consider and limit the dose of the organ at risk. The effect of this system was validated by calculating the dose-volume histogram metric and time consumption.

RESULTS

Regarding the percentage of the volume receiving 100% of the prescribed dose (V100), this approach yielded an average difference in V100 of 5.01% for the tumor and of 1.32% for the organ at risk in the small tumor group; in the large tumor group, the average difference in V100 was 2.3% for the tumor and - 4.49% for the organ at risk. The average time required for inverse planning was 1.63 ± 0.26 s for small tumors and 3.81 ± 0.51 s for large tumors. Compared with other inverse planning methods, the optimal quality of the plans yielded by this method was further improved.

CONCLUSION

This paper presents a new type of inverse planning method for the treatment of pancreatic cancer based on SA. Compared with other LDR inverse planning methods, the method presented here can provide the prescribed dose to the tumor while considering the dose of the organ at risk. Also, the required time is significantly lower than other methods. All the experimental results indicate that this method is ready to be applied in further clinical studies.

An inverse planning simulated annealing algorithm with adaptive weight adjustment for LDR pancreatic brachytherapy

PURPOSE

The inverse planning simulated annealing (IPSA) algorithm has shown good results in cancer surgical treatment planning. However, an adaptive approach has not well been proposed for different shapes and sizes of tumors. The purpose of this study was to propose an adaptive, efficient and safe algorithm to get high-quality treatment dose planning, which is presented for pancreatic cancer.

METHODS

An algorithm employs an optimized IPSA and an adaptive process for adjusting the weight of organs at risk (OAR) and tumor. The algorithm, which was combined with ant colony optimization, was further optimized to reduce the number of needles. It could meet the clinical dose objectives within the tumors, reduce the dose distribution within the OAR and minimize the number of needles. Ten clinical cases were chosen randomly from patients, previously successfully treated in clinic to test our method. The algorithm was validated against clinical cases, using clinically relevant dose parameters.

RESULTS

The results were compared with clinical results in ten cases, indicating that the dose distribution within the tumor meets the clinical dose objectives. The dose received by OAR had been greatly reduced, and the number of needles could be reduced by about 50%. It was a significant improvement over the clinical treatment planning.

CONCLUSIONS

In this paper, we have devised an algorithm to optimize the treatment planning in brachytherapy. The method in this paper could meet the clinical dose objectives and reduce the difficulty of operation. The results were clinically acceptable. This algorithm is also applicable to other cancers such as lung cancer.

Knowledge-based inverse treatment planning for low-dose-rate prostate brachytherapy

PURPOSE

Permanent low-dose-rate brachytherapy is a widely used treatment modality for managing prostate cancer. In such interventions, treatment planning can be a challenging task and requires experience and skills of the planner. We developed a novel knowledge-based (KB) optimization method based on previous treatment plans. The purpose of this method was to generate clinically acceptable plans that do not require extensive manual adjustments in clinical scenarios.

METHODS

Objective functions used in current inverse planning methods are preferably based on spatial invariant dose objectives rather than spatial dose distributions. Therefore, they are prone to return suboptimal plans resulting in time consuming plan adjustments. To overcome this limitation, a KB approach is introduced. The KB model uses the dose distributions of previous clinical plans projected onto a standardized geometry. From those standardized distributions a template plan is generated. The treatment plans were optimized with an in-house developed planning system by solving a constraint inverse optimization problem that mimics the projected template dose plan constraint to DVH metrics. The method is benchmarked under an IRB-approved retrospective study by comparing optimization time, dosimetric performance, and clinical acceptability against current clinical practice. The quality of the KB model is evaluated with a Turing test.

RESULTS

The KB model consists of five high-quality treatment plans. Those plans were selected by one of our experts and showed all desired dosimetric features. After generating the model treatment plans were created with one run of the optimizer for the remaining 20 patients. The optimization time including needle optimization ranged from 6 to 29 s. Based on a Wilcoxon signed rank test the new plans are dosimetrically equivalent to current clinical practice. The Turing test showed that the proposed method generates plans that are equivalent to current clinical practice and that the dose prediction drives the optimization to achieve high-quality treatment plans.

CONCLUSIONS

This study demonstrated that the proposed KB model was able to capture user-specific features in isodose lines which can be used to generate acceptable treatment plans with a single run of the optimization engine in under a minute. This could potentially reduce the time in the operating room and the time a patient is under anesthesia.

Machine learning and registration for automatic seed localization in 3D US images for prostate brachytherapy

PURPOSE

New radiation therapy protocols, in particular adaptive, focal or boost brachytherapy treatments, require determining precisely the position and orientation of the implanted radioactive seeds from real-time ultrasound (US) images. This is necessary to compare them to the planned one and to adjust automatically the dosimetric plan accordingly for next seeds implantations. The image modality, the small size of the seeds, and the artifacts they produce make it a very challenging problem. The objective of the presented work is to setup and to evaluate a robust and automatic method for seed localization in three-dimensional (3D) US images.

METHODS

The presented method is based on a prelocalization of the needles through which the seeds are injected in the prostate. This prelocalization allows focusing the search on a region of interest (ROI) around the needle tip. Seeds localization starts by binarizing the ROI and removing false positives using, respectively, a Bayesian classifier and a support vector machine (SVM). This is followed by a registration stage using first an iterative closest point (ICP) for localizing the connected set of seeds (named strand) inserted through a needle, and secondly refining each seed position using sum of squared differences (SSD) as a similarity criterion. ICP registers a geometric model of the strand to the candidate voxels while SSD compares an appearance model of a single seed to a subset of the image. The method was evaluated both for 3D images of an Agar-agar phantom and a dataset of clinical 3D images. It was tested on stranded and on loose seeds.

RESULTS

Results on phantom and clinical images were compared with a manual localization giving mean errors of 1.09 ± 0.61 mm on phantom image and 1.44 ± 0.45 mm on clinical images. On clinical images, the mean errors of individual seeds orientation was 4.33 ± 8 . 51 ∘ .

CONCLUSIONS

The proposed algorithm for radioactive seed localization is robust, tested on different US images, accurate, giving small mean error values, and returns the five cylindrical seeds degrees of freedom.

Hybrid optimization based on non-coplanar needles for brachytherapy dose planning

PURPOSE

An ideal dose distribution in a target is the ultimate goal of preoperative dose planning. Furthermore, avoiding vital organs or tissues such as blood vessels or bones during the puncture procedure is significant in low-dose-rate brachytherapy. The aim of this work is to develop a hybrid inverse optimization method based on non-coplanar needles to assist the physician during conformal dose planning, which cannot be properly achieved with a traditional coplanar template.

MATERIAL AND METHODS

The hybrid inverse optimization technique include two novel technologies: an inverse optimization algorithm and a dose volume histogram evaluation method. Brachytherapy treatment planning system was designed as an experimental platform. Left lung adenocarcinoma case was used to test the performance of the method in non-coplanar and coplanar needles, and malignant tumor of spine case was involved to test the practical application of this technique. In addition, the optimization time of every test was also recorded.

RESULTS

The proposed method can achieve an ideal dose distribution, avoiding vital organs (bones). In the first experiment, 13 non-coplanar needles and 24 seeds were used to get an ideal dose distribution to cover the target, whereas 11 coplanar needles and 23 seeds were used to cover the same target. In the second experiment, the new method used 22 non-coplanar needles and 65 seeds to cover the target, while 63 seeds and 22 needles were used in the actual operation. In addition, the computation time of the hybrid inverse optimization method was 20.5 seconds in the tumor of 94.67 cm3 by using 22 needles, which was fast enough for clinical application.

CONCLUSIONS

The hybrid inverse optimization method achieved high conformity in the clinical practice. The non-coplanar needle can help to achieve a better dose distribution than the coplanar needle.