Search

Typically, the current dose prediction models are limited to small amounts of data and require re-training for a specific site, often leading to suboptimal performance. We propose a site-agnostic, 3D dose distribution prediction model using deep learning that can leverage data from any treatment site, thus increasing the total data available to train the model. Applying our proposed model to a new target treatment site requires only a brief fine-tuning of the model to the new data and involves no modifications to the model input channels or its parameters. Thus, it can be efficiently adapted to a different treatment site, even with a small training dataset.

Volumetric modulated arc therapy planning is a challenging problem in high-dimensional, non-convex optimization. Traditionally, heuristics such as fluence-map-optimization-informed segment initialization use locally optimal solutions to begin the search of the full arc therapy plan space from a reasonable starting point. These routines facilitate arc therapy optimization such that clinically satisfactory radiation treatment plans can be created in about 10 minutes. However, current optimization algorithms favor solutions near their initialization point and are slower than necessary due to plan overparameterization. In this work, arc therapy overparameterization is addressed by reducing the effective dimension of treatment plans with unsupervised deep learning. An optimization engine is then built based on low-dimensional arc representations which facilitates faster planning times.

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). 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 auto-contouring task on re-planning 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. In the re-planning CT auto-contouring 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.

Since the outbreak of the COVID-19 pandemic, worldwide research efforts have focused on using artificial intelligence (AI) technologies on various medical data of COVID-19-positive patients in order to identify or classify various aspects of the disease, with promising reported results. However, concerns have been raised over their generalizability, given the heterogeneous factors in training datasets. This study aims to examine the severity of this problem by evaluating deep learning (DL) classification models trained to identify COVID-19-positive patients on 3D computed tomography (CT) datasets from different countries. We collected one dataset at UT Southwestern (UTSW), and three external datasets from different countries: CC-CCII Dataset (China), COVID-CTset (Iran), and MosMedData (Russia). We divided the data into 2 classes: COVID-19-positive and COVID-19-negative patients. We trained nine identical DL-based classification models by using combinations of the datasets with a 72% train, 8% validation, and 20% test data split. The models trained on a single dataset achieved accuracy/area under the receiver operating characteristics curve (AUC) values of 0.87/0.826 (UTSW), 0.97/0.988 (CC-CCCI), and 0.86/0.873 (COVID-CTset) when evaluated on their own dataset. The models trained on multiple datasets and evaluated on a test set from one of the datasets used for training performed better. However, the performance dropped close to an AUC of 0.5 (random guess) for all models when evaluated on a different dataset outside of its training datasets. Including the MosMedData, which only contained positive labels, into the training did not necessarily help the performance on the other datasets. Multiple factors likely contribute to these results, such as patient demographics and differences in image acquisition or reconstruction, causing a data shift among different study cohorts.

Automatic segmentation of medical images with DL algorithms has proven to be highly successful. With most of these algorithms, inter-observer variation is an acknowledged problem, leading to sub-optimal results. This problem is even more significant in post-operative clinical target volume (post-op CTV) segmentation due to the absence of macroscopic visual tumor in the image. This study, using post-op CTV segmentation as the test bed, tries to determine if physician styles are consistent and learnable, if there is an impact of physician styles on treatment outcome and toxicity; and how to explicitly deal with physician styles in DL algorithms to facilitate its clinical acceptance. A classifier is trained to identify which physician has contoured the CTV from just the contour and corresponding CT scan, to determine if physician styles are consistent and learnable. Next, we evaluate if adapting automatic segmentation to physician styles would be clinically feasible based on a lack of difference between outcomes. For modeling different physician styles of CTV segmentation, a concept called physician style-aware (PSA) segmentation is proposed which is an encoder-multidecoder network trained with perceptual loss. With the proposed physician style-aware network (PSA-Net), Dice similarity coefficient (DSC) accuracy increases on an average of 3.4% for all physicians from a general model that is not style adapted. We show that stylistic contouring variations also exist between institutions that follow the same segmentation guidelines and show the effectiveness of the proposed method in adapting to new institutional styles. We observed an accuracy improvement of 5% in terms of DSC when adapting to the style of a separate institution.

Radiotherapy, due to its technology-intensive nature and reliance on digital data and human-machine interactions, is particularly suited to benefit from artificial intelligence (AI) to improve the accuracy and efficiency of its clinical workflow. Recently, various artificial intelligence (AI) methods have been successfully developed to exploit the benefit of the inherent physical properties of particle therapy. Many reviews about AI applications in radiotherapy have already been published, but none were specifically dedicated to particle therapy. In this article, we present a comprehensive review of the recent published works on AI applications in particle therapy, which can be classified into particle therapy treatment planning, adaptive particle therapy, range and dose verification and other applications in particle therapy. Although promising results reported in these works demonstrate how AI-based methods can help exploit the intrinsic physic advantages of particle therapy, challenges remained to be address before AI applications in particle therapy enjoy widespread implementation in clinical practice.

Inter-observer variation is a significant problem in clinical target volume(CTV) segmentation in postoperative settings, where there is no gross tumor present. In this scenario, the CTV is not an anatomically established structure, but one determined by the physician based on the clinical guideline used, the preferred tradeoff between tumor control and toxicity, their experience and training background, and other factors. This results in high inter-observer variability between physicians. This variability has been considered an issue, but the absence of multiple physician CTV contours for each patient and the significant amount of time required for dose planning have made it impractical to study its dosimetric consequences. In this study, we analyze the impact that variations in physician style have on dose to organs-at-risk(OAR) by simulating the clinical workflow via deep learning. For a given patient previously treated by one physician, we use deep learning-based tools to simulate how other physicians would contour the CTV and how the corresponding dose distributions would look for this patient. To simulate multiple physician styles, we use a previously developed in-house CTV segmentation model that can produce physician style-aware segmentations. The corresponding dose distribution is predicted using another in-house deep learning tool, which, can predict dose within 3% of the prescription dose, on average, on the test data. For every test patient, four different physician style CTVs are considered, and four different dose distributions are analyzed. OAR dose metrics are compared, showing that even though physician style variations result in organs getting different doses, all the important dose metrics except Maximum Dose point are within the clinically acceptable limit.

Low Dose Computed Tomography (LDCT) is clinically desirable due to the reduced radiation to patients. However, the quality of LDCT images is often sub-optimal because of the inevitable strong quantum noise. Inspired by their unprecedent success in computer vision, deep learning (DL)-based techniques have been used for LDCT denoising. Despite the promising noise removal ability of DL models, people have observed that the resolution of the DL-denoised images is compromised, decreasing their clinical value. Aiming at relieving this problem, in this work, we developed a more effective denoiser by introducing a high-resolution network (HRNet). Since HRNet consists of multiple branches of subnetworks to extract multiscale features which are later fused together, the quality of the generated features can be substantially enhanced, leading to improved denoising performance. Experimental results demonstrated that the introduced HRNet-based denoiser outperforms the benchmarked UNet-based denoiser in terms of superior image resolution preservation ability while comparable, if not better, noise suppression ability. Quantitative metrics in terms of root-mean-squared-errors (RMSE)/structure similarity index (SSIM) showed that the HRNet-based denoiser can improve the values from 113.80/0.550 (LDCT) to 55.24/0.745 (HRNet), in comparison to 59.87/0.712 for the UNet-based denoiser.

The purpose of this study is to develop a deep learning based method that can automatically generate segmentations on cone-beam CT (CBCT) for head and neck online adaptive radiation therapy (ART), where expert-drawn contours in planning CT (pCT) can serve as prior knowledge. Due to lots of artifacts and truncations on CBCT, we propose to utilize a learning based deformable image registration method and contour propagation to get updated contours on CBCT. Our method takes CBCT and pCT as inputs, and output deformation vector field and synthetic CT (sCT) at the same time by jointly training a CycleGAN model and 5-cascaded Voxelmorph model together.The CycleGAN serves to generate sCT from CBCT, while the 5-cascaded Voxelmorph serves to warp pCT to sCT's anatommy. The segmentation results were compared to Elastix, Voxelmorph and 5-cascaded Voxelmorph on 18 structures including left brachial plexus, right brachial plexus, brainstem, oral cavity, middle pharyngeal constrictor, superior pharyngeal constrictor, inferior pharyngeal constrictor, esophagus, nodal gross tumor volume, larynx, mandible, left masseter, right masseter, left parotid gland, right parotid gland, left submandibular gland, right submandibular gland, and spinal cord. Results show that our proposed method can achieve average Dice similarity coefficients and 95% Hausdorff distance of 0.83 and 2.01mm. As compared to other methods, our method has shown better accuracy to Voxelmorph and 5-cascaded Voxelmorph, and comparable accuracy to Elastix but much higher efficiency. The proposed method can rapidly and simultaneously generate sCT with correct CT numbers and propagate contours from pCT to CBCT for online ART re-planning., Comment: 16 pages, 6 figures, 2 tables

Purpose: Radiation therapy treatment planning is a trial-and-error, often time-consuming process. An optimal dose distribution based on a specific anatomy can be predicted by pre-trained deep learning (DL) models. However, dose distributions are often optimized based on not only patient-specific anatomy but also physician preferred trade-offs between planning target volume (PTV) coverage and organ at risk (OAR) sparing. Therefore, it is desirable to allow physicians to fine-tune the dose distribution predicted based on patient anatomy. In this work, we developed a DL model to predict the individualized 3D dose distributions by using not only the anatomy but also the desired PTV/OAR trade-offs, as represented by a dose volume histogram (DVH), as inputs. Methods: The desired DVH, fine-tuned by physicians from the initially predicted DVH, is first projected onto the Pareto surface, then converted into a vector, and then concatenated with mask feature maps. The network output for training is the dose distribution corresponding to the Pareto optimal DVH. The training/validation datasets contain 77 prostate cancer patients, and the testing dataset has 20 patients. Results: The trained model can predict a 3D dose distribution that is approximately Pareto optimal. We calculated the difference between the predicted and the optimized dose distribution for the PTV and all OARs as a quantitative evaluation. The largest average error in mean dose was about 1.6% of the prescription dose, and the largest average error in the maximum dose was about 1.8%. Conclusions: In this feasibility study, we have developed a 3D U-Net model with the anatomy and desired DVH as inputs to predict an individualized 3D dose distribution. The predicted dose distributions can be used as references for dosimetrists and physicians to rapidly develop a clinically acceptable treatment plan.

Low dose computed tomography (LDCT) is desirable for both diagnostic imaging and image guided interventions. Denoisers are openly used to improve the quality of LDCT. Deep learning (DL)-based denoisers have shown state-of-the-art performance and are becoming one of the mainstream methods. However, there exists two challenges regarding the DL-based denoisers: 1) a trained model typically does not generate different image candidates with different noise-resolution tradeoffs which sometimes are needed for different clinical tasks; 2) the model generalizability might be an issue when the noise level in the testing images is different from that in the training dataset. To address these two challenges, in this work, we introduce a lightweight optimization process at the testing phase on top of any existing DL-based denoisers to generate multiple image candidates with different noise-resolution tradeoffs suitable for different clinical tasks in real-time. Consequently, our method allows the users to interact with the denoiser to efficiently review various image candidates and quickly pick up the desired one, and thereby was termed as deep interactive denoiser (DID). Experimental results demonstrated that DID can deliver multiple image candidates with different noise-resolution tradeoffs, and shows great generalizability regarding various network architectures, as well as training and testing datasets with various noise levels., Comment: under review

Monte Carlo (MC) simulation is considered the gold standard method for radiotherapy dose calculation. However, achieving high precision requires a large number of simulation histories, which is time consuming. The use of computer graphics processing units (GPUs) has greatly accelerated MC simulation and allows dose calculation within a few minutes for a typical radiotherapy treatment plan. However, some clinical applications demand real time efficiency for MC dose calculation. To tackle this problem, we have developed a real time, deep learning based dose denoiser that can be plugged into a current GPU based MC dose engine to enable real time MC dose calculation. We used two different acceleration strategies to achieve this goal: 1) we applied voxel unshuffle and voxel shuffle operators to decrease the input and output sizes without any information loss, and 2) we decoupled the 3D volumetric convolution into a 2D axial convolution and a 1D slice convolution. In addition, we used a weakly supervised learning framework to train the network, which greatly reduces the size of the required training dataset and thus enables fast fine tuning based adaptation of the trained model to different radiation beams. Experimental results show that the proposed denoiser can run in as little as 39 ms, which is around 11.6 times faster than the baseline model. As a result, the whole MC dose calculation pipeline can be finished within 0.15 seconds, including both GPU MC dose calculation and deep learning based denoising, achieving the real time efficiency needed for some radiotherapy applications, such as online adaptive radiotherapy., Comment: under review

Recently, artificial intelligence technologies and algorithms have become a major focus for advancements in treatment planning for radiation therapy. As these are starting to become incorporated into the clinical workflow, a major concern from clinicians is not whether the model is accurate, but whether the model can express to a human operator when it does not know if its answer is correct. We propose to use Monte Carlo dropout (MCDO) and the bootstrap aggregation (bagging) technique on deep learning models to produce uncertainty estimations for radiation therapy dose prediction. We show that both models are capable of generating a reasonable uncertainty map, and, with our proposed scaling technique, creating interpretable uncertainties and bounds on the prediction and any relevant metrics. Performance-wise, bagging provides statistically significant reduced loss value and errors in most of the metrics investigated in this study. The addition of bagging was able to further reduce errors by another 0.34% for Dmean and 0.19% for Dmax, on average, when compared to the baseline framework. Overall, the bagging framework provided significantly lower MAE of 2.62, as opposed to the baseline framework's MAE of 2.87. The usefulness of bagging, from solely a performance standpoint, does highly depend on the problem and the acceptable predictive error, and its high upfront computational cost during training should be factored in to deciding whether it is advantageous to use it. In terms of deployment with uncertainty estimations turned on, both frameworks offer the same performance time of about 12 seconds. As an ensemble-based metaheuristic, bagging can be used with existing machine learning architectures to improve stability and performance, and MCDO can be applied to any deep learning models that have dropout as part of their architecture.

This work aims to study the generalizability of a pre-developed deep learning (DL) dose prediction model for volumetric modulated arc therapy (VMAT) for prostate cancer and to adapt the model to three different internal treatment planning styles and one external institution planning style. We built the source model with planning data from 108 patients previously treated with VMAT for prostate cancer. For the transfer learning, we selected patient cases planned with three different styles from the same institution and one style from a different institution to adapt the source model to four target models. We compared the dose distributions predicted by the source model and the target models with the clinical dose predictions and quantified the improvement in the prediction quality for the target models over the source model using the Dice similarity coefficients (DSC) of 10% to 100% isodose volumes and the dose-volume-histogram (DVH) parameters of the planning target volume and the organs-at-risk. The source model accurately predicts dose distributions for plans generated in the same source style but performs sub-optimally for the three internal and one external target styles, with the mean DSC ranging between 0.81-0.94 and 0.82-0.91 for the internal and the external styles, respectively. With transfer learning, the target model predictions improved the mean DSC to 0.88-0.95 and 0.92-0.96 for the internal and the external styles, respectively. Target model predictions significantly improved the accuracy of the DVH parameter predictions to within 1.6%. We demonstrated model generalizability for DL-based dose prediction and the feasibility of using transfer learning to solve this problem. With 14-29 cases per style, we successfully adapted the source model into several different practice styles. This indicates a realistic way to widespread clinical implementation of DL-based dose prediction.

We propose to develop deep learning models that can predict Pareto optimal dose distributions by using any given set of beam angles, along with patient anatomy, as input to train the deep neural networks. We implement and compare two deep learning networks that predict with two different beam configuration modalities. We generated Pareto optimal plans for 70 patients with prostate cancer. We used fluence map optimization to generate 500 IMRT plans that sampled the Pareto surface for each patient, for a total of 35,000 plans. We studied and compared two different models, Model I and Model II. Model I directly uses beam angles as a second input to the network as a binary vector. Model II converts the beam angles into beam doses that are conformal to the PTV. Our deep learning models predicted voxel-level dose distributions that precisely matched the ground truth dose distributions. Quantitatively, Model I prediction error of 0.043 (confirmation), 0.043 (homogeneity), 0.327 (R50), 2.80% (D95), 3.90% (D98), 0.6% (D50), 1.10% (D2) was lower than that of Model II, which obtained 0.076 (confirmation), 0.058 (homogeneity), 0.626 (R50), 7.10% (D95), 6.50% (D98), 8.40% (D50), 6.30% (D2). Treatment planners who use our models will be able to use deep learning to control the tradeoffs between the PTV and OAR weights, as well as the beam number and configurations in real time. Our dose prediction methods provide a stepping stone to building automatic IMRT treatment planning., Comment: 12 figures

Despite the indispensable role of X-ray computed tomography (CT) in diagnostic medicine field, the associated ionizing radiation is still a major concern considering that it may cause genetic and cancerous diseases. Decreasing the exposure can reduce the dose and hence the radiation-related risk, but will also induce higher quantum noise. Supervised deep learning can be used to train a neural network to denoise the low-dose CT (LDCT). However, its success requires massive pixel-wise paired LDCT and normal-dose CT (NDCT) images, which are rarely available in real practice. To alleviate this problem, in this paper, a shift-invariant property based neural network was devised to learn the inherent pixel correlations and also the noise distribution by only using the LDCT images, shaping into our probabilistic self-learning framework. Experimental results demonstrated that the proposed method outperformed the competitors, producing an enhanced LDCT image that has similar image style as the routine NDCT which is highly-preferable in clinic practice.

In radiotherapy, a trade-off exists between computational workload/speed and dose calculation accuracy. Calculation methods like pencil-beam convolution can be much faster than Monte-Carlo methods, but less accurate. The dose difference, mostly caused by inhomogeneities and electronic disequilibrium, is highly correlated with the dose distribution and the underlying anatomical tissue density. We hypothesize that a conversion scheme can be established to boost low-accuracy doses to high-accuracy, using intensity information obtained from computed tomography (CT) images. A deep learning-driven framework was developed to test the hypothesis by converting between two commercially-available dose calculation methods: AAA (anisotropic-analytic-algorithm) and AXB (Acuros XB).A hierarchically-dense U-Net model was developed to boost the accuracy of AAA dose towards the AXB level. The network contained multiple layers of varying feature sizes to learn their dose differences, in relationship to CT, both locally and globally. AAA and AXB doses were calculated in pairs for 120 lung radiotherapy plans covering various treatment techniques, beam energies, tumor locations, and dose levels., Comment: Paper accepted

In post-operative radiotherapy for prostate cancer, the cancerous prostate gland has been surgically removed, so the clinical target volume (CTV) to be irradiated encompasses the microscopic spread of tumor cells, which cannot be visualized in typical clinical images such as 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, per clinical guidelines. Automating post-operative prostate CTV segmentation with traditional image segmentation methods has been a major challenge. Here, we propose a deep learning model to overcome this problem by segmenting nearby organs first, then using their relationship with the CTV to assist CTV segmentation. The model proposed is trained using labels clinically approved and used for patient treatment, which are subject to relatively large inter-physician variations due to the absence of a visual ground truth. The model achieves an average Dice similarity coefficient (DSC) of 0.87 on a holdout dataset of 50 patients, much better than established methods, such as atlas-based methods (DSC<0.7). The uncertainties associated with automatically segmented CTV contours are also estimated to help physicians inspect and revise the contours, especially in areas with large inter-physician variations. We also use a 4-point grading system to show that the clinical quality of the automatically segmented CTV contours is equal to that of approved clinical contours manually drawn by physicians.

Generalizability is a concern when applying a deep learning (DL) model trained on one dataset to other datasets. Training a universal model that works anywhere, anytime, for anybody is unrealistic. In this work, we demonstrate the generalizability problem, then explore potential solutions based on transfer learning (TL) by using the cone-beam computed tomography (CBCT) to computed tomography (CT) image conversion task as the testbed. Previous works have converted CBCT to CT-like images. However, all of those works studied only one or two anatomical sites and used images from the same vendor's scanners. Here, we investigated how a model trained for one machine and one anatomical site works on other machines and other sites. We trained a model on CBCT images acquired from one vendor's scanners for head and neck cancer patients and applied it to images from another vendor's scanners and for other disease sites. We found that generalizability could be a significant problem for this particular application when applying a trained DL model to datasets from another vendor's scanners. We then explored three practical solutions based on TL to solve this generalization problem: the target model, which is trained on a target domain from scratch; the combined model, which is trained on both source and target domain datasets from scratch; and the adapted model, which fine-tunes the trained source model to a target domain. We found that when there are sufficient data in the target domain, all three models can achieve good performance. When the target dataset is limited, the adapted model works the best, which indicates that using the fine-tuning strategy to adapt the trained model to an unseen target domain dataset is a viable and easy way to implement DL models in the clinic., Comment: 20 pages, 5 figures, 7 supplementary figures, 8 tables

Due to the large combinatorial problem, current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature, leading to suboptimal solutions. We propose a reinforcement learning strategy using Monte Carlo Tree Search capable of finding a superior beam orientation set and in less time than CG.We utilized a reinforcement learning structure involving a supervised learning network to guide Monte Carlo tree search (GTS) to explore the decision space of beam orientation selection problem. We have previously trained a deep neural network (DNN) that takes in the patient anatomy, organ weights, and current beams, and then approximates beam fitness values, indicating the next best beam to add. This DNN is used to probabilistically guide the traversal of the branches of the Monte Carlo decision tree to add a new beam to the plan. To test the feasibility of the algorithm, we solved for 5-beam plans, using 13 test prostate cancer patients, different from the 57 training and validation patients originally trained the DNN. To show the strength of GTS to other search methods, performances of three other search methods including a guided search, uniform tree search and random search algorithms are also provided. On average GTS outperforms all other methods, it find a solution better than CG in 237 seconds on average, compared to CG which takes 360 seconds, and outperforms all other methods in finding a solution with lower objective function value in less than 1000 seconds. Using our guided tree search (GTS) method we were able to maintain a similar planning target volume (PTV) coverage within 1% error, and reduce the organ at risk (OAR) mean dose for body, rectum, left and right femoral heads, but a slight increase of 1% in bladder mean dose.

Accurate dose calculation is vitally important for proton therapy. Pencil beam (PB) model-based dose calculation is fast but inaccurate due to the approximation when dealing with inhomogeneities. Monte Carlo (MC) dose calculation is the most accurate method, but it is time consuming. We hypothesize that deep learning methods can boost the accuracy of PB dose calculation to the level of MC. In this work, we developed a deep learning model that converts PB to MC doses for different tumor sites. The proposed model is based on our newly developed hierarchically densely connected U-Net (HD U-Net) network, and it uses the PB dose and patient CT image as inputs to generate the MC dose. We used 290 patients (90 with head and neck, 93 with liver, 75 with prostate, and 32 with lung cancer) to train, validate, and test the model. For each tumor site, we performed four numerical experiments to explore various combinations of training datasets. Training the model on data from all tumor sites together and using the dose distribution of each individual beam as input yielded the best performance for all four tumor sites. The average gamma index (1mm/1% criteria) between the converted dose and the MC dose was 92.8%, 92.7%, 89.7% and 99.6% for head and neck, liver, lung, and prostate test patients, respectively. The average time for dose conversion for a single field was less than 4 seconds. In conclusion, our deep learning-based approach can quickly boost the accuracy of proton PB dose distributions to that of MC dose distributions. The trained model can be readily adapted to new datasets for different tumor sites and from different hospitals through transfer learning. This model can be added as a plug-in to the clinical workflow of proton therapy treatment planning to improve the accuracy of proton dose calculation.

The automatic standardization of nomenclature for anatomical structures in radiotherapy (RT) clinical data is a critical prerequisite for data curation and data-driven research in the era of big data and artificial intelligence, but it is currently an unmet need. Existing methods either cannot handle cross-institutional datasets or suffer from heavy imbalance and poor-quality delineation in clinical RT datasets. To solve these problems, we propose an automated structure nomenclature standardization framework, 3D Non-local Network with Voting (3DNNV). This framework consists of an improved data processing strategy, namely, adaptive sampling and adaptive cropping (ASAC) with voting, and an optimized feature extraction module. The framework simulates clinicians' domain knowledge and recognition mechanisms to identify small-volume organs at risk (OARs) with heavily imbalanced data better than other methods. We used partial data from an open-source head-and-neck cancer dataset to train the model, then tested the model on three cross-institutional datasets to demonstrate its generalizability. 3DNNV outperformed the baseline model, achieving higher average true positive rates (TPR) overall categories on the three test datasets (+8.27%, +2.39%, and +5.53%, respectively). More importantly, the 3DNNV outperformed the baseline on the test dataset, 28.63% to 91.17%, in terms of F1 score for a small-volume OAR with only 9 training samples. The results show that 3DNNV can be applied to identify OARs, even error-prone ones. Furthermore, we discussed the limitations and applicability of the framework in practical scenarios. The framework we developed can assist in standardizing structure nomenclature to facilitate data-driven clinical research in cancer radiotherapy., Comment: 15 pages, 8 figures

Quantum walk is a key operation in quantum computing, simulation, communication and information. Here, we report for the first time the demonstration of quantum walks and localized quantum walks in a new type of optical fibers having a ring of cores constructed with both periodic and quasiperiodic Fibonacci sequences, respectively. Good agreement between theoretical and experimental results have been achieved. The new multicore ring fibers provide a new platform for experiments of quantum effects in low-loss optical fibers which is critical for scalability of real applications with large-size problems. Furthermore, our new quasiperiodic Fibonacci multicore ring fibers provide a new class of quasiperiodic photonics lattices possessing both on- and off-diagonal deterministic disorders for realizing localized quantum walks deterministically. The proposed Fibonacci fibers are simple and straightforward to fabricate and have a rich set of properties that are of potential use for quantum applications. Our simulation and experimental results show that, in contrast with randomly disordered structures, localized quantum walks in new proposed quasiperiodic photonics lattices are highly controllable due to the deterministic disordered nature of quasiperiodic systems.

We propose a novel domain specific loss, which is a differentiable loss function based on the dose volume histogram, and combine it with an adversarial loss for the training of deep neural networks to generate Pareto optimal dose distributions. The mean squared error (MSE) loss, dose volume histogram (DVH) loss, and adversarial (ADV) loss were used to train 4 instances of the neural network model: 1) MSE, 2) MSE+ADV, 3) MSE+DVH, and 4) MSE+DVH+ADV. 70 prostate patients were acquired, and the dose influence arrays were calculated for each patient. 1200 Pareto surface plans per patient were generated by pseudo-randomizing the tradeoff weights (84,000 plans total). We divided the data into 54 training, 6 validation, and 10 testing patients. Each model was trained for 100,000 iterations, with a batch size of 2. The prediction time of each model is 0.052 seconds. Quantitatively, the MSE+DVH+ADV model had the lowest prediction error of 0.038 (conformation), 0.026 (homogeneity), 0.298 (R50), 1.65% (D95), 2.14% (D98), 2.43% (D99). The MSE model had the worst prediction error of 0.134 (conformation), 0.041 (homogeneity), 0.520 (R50), 3.91% (D95), 4.33% (D98), 4.60% (D99). For both the mean dose PTV error and the max dose PTV, Body, Bladder and rectum error, the MSE+DVH+ADV outperformed all other models. All model's predictions have an average mean and max dose error less than 2.8% and 4.2%, respectively. Expert human domain specific knowledge can be the largest driver in the performance improvement, and adversarial learning can be used to further capture nuanced features. The real-time prediction capabilities allow for a physician to quickly navigate the tradeoff space, and produce a dose distribution as a tangible endpoint for the dosimetrist to use for planning. This can considerably reduce the treatment planning time, allowing for clinicians to focus their efforts on challenging cases.

Purpose: Various dose calculation algorithms are available for radiation therapy for cancer patients. However, these algorithms are faced with the tradeoff between efficiency and accuracy. The fast algorithms are generally less accurate, while the accurate dose engines are often time consuming. In this work, we try to resolve this dilemma by exploring deep learning (DL) for dose calculation. Methods: We developed a new radiotherapy dose calculation engine based on a modified Hierarchically Densely Connected U-net (HD U-net) model and tested its feasibility with prostate intensity-modulated radiation therapy (IMRT) cases. Mapping from an IMRT fluence map domain to a 3D dose domain requires a deep neural network of complicated architecture and a huge training dataset. To solve this problem, we first project the fluence maps to the dose domain using a modified ray-tracing algorithm, and then we use the HD U-net to map the ray-tracing dose distribution into an accurate dose distribution calculated using a collapsed cone convolution/superposition (CS) algorithm. Results: It takes about one second to compute a 3D dose distribution for a typical 7-field prostate IMRT plan, which can be further reduced to achieve real-time dose calculation by optimizing the network. For all eight testing patients, evaluation with Gamma Index and various clinical goals for IMRT optimization shows that the DL dose distributions are clinically identical to the CS dose distributions. Conclusions: We have shown the feasibility of using DL for calculating radiotherapy dose distribution with high accuracy and efficiency.

Radiotherapy treatment planning currently requires many trail-and-error iterations between the planner and treatment planning system, as well as between the planner and physician for discussion/consultation. The physician's preferences for a particular patient cannot be easily quantified and precisely conveyed to the planner. In this study we present a real-time volumetric Pareto surface dose generation deep learning neural network that can be used after segmentation by the physician, adding a tangible and quantifiable end-point to portray to the planner. From 70 prostate patients, we first generated 84,000 intensity modulated radiation therapy plans (1,200 plans per patient) sampling the Pareto surface, representing various tradeoffs between the planning target volume (PTV) and the organs-at-risk (OAR), including bladder, rectum, left femur, right femur, and body. We divided the data to 10 test patients and 60 training/validation patients. We then trained a hierarchically densely connected convolutional U-net (HD U-net), to take the PTV and avoidance map representing OARs masks and weights, and predict the optimized plan. The HD U-net is capable of accurately predicting the 3D Pareto optimal dose distributions, with average [mean, max] dose errors of [3.4%, 7.7%](PTV), [1.6%, 5.6%](bladder), [3.7%, 4.2%](rectum), [3.2%, 8.0%](left femur), [2.9%, 7.7%](right femur), and [0.04%, 5.4%](body) of the prescription dose. The PTV dose coverage prediction was also very similar, with errors of 1.3% (D98) and 2.0% (D99). Homogeneity was also similar, differing by 0.06 on average. The neural network can predict the dose within 1.7 seconds. Clinically, the optimization and dose calculation is much slower, taking 5-10 minutes., Comment: Accepted by the Medical Image Computing and Computer Assisted Intervention (MICCAI) Conference

We propose a fast beam orientation selection method, based on deep neural networks (DNN), capable of developing a plan comparable to those by the state-of-the-art column generation method. The novelty of Our model lies in its supervised learning structure, the DNN architecture, and ability to learn from anatomical features to predict dosimetrically suitable beam orientations without using the dosimetric information from the candidate beams, a time consuming and computationally expensive process. This may save hours of computation. A supervised DNN is trained to mimic the column generation algorithm, which iteratively chooses beam orientations by calculating beam fitness values based on the KKT optimality conditions. The dataset contains 70 prostate cancer patients. The DNN trained over 400 epochs, each with 2500 steps, using the Adam optimizer and a 6-fold cross-validation technique. The average and standard deviation of training, validation, and testing loss functions among the 6-folds were at most 1.44%. The differences in the dose coverage of PTV between plans generated by column generation and by DNN were 0.2%. The average dose differences received by organs at risk were between 1 and 6 percent: bladder had the smallest average difference, then rectum, left and right femoral heads. The dose received by body had an average difference of 0.1%. In the training phase of the proposed method, the model learns the suitable beam orientations based on the anatomical features of patients and omits time intensive calculations of dose influence matrices for all possible candidate beams. Solving the Fluence Map Optimization to get the final treatment plan requires calculating dose influence matrices only for the selected beams. The proposed DNN is a fast beam orientation selection method based that selects beam orientations in seconds and is therefore suitable for clinical routines., Comment: 28 pages, 9 figures

Purpose: This study assessed the dosimetric accuracy of synthetic CT images generated from magnetic resonance imaging (MRI) data for focal brain radiation therapy, using a deep learning approach. Material and Methods: We conducted a study in 77 patients with brain tumors who had undergone both MRI and computed tomography (CT) imaging as part of their simulation for external beam treatment planning. We designed a generative adversarial network (GAN) to generate synthetic CT images from MRI images. We used Mutual Information (MI) as the loss function in the generator to overcome the misalignment between MRI and CT images (unregistered data). The model was trained using all MRI slices with corresponding CT slices from each training subject s MRI/CT pair. Results: The proposed GAN method produced an average mean absolute error (MAE) of 47.2 +- 11.0 HU over 5-fold cross validation. The overall mean Dice similarity coefficient between CT and synthetic CT images was 80% +- 6% in bone for all test data. Though training a GAN model may take several hours, the model only needs to be trained once. Generating a complete synthetic CT volume for each new patient MRI volume using a trained GAN model took only one second. Conclusions: The GAN model we developed produced highly accurate synthetic CT images from conventional, single-sequence MRI images in seconds. Our proposed method has strong potential to perform well in a clinical workflow for MRI-only brain treatment planning.