Background The number of patients undergoing proton therapy has increased in recent years. Current treatment planning systems (TPS) calculate dose maps using three-dimensional (3D) maps of relative stopping power (RSP) and mass density. The patient-specific maps of RSP and mass density were obtained by translating the CT number (HU) acquired using single-energy computed tomography (SECT) with appropriate conversions and coefficients. The proton dose calculation uncertainty of this approach is 2.5%-3.5% plus 1 mm margin. SECT is the major clinical modality for proton therapy treatment planning. It would be intriguing to enhance proton dose calculation accuracy using a deep learning (DL) approach centered on SECT. Objectives The purpose of this work is to develop a deep learning method to generate mass density and relative stopping power (RSP) maps based on clinical single-energy CT (SECT) data for proton dose calculation in proton therapy treatment. Methods Artificial neural networks (ANN), fully convolutional neural networks (FCNN), and residual neural networks (ResNet) were used to learn the correlation between voxel-specific mass density, RSP, and SECT CT number (HU). A stoichiometric calibration method based on SECT data and an empirical model based on dual-energy CT (DECT) images were chosen as reference models to evaluate the performance of deep learning neural networks. SECT images of a CIRS 062M electron density phantom were used as the training dataset for deep learning models. CIRS anthropomorphic M701 and M702 phantoms were used to test the performance of deep learning models. Results For M701, the mean absolute percentage errors (MAPE) of the mass density map by FCNN are 0.39%, 0.92%, 0.68%, 0.92%, and 1.57% on the brain, spinal cord, soft tissue, bone, and lung, respectively, whereas with the SECT stoichiometric method, they are 0.99%, 2.34%, 1.87%, 2.90%, and 12.96%. For RSP maps, the MAPE of FCNN on M701 are 0.85%, 2.32%, 0.75%, 1.22%, and 1.25%, whereas with the SECT reference model, they are 0.95%, 2.61%, 2.08%, 7.74%, and 8.62%. Conclusion The results show that deep learning neural networks have the potential to generate accurate voxel-specific material property information, which can be used to improve the accuracy of proton dose calculation. Advances in knowledge Deep learning-based frameworks are proposed to estimate material mass density and RSP from SECT with improved accuracy compared with conventional methods.

Proton therapy requires accurate dose calculation for treatment planning to ensure the conformal doses are precisely delivered to the targets. The conversion of CT numbers to material properties is a significant source of uncertainty for dose calculation. The aim of this study is to develop a physics-informed deep learning (PIDL) framework to derive accurate mass density and relative stopping power maps from dual-energy computed tomography (DECT) images. The PIDL framework allows deep learning (DL) models to be trained with a physics loss function, which includes a physics model to constrain DL models. Five DL models were implemented including a fully connected neural network (FCNN), dual-FCNN (DFCNN), and three variants of residual networks (ResNet): ResNet-v1 (RN-v1), ResNet-v2 (RN-v2), and dual-ResNet-v2 (DRN-v2). An artificial neural network (ANN) and the five DL models trained with and without physics loss were explored to evaluate the PIDL framework. Two empirical DECT models were implemented to compare with the PIDL method. DL training data were from CIRS electron density phantom 062M (Computerized Imaging Reference Systems, Inc., Norfolk, VA). The performance of DL models was tested by CIRS adult male, adult female, and 5-year-old child anthropomorphic phantoms. For density map inference, the physics-informed RN-v2 was 3.3%, 2.9% and 1.9% more accurate than ANN for the adult male, adult female, and child phantoms. The physics-informed DRN-v2 was 0.7%, 0.6%, and 0.8% more accurate than DRN-v2 without physics training for the three phantoms, respectfully. The results indicated that physics-informed training could reduce uncertainty when ANN/DL models without physics training were insufficient to capture data structures or derived significant errors. DL models could also achieve better image noise control compared to the empirical DECT parametric mapping methods. The proposed PIDL framework can potentially improve proton range uncertainty by offering accurate material properties conversion from DECT.

Magnetic resonance imaging (MRI) has been widely used in combination with computed tomography (CT) radiation therapy because MRI improves the accuracy and reliability of target delineation due to its superior soft tissue contrast over CT. The MRI-only treatment process is currently an active field of research since it could eliminate systematic MR-CT co-registration errors, reduce medical cost, avoid diagnostic radiation exposure, and simplify clinical workflow. The purpose of this work is to validate the application of a deep learning-based method for abdominal synthetic CT (sCT) generation by image evaluation and dosimetric assessment in a commercial proton pencil beam treatment planning system (TPS). This study proposes to integrate dense block into a 3D cycle-consistent generative adversarial networks (cycle GAN) framework in an effort to effectively learn the nonlinear mapping between MRI and CT pairs. A cohort of 21 patients with co-registered CT and MR pairs were used to test the deep learning-based sCT image quality by leave-one-out cross validation. The CT image quality, dosimetric accuracy and the distal range fidelity were rigorously checked, using side-by-side comparison against the corresponding original CT images. The average mean absolute error (MAE) was 72.87±18.16 HU. The relative differences of the statistics of the PTV dose volume histogram (DVH) metrics between sCT and CT were generally less than 1%. Mean 3D gamma analysis passing rate of 1mm/1%, 2mm/2%, 3mm/3% criteria with 10% dose threshold were 90.76±5.94%, 96.98±2.93% and 99.37±0.99%, respectively. The median, mean and standard deviation of absolute maximum range differences were 0.170 cm, 0.186 cm and 0.155 cm. The image similarity, dosimetric and distal range agreement between sCT and original CT suggests the feasibility of further development of an MRI-only workflow for liver proton radiotherapy.

Breast cancer is the most prevalent cancer in women worldwide with a high mortality rate, and the identification of new biomarkers and targets for this disease is greatly needed. Here we present evidence that microtubule-associated protein (MAP) 7 domain-containing protein 3 (Mdp3) is highly expressed in clinical samples and cell lines of breast cancer. The expression of Mdp3 correlates with clinicopathological parameters indicating breast cancer malignancy. In addition, Mdp3 promotes breast cancer cell proliferation and motility in vitro and stimulates breast cancer growth and metastasis in mice. Mechanistic studies reveal that ?-tubulin interacts with and recruits Mdp3 to the centrosome and that the centrosomal localization of Mdp3 is required for its activity to promote breast cancer cell proliferation and motility. These findings suggest a critical role for Mdp3 in the growth and metastasis of breast cancer and may have important implications for the management of this disease.

Noscapine is an orally administrable drug used worldwide for cough suppression and has recently been demonstrated to disrupt microtubule dynamics and possess anticancer activity. However, the molecular mechanisms regulating noscapine activity remain poorly defined. Here we demonstrate that cylindromatosis (CYLD), a microtubule-associated tumor suppressor protein, modulates the activity of noscapine both in cell lines and in primary cells of acute lymphoblastic leukemia (ALL). Flow cytometry and immunofluorescence microscopy reveal that CYLD increases the ability of noscapine to induce mitotic arrest and apoptosis. Examination of cellular microtubules as well as in vitro assembled microtubules shows that CYLD enhances the effect of noscapine on microtubule polymerization. Microtubule cosedimentation and fluorescence titration assays further reveal that CYLD interacts with microtubule outer surface and promotes noscapine binding to microtubules. These findings thus demonstrate CYLD as a critical regulator of noscapine activity and have important implications for ALL treatment.

In the initially published version of this article, the image of the siMdp3#2 group (Hs578T cells, 24 hr) in Figure 3B is wrong. The correct Figure 3B is as follows: (Figure Presented) The correction made in this erratum does not affect the original conclusions. The authors apologize for any inconvenience or misunderstanding that this error may have caused.

Purpose: Elekta XVI 5.0 allows for four-dimensional cone beam computed tomography (4D CBCT) image acquisition during treatment delivery to monitor intrafraction motion. These images can have poorer image quality due to undersampling of kV projections and treatment beam MV scatter effects. We determine if a universal intrafraction preset can be used for stereotactic body radiotherapy (SBRT) lung patients and validate the accuracy of target motion characterized by XVI intrafraction 4D CBCT. Methods: The most critical parameter within the intrafraction preset is the nominal AcquisitionInterval, which controls kV imaging acquisition frequency. An optimal value was determined by maximizing the kV frame number acquired up to 1000 frames, typical of pretreatment 4D CBCT. CIRS motion phantom intrafraction phase images for 16 SBRT beams were obtained. Mean target position, time-weighted standard deviation, and amplitude for these images as well as target motion for three SBRT lung patients were compared to respective pretreatment 4D CBCTs. Evaluation of intrafraction 4D CBCT reconstruction revealed inclusion of MV only images acquired to remove MV scatter effects. A workaround to remove these images was developed. Results: AcquisitionInterval of 0.1°/frame was optimal. The number of kV frames acquired was 567–1116 and showed strong linear correlation with beam monitor unit (MUs). Phantom target motion accuracy was excellent with average differences in target position, standard deviation and amplitude range of ≤0.5 mm. Target tracking for SBRT patients also showed good agreement. Evaluation of phase sorting wave forms showed that inclusion of MV only images significantly impacts intrafraction image reconstruction for patients and use of workaround is necessary. Conclusions: A universal intrafraction imaging preset can be used safely for SBRT lung patients. The number of kV projections with MV delivery parameters varies; however images with fewer kV projections still provided accurate target position information. Impact of the reconstruction workaround was significant and is mandated for all 4D CBCT intrafraction imaging performed at our institution.

Purpose: To develop a patients-based statistical model of dose distribution among patients with nasopharyngeal cancer (NPC). Methods and Materials: The dose distributions of 75 patients with NPC were acquired and preprocessed to generate a dose-template library. Subsequently, the dominant modes of dose distribution were extracted using principal component analysis (PCA). Leave-one-out cross-validation (LOOCV) was performed for evaluation. Residual reconstruction errors between the doses reconstructed using different dominating eigenvectors and the planned dose distribution were calculated to investigate the convergence characteristics. Three-dimensional Gamma analysis was performed to investigate the accuracy of dose reconstruction. Results: The first 29 components contained 90% of the variance in dose distribution, and 45 components accounted for more than 95% of the variance on average. The residual error of the LOOCV model for the cumulative sum of components over all patients decreased from 8.16 to 4.79 Gy when 1 to 74 components were included in the LOOCV model. The 3-dimensional Gamma analysis results implied that the PCA model was capable of dose distribution reconstruction, and the accuracy was especially satisfactory in the high-dose area. Conclusions: A PCA-based model of dose distribution variations in patients with NPC was developed, and its accuracy was determined. This model could serve as a predictor of 3-dimensional dose distribution.

Purpose: While intensity modulated proton therapy can deliver simultaneous integrated boost (SIB) to the dominant intraprostatic lesion (DIL) with high precision, it is sensitive to anatomic changes. We investigated the dosimetric effects from these changes based on pretreatment cone-beam computed tomographic (CBCT) images and identified the most important factors using a multilayer perceptron neural network (MLPNN). Methods and Materials: DILs were contoured based on coregistered multiparametric magnetic resonance images for 25 previously treated prostate cancer patients. SIB plans were created with (1) prostate clinical target volume − V70 Gy = 98%; (2) DIL − V98 Gy > 95%; and (3) all organs at risk (OARs)"?> within clinical constraints. SIB plans were applied to daily CBCT-based deformed planning computed tomography (CT)"?>. DIL − V98 Gy, bladder/rectum maximum dose (Dmax) and volume changes, femur shifts, and the distance from DIL to organs at riskOARs"?> in both planning computed tomogramsCT"?> and CBCT were calculated. Wilcoxon signed-ranks tests were used to compare the changes. MLPNNs were used to model the change in ΔDIL − V98 Gy > 10% and bladder/rectum Dmax > 80 Gy, and the relative importance factors for the model were provided. The performances of the models were evaluated with receiver operating characteristic curves. Results: Comparing initial plan to the average from evaluation plans, respectively, DIL − V98 Gy was 89.3% ± 19.9% versus 86.2% ± 21.3% (P =.151); bladder Dmax 71.9 ± 0.6 Gy versus 74.5 ± 2.9 Gy (P <.001); and rectum Dmax 70.1 ± 2.4 Gy versus 74.9 ± 9.1Gy (P =.007). Bladder and rectal volumes were 99.6% ± 39.5% and 112.8% ± 27.2%, respectively, of their initial volume. The femur shift was 3.16 ± 2.52 mm. In the modeling of ΔDIL V98 Gy > 10%, DIL to rectum distance changes, DIL to bladder distance changes, and rectum volume changes ratio are the 3 most important factors. The areas under the receiver operating characteristic curves were 0.89, 1.00, and 0.99 for the modeling of ΔDIL − V98 Gy > 10%, and bladder and rectum Dmax > 80 Gy, respectively. Conclusions: Dosimetric changes in DIL SIB with intensity modulated proton therapy can be modeled and classified based on anatomic changes on pretreatment images by an MLPNN.

Purpose: Conventional iterative low-dose CBCT reconstruction techniques are slow and tend to over-smooth edges through uniform weighting of the image penalty gradient. In this study, we present a non-iterative analytical low-dose CBCT reconstruction technique by restoring the noisy low-dose CBCT projection with the non-local total variation (NLTV) method. Methods: We modeled the low-dose CBCT reconstruction as recovering high quality, high-dose CBCT x-ray projections (100 kVp, 1.6 mAs) from low-dose, noisy CBCT x-ray projections (100 kVp, 0.1 mAs). The restoration of CBCT projections was performed using the NLTV regularization method. In NLTV, the x-ray image is optimized by minimizing an energy function that penalizes gray-level difference between pair of pixels between noisy x-ray projection and denoising x-ray projection. After the noisy projection is restored by NLTV regularization, the standard FDK method was applied to generate the final reconstruction output. Results: Significant noise reduction was achieved comparing to original, noisy inputs while maintaining the image quality comparable to the high-dose CBCT projections. The experimental validations show the proposed NLTV algorithm can robustly restore the noise level of x-ray projection images while significantly improving the overall image quality. The improvement in normalized mean square error (NMSE) and peak signal-to-noise ratio (PSNR) measured from the non-local total variation-gradient projection (NLTV-GPSR) algorithm is noticeable compared to that of uncorrected low-dose CBCT images. Moreover, the difference of CNRs from the gains from the proposed algorithm is noticeable and comparable to high-dose CBCT. Conclusion: The proposed method successfully restores noise degraded, low-dose CBCT projections to high-dose projection quality. Such an outcome is a considerable improvement to the reconstruction result compared to the FDK-based method. In addition, a significant reduction in reconstruction time makes the proposed algorithm more attractive. This demonstrates the potential use of the proposed algorithm for clinical practice in radiotherapy.