Purpose The purpose of this study is to investigate the effect different magnetic resonance (MR) sequences on accuracy deep learning‐based synthetic computed tomography (sCT) generation in complex head and neck region. Methods Four MR images (T1, T2, T1C, T1DixonC‐water) were collected from 45 patients with nasopharyngeal carcinoma. Seven conditional generative adversarial network (cGAN) models trained (single channel) combinations (multi‐channel) as inputs. To further verify cGAN...

Abstract Background At present, the implementation of intensity-modulated radiation therapy (IMRT) treatment planning for geometrically complex nasopharyngeal carcinoma (NPC) through manual trial-and-error fashion presents challenges to improvement efficiency and obtaining high-consistency plan quality. This paper aims propose an automatic IMRT generation method fluence prediction further fine-tuning patients with NPC evaluates Methods A total 38 treated nine-beam were enrolled in this study...

To propose a new method for optimizing radiotherapy planning lung cancer by incorporating prognostic models that take into account individual patient information and assess the feasibility of treatment optimization directly guided minimizing predicted risk. A mixed fluence map objective was constructed, outcome-based physical dose constraints. The function constructed as an equally weighted summation prediction local control failure, radiation-induced cardiac toxicity, radiation pneumonitis...

Accurate localization of lung tumor in real time based on a single X-ray projection is great interest to the tumor-tracking radiotherapy but very challenging. In this paper, convolutional neural network (CNN)-based method was proposed address problem with aid principal component analysis-based motion modeling. A CNN regression model trained before treatment recover ill-conditioned nonlinear mapping from motion. Novel intensity correction and data augmentation techniques were adopted improve...

Abstract Objective . To present a transformer-based UNet model (TransDose) for fast and accurate dose calculation magnetic resonance-linear accelerators (MR-LINACs). Approach A 2D fluence map from each beam was first projected into 3D volume then fed the TransDose together with patient density output predicted dose. The proposed combined residual transformer encoder, where convolutional layers extracted volumetric spatial features, encoder processed long-range dependencies in global space....

Automatic multi-criteria optimization is necessary for intensity modulated radiation therapy (IMRT) because of low planning efficiency and large plan quality uncertainty in current clinical practice. Most studies focused on imitating dosimetrists' procedures to automate this process ignored the fact that organ-based objective functions typically used commercial treatment systems (such as dose-volume function) usually lead sub-optimal plans. To guarantee optimum results process, we...

To extend and validate the accuracy efficiency of a graphics processing unit (GPU)-Monte Carlo dose engine for Elekta Unity 1.5 T Magnetic Resonance-Linear Accelerator (MR-LINAC) online independent verification.Electron/positron propagation physics in uniform magnetic field was implemented previously developed GPU-Monte engine-gDPM. The calculation first evaluated heterogeneous phantom with EGSnrc. then commissioned to machine virtual two photon-source model compared Monaco treatment...

In this study, we assess the dosimetric qualities and usability of planning for 1.5 T MR-Linac based intensity modulated radiotherapy (MRL-IMRT) various clinical sites in comparison with IMRT plans using a conventional linac. total 30 patients disease brain, esophagus, lung, rectum vertebra were re-planned retrospectively simulated MRL-IMRT Elekta Unity dedicated treatment system (TPS) Monaco (v5.40.01). Currently, step-and-shoot (ss) is only delivery technique available on Unity. All...

To verify the feasibility of our in-house developed multisequence magnetic resonance (MR)-generated synthetic computed tomography (sCT) for accurate dose calculation and fractional positioning head neck MR-only radiation therapy (RT).Forty-five patients with nasopharyngeal carcinoma were retrospectively studied. By applying previously network, a patient's sCT can rapidly be generated respect to feeding sole T1 image, T1C T1DixonC T2 their combination (five pipelines in total). A k(5)-fold...

In this paper, methods of measuring the softness open-cell polyurethane foams in terms their Young's modulus using indentation are investigated and shown to be agreement with values determined by normal compression tests. The comparison involved use a formula relating for elastomers axial forces on cylindrical probe. This had been developed cartilage verified other biological tissues could not automatically assumed valid an structure. An method was then used characterize soft female human...

Liver cancer is one of the most common malignant tumors worldwide. In order to enable noninvasive detection small liver in mice, we present a parallel iterative shrinkage (PIS) algorithm for dual-modality tomography. It takes advantage microcomputed tomography and multiview bioluminescence imaging, providing anatomical structure intensity information reconstruct size location tumors. By incorporating prior knowledge signal sparsity, associate some mathematical strategies including specific...

Abstract Background Current intensity-modulated radiation therapy (IMRT) treatment planning is still a manual and time/resource consuming task, knowledge-based methods with appropriate predictions have been shown to enhance the plan quality consistency improve efficiency. This study aims develop novel prediction framework simultaneously predict dose distribution fluence for nasopharyngeal carcinoma treated IMRT, predicted information can be used as objectives initial solution an automatic...

Abstract This article reports on a numerical investigation of the transient heat and moisture transfer behavior in clothing insulation made fibrous battings covering fabrics. The finite-volume method (FVM) is applied mathematical formation calculation. provides more accurate representation element properties their grid locations. Combined with upstream scheme dealing bulk flow considering effect condensate permeability batting, present model improves accuracy solution. calculated results...

To investigate the in-air out-of-field electron streaming effect (ESE) for esophageal cancer radiotherapy in presence of 1.5 T perpendicular magnetic field. Ten patients treated with conventional Linac were retrospectively enrolled into a cohort this study, prescription 4,400 cGy/20 fx. All cases received IMRT replanning using Elekta Unity MR-Linac specified Monaco system, denoted as primary plan. visualize dose outside body an auxiliary structure was created by extending external structure....

Abstract Structural defects are inevitably produced by residual stress in the 3D printing process, which reduce structural-functional properties. For a typical lattice structure, new sliding window approach to intelligently identify defects, based on difference principle, inspection process was proposed. Industrial computed tomography (CT) used for image information acquisition. The grayscale standard deviation local range of CT slice is calculated characterize variation defect location. On...

Abstract Objective. To develop a novel deep learning-based 3D in vivo dose reconstruction framework with an electronic portal imaging device (EPID) for magnetic resonance-linear accelerators (MR-LINACs). Approach. The proposed method directly back-projected 2D into patient coarse dose, which bypassed the complicated patient-to-EPID scatter estimation step used conventional methods. A pre-trained convolutional neural network (CNN) was then employed to map final accurate dose. electron return...

Abstract Objective. To develop and validate a graphics processing unit (GPU) based superposition Monte Carlo (SMC) code for efficient accurate dose calculation in magnetic fields. Approach. A series of mono-energy photons ranging from 25 keV to 7.7 MeV were simulated with EGSnrc water phantom generate particle tracks database. SMC physics was extended charged transport fields subsequently programmed on GPU as gSMC. Optimized simulation scheme designed by combining variance reduction...

In current knowledge-based treatment planning for intensity-modulated radiation therapy (IMRT), 3-dimensional dosimetric goals are predicted to provide abundant and appropriate starting points optimization, but considering there're uncertainties with those dose distribution predictions, how tailor the objective function constraints accordingly is quite a concern. Here, we represent novel automatic optimization method that capable of making most prediction meanwhile achieving its optimum as...

Purpose CyberKnife system is initially equipped with fixed circular cones for stereotactic radiosurgery. Two dose calculation algorithms, Ray‐Tracing and Monte Carlo, are available in the supplied treatment planning system. A multileaf collimator was recently introduced latest generation of system, capable arbitrarily shaped field. The purpose this study to develop a model based algorithm better handle lateral scatter an irregularly small field Methods pencil beam widely used linac modified....