Lack of a reference dose distribution is one of the challenges in the treatment planning used in volumetric modulated arc therapy because numerous manual processes result from variations in the location and size of a tumor in different cases. In this study, a predicted dose distribution was generated using two independent methods. Treatment planning using the predicted distribution was compared with the clinical value, and its efficacy was evaluated.
 
  Computed tomography scans of 81 patients with oropharynx or hypopharynx tumors were acquired retrospectively. The predicted dose distributions were determined using a modified filtered back projection (mFBP) and a hierarchically densely connected U-net (HD-Unet). Optimization parameters were extracted from the predicted distribution, and the optimized dose distribution was obtained using a commercial treatment planning system.
 
  In the test data from ten patients, significant differences between the mFBP and clinical plan were observed for the maximum dose of the brain stem, spinal cord, and mean dose of the larynx. A significant difference between the dose distributions from the HD-Unet dose and the clinical plan was observed for the mean dose of the left parotid gland. In both cases, the equivalent coverage and flatness of the clinical plan were observed for the tumor target.
 
  The predicted dose distribution was generated using two approaches. In the case of the mFBP approach, no prior learning, such as deep learning, is required; therefore, the accuracy and efficiency of treatment planning will be improved even for sites where sufficient training data are unavailable.
 The predicted dose distribution was generated using two approaches. In the case of the mFBP approach, no prior learning, such as deep learning, is required; therefore, the accuracy and efficiency of treatment planning will be improved even for sites where sufficient training data are unavailable.
  To commission and assess the performance of AlignRT InBore™, a Halcyon™ and Ethos™-dedicated Surface Guided Radiation Therapy (SGRT) platform which combines ceiling-mounted cameras for patient setup and bore-mounted cameras for in-bore tracking.
 
  To check the potential impact of InBore™ cameras on dose delivery, 16 SRS, H&N, breast and pelvis patients' quality assurance (QA) treatment plans were measured with/without AlignRT InBore™ and using ArcCHECK® and SRS MapCHECK®. Impact on image quality was determined using Catphan® 540 phantom and considering all available MV and CBCT protocols (head, breast, chest and pelvis). The stability, accuracy and overall performance of AlignRT InBore™ was assessed using an MV Cube and anthropomorphic phantoms.
 
  Comparison of 2D dose distributions with/without AlignRT InBore™ showed no impact on treatment delivery for all 16 QA checks (p-value>0.25).  https://www.selleckchem.com/HIF.html  2D and CBCT images showed no artefacts or change in the contrast-to-noise ratio, resolution and noise values measured with Catphan® 540. Anti-collision sensors were unaffected by the bore-mounted cameras. Additionally, AlignRT InBore™ cameras allowed for motion detection with sub-0.5mm accuracy and sub-0.4mm stability with surface coverage of >50×60×35 cc. Accurate transition (sub-0.3mm) from virtual to treatment isocentres was achieved. Finally, Halcyon™ rotations during CBCT and beam delivery resulted in limited camera vibrations with translation uncertainty <0.5mm in left-right and anterior-posterior directions and <0.1mm in head-feet direction.
 
  AlignRT InBore™ provides SGRT setup and intrafraction monitoring capabilities with a performance comparable to standard SGRT solutions while having no adverse effect on Halcyon™.
 AlignRT InBore™ provides SGRT setup and intrafraction monitoring capabilities with a performance comparable to standard SGRT solutions while having no adverse effect on Halcyon™.
  Our markerless tumor tracking algorithm requires 4DCT data to train models. 4DCT cannot be used for markerless tracking for respiratory-gated treatment due to inaccuracies and a high radiation dose. We developed a deep neural network (DNN) to generate 4DCT from 3DCT data.
 
  We used 2420 thoracic 4DCT datasets from 436 patients to train a DNN, designed to export 9 deformation vector fields (each field representing one-ninth of the respiratory cycle) from each CT dataset based on a 3D convolutional autoencoder with shortcut connections using deformable image registration. Then 3DCT data at exhale were transformed using the predicted deformation vector fields to obtain simulated 4DCT data. We compared markerless tracking accuracy between original and simulated 4DCT datasets for 20 patients. Our tracking algorithm used a machine learning approach with patient-specific model parameters. For the training stage, a pair of digitally reconstructed radiography images was generated using 4DCT for each patient. For the prediction stage, the tracking algorithm calculated tumor position using incoming fluoroscopic image data.
 
  Diaphragmatic displacement averaged over 40 cases for the original 4DCT were slightly higher (<1.3mm) than those for the simulated 4DCT. Tracking positional errors (95th percentile of the absolute value of displacement, "simulated 4DCT" minus "original 4DCT") averaged over the 20 cases were 0.56mm, 0.65mm, and 0.96mm in theX,Y and Z directions, respectively.
 
  We developed a DNN to generate simulated 4DCT data that are useful for markerless tumor tracking when original 4DCT is not available. Using this DNN would accelerate markerless tumor tracking and increase treatment accuracy in thoracoabdominal treatment.
 We developed a DNN to generate simulated 4DCT data that are useful for markerless tumor tracking when original 4DCT is not available. Using this DNN would accelerate markerless tumor tracking and increase treatment accuracy in thoracoabdominal treatment.This study aimed to propose a new type of micro-pressure swirl reactor (MPSR) to treat urban sewage. The MPSR could form a stable swirl in the reactor, and realized the coexistence of anaerobic, anoxic, and aerobic zones in a single aeration tank. The pilot study showed that MPSR achieved high removal efficient of SS, COD, NH4+-N, TN, TP under the conditions of drastic fluctuation in influent quality and temperature, and the average removal rate were 88.58%, 93.32%, 94.47%, 73.19%, 96.16%. The relative high abundance of Thermomonas, Thaurea, and Dechloromonas, etc, guaranteed the denitrification efficiency of the MPSR, and Dechloromonas was the main phosphorus removal bacteria in the system. The study confirmed the rationality of the structural design of the MPSR, and it was excellent in sewage treatment and stability.