Abstract. A database of 15,617 point measurements of dimethylsulfide (DMS) in surface waters along with lesser amounts of data for aqueous and particulate dirhethylsulfoniopropionate concentration, chlorophyll concentration, sea surface salinity and temperature, and wind speed has been assembled. The database was processed to create a series of climatological annual and monthly 1øxl ø latitude-longitude squares of data. The results were compared to published fields of geophysical and biological parameters. No significant correlation was found between DMS and these parameters, and no simple algorithm could be found to create monthly fields of sea surface DMS concentration based on these parameters. Instead, an annual map of sea surface DMS was produced using an algorithm similar to that employed by Conkright et al. [1994]. In this approach, a first-guess field of DMS sea surface concentration measurements is created and then a correction to this field is generated based on actual measurements. Monthly sea surface grids of DMS were obtained using a similar scheme, but the sparsity of DMS measurements made the method difficult to implement. A scheme was used which projected actual data into months of the year where no data were otherwise present.

To enable magnetic resonance (MR)-only radiotherapy and facilitate modelling of radiation attenuation in humans, synthetic CT (sCT) images need to be generated. Considering the application of MR-guided radiotherapy and online adaptive replanning, sCT generation should occur within minutes. This work aims at assessing whether an existing deep learning network can rapidly generate sCT images for accurate MR-based dose calculations in the entire pelvis. A study was conducted on data of 91 patients with prostate (59), rectal (18) and cervical (14) cancer who underwent external beam radiotherapy acquiring both CT and MRI for patients' simulation. Dixon reconstructed water, fat and in-phase images obtained from a conventional dual gradient-recalled echo sequence were used to generate sCT images. A conditional generative adversarial network (cGAN) was trained in a paired fashion on 2D transverse slices of 32 prostate cancer patients. The trained network was tested on the remaining patients to generate sCT images. For 30 patients in the test set, dose recalculations of the clinical plan were performed on sCT images. Dose distributions were evaluated comparing voxel-based dose differences, gamma and dose-volume histogram (DVH) analysis. The sCT generation required 5.6 s and 21 s for a single patient volume on a GPU and CPU, respectively. On average, sCT images resulted in a higher dose to the target of maximum 0.3%. The average gamma pass rates using the 3%, 3 mm and 2%, 2 mm criteria were above 97 and 91%, respectively, for all volumes of interests considered. All DVH points calculated on sCT differed less than  ±2.5% from the corresponding points on CT. Results suggest that accurate MR-based dose calculation using sCT images generated with a cGAN trained on prostate cancer patients is feasible for the entire pelvis. The sCT generation was sufficiently fast for integration in an MR-guided radiotherapy workflow.

No abstract

Background and purpose Adaptive radiotherapy based on cone-beam computed tomography (CBCT) requires high CT number accuracy to ensure accurate dose calculations. Recently, deep learning has been proposed for fast CBCT artefact corrections on single anatomical sites. This study investigated the feasibility of applying a single convolutional network to facilitate dose calculation based on CBCT for head-and-neck, lung and breast cancer patients. Materials and Methods Ninety-nine patients diagnosed with head-and-neck, lung or breast cancer undergoing radiotherapy with CBCT-based position verification were included in this study. The CBCTs were registered to planning CT according to clinical procedures. Three cycle-consistent generative adversarial networks (cycle-GANs) were trained in an unpaired manner on 15 patients per anatomical site generating synthetic-CTs (sCTs). Another network was trained with all the anatomical sites together. Performances of all four networks were compared and evaluated for image similarity against rescan CT (rCT). Clinical plans were recalculated on rCT and sCT and analysed through voxel-based dose differences and-analysis. Results A sCT was generated in 10 s. Image similarity was comparable between models trained on different anatomical sites and a single model for all sites. Mean dose differences <0.5% were obtained in high-dose regions. Mean gamma (3%, 3 mm) pass-rates were achieved for all sites. Conclusion Cycle-GAN reduced CBCT artefacts and increased similarity to CT, enabling sCT-based dose calculations. A single network achieved CBCT-based dose calculation generating synthetic CT for head-and-neck, lung, and breast cancer patients with similar performance to a network specifically trained for each anatomical site.