English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

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

MRI-only brain radiotherapy: assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach