Generating synthetic MRI images from CBCT images with deep learning.
- Generate high contrast MRI images from cone-beam CT images.
- High-quality, high contrast images to enable precise radiation treatment.
Cone-beam computed tomography (CBCT) is an imaging method that produces 3D images of tissues during daily patient treatment. CBCT is cheaper, more accurate, and uses a lower dose of radiation compared to computerized tomography (CT), but often produces lower contrast images. Researchers at Emory University propose generating synthetic MRI images (sMRI) with machine learning to enhance the quality of CBCT images, particularly for soft tissue samples. This technology would contribute to the global radiotherapy market, which is expected to reach $21.95 billion by 2023 at a CAGR of 9.24% from 2018-to 20231. Another potential market is the global external beam radiotherapy market, which is expected to reach $7.869 billion by 2023 at a CAGR of 6.3% from 2017-to 2023 (BCC Research HLC176C).
Researchers have developed a method to enhance the quality of CBCT (cone-beamed computed tomography) images by producing synthetic MRI images (sMRI) via machine learning. The method consists of training a deep learning algorithm 3D cycleGAN to translate CBCT images into MRI images then capture features on the CBCT images using dense blocks and attention gates. When the system is trained the CBCT images can be transmitted into the model, which will generate patches of sMRI. These patches can then be fused together to reconstruct a whole sMRI image.
TTO Home Page: https://emoryott.technologypublisher.com
Name: Sat Balachander
Title: Licensing Associate
Phone: (404) 727-4968