Application
A software that employs unsupervised deep learning to correct 4D CT scan image distortion due to respiratory motions.
Key Benefits
Allows the generation of highly precise, motion-corrected 4D CT images
Market Summary
CT scans usually allow radiation oncologists to contour a tumor’s area and position. However, abdominal motions due to breathing can introduce artifacts to the CT images. These artifacts include geometry distortion and image displacement, which cause problems in treatment planning. Deformable image registration (DIR) of 4D-CT images is important in multiple radiation therapy applications including motion tracking of soft tissue or fiducial markers, target definition, image fusion, dose accumulation and treatment response evaluations. It is very challenging to accurately and quickly register 4D-CT abdominal images due to its large appearance variances and bulky sizes.
Technology Summary
The current invention is a deep learning-based software (MS-DIR Net) to reduce target registration errors (TREs) and increase CT image accuracy. MS-DIR Net was tested on a 4D CT dataset of 25 patients and compared to a clinically used software, Velocity. Statistical analysis showed MS-DIR Net produced images with a lower TRE (1.19±0.76 mm) than Velocity (2.49±0.83 mm). These results demonstrate the superior performance of this method in fiducial marker tracking and overall soft tissue alignment compared to software currently available on the market.
Development Stage
Early-stage testing on a 25 patient dataset has been completed.
