From: Preliminary landscape analysis of deep tomographic imaging patents
No | Title | Comments | Owner | Priority date |
---|---|---|---|---|
US2020273215A1 | Monochromatic CT image reconstruction from current-integrating data via ML | A neural network is configured to learn a nonlinear mapping function to map from a CT image reconstructed from a single spectral current-integrating projection data collected in a current-integrating X-ray detector to an image reconstructed from a virtual monochromatic projection data at a pre-specified kVp energy level. The technique realizes monochromatic CT imaging and overcomes the beam hardening problem. | RPI | 09–26-17 |
US2020196973A1 | Apparatus and method for dual-energy CT image reconstruction using sparse kVp-switching and DL | A neural network is trained to suppress artifacts in the reconstructed CT images. Another network is trained to perform image-domain material decomposition from the previous model’s output to correct beam hardening and spatial variations in the X-ray beam. | Canon | 12–21-18 |
US2019130571A1 | Method and system for compensating for motion artifacts by means of ML | A ML method is used for motion artifacts compensation. | Siemens | 10–27-17 |
US2019295294A1 | Method for processing parameters of a machine-learning method and reconstruction method | A method is proposed for providing a correction dataset for motion correction of a CT image dataset of an object using processing parameters of a machine-learning method. | Siemens | 03–23-18 |
US2019328341A1 | System and method for motion estimation using AI in helical computed tomography | A method is proposed for estimating and compensating motion artifacts produced during image reconstruction from helical CT scan data. | Canon | 11–16-16 |
US2021056688A1 | Using DL to reduce metal artifacts | An image correction method is proposed by using a neural network to generate a metal artifact image from a CT image; and generating a corrected X-ray image by subtracting the metal artifact image from the original image. | Philips | 01–26-18 |
WO2020033355A1 | DL-based method for metal reduction in CT images and applications of same | A deep-learning-based method is proposed for metal artifact reduction in CT images. | Vanderbilt University | 08–06-18 |
WO2019063760A1 | DL based scatter correction | A neural network is trained on Monte Carlo simulated imaging data with at least one X-ray photon scattering mechanism to convert the projection data to a scatter free data, which is further used to reconstruct the CT image. | Philips | 09–28-17 |