Abstract: The present disclosure relates to a low-dose computed tomography denoising neural network apparatus, wherein the apparatus comprises a dose-aware network unit that provides an LDCT image as an input image to a convolutional neural network (CNN) and outputs a simulated normal-dose computed tomography (NDCT) image as an output image, a noise variance calibration unit that performs noise-variance calibration on the input image fed to the CNN to address the oversmoothing issue of the CNN, and an adaptive noise reduction unit that controls the CNN to progressively remove the noise according to the dose level of a given LDCT image.

Abstract: A neural network training apparatus for dental images through patient-specific data augmentation of the present disclosure includes a bone segmentation unit configured to segment a bone in a dental image to generate a bone mask, a tooth labeling unit configured to label a tooth into which a metal will be inserted in the bone mask to generate a labeled dental image, a metal mask generation unit configured to generate a metal mask in the labeled dental image and perform data augmentation with the metal mask to generate a plurality of augmented metal masks, and a metal-affected image processing unit configured to simulate polychromatic spectrum-based metal artifacts in the plurality of augmented metal masks and calculate a metal attenuation coefficient to generate a metal-affected dental image.

Abstract: The present disclosure relates to an SGM-based LDCT denoising neural network apparatus, wherein the apparatus comprises an input unit receiving an LDCT image, a score model unit processing the LDCT image at each time step by constructing a score-based generative model pre-trained to remove noise from the LDCT training image, an image adjustment unit adjusting noise characteristics of the LDCT image by utilizing the LDCT image at a reference time step through the score-based generative model and generating a noise-fitted LDCT image, a denoising unit progressively removing noise from the noise-fitted LDCT image through iterative input and output operations for each reverse time step of the score-based generative model, and a noise-reconstructed image output unit outputting a noise-reconstructed image generated based on the noise-fitted LDCT image.

Abstract: Disclosed is a technique for quickly removing and correcting a cone-beam artifact generated in a computed tomography (CT) image in consideration of bone and soft tissue regions when using a large-area X-ray detector in order to reduce a CT imaging time for large volumes in a cone-beam CT system. An apparatus includes an input unit configured to receive a start image including a cone-beam artifact, a computation unit configured to separate a high-density material image and a low-density material image from the start image received by the input unit, generate a reproduced image in which the cone-beam artifact is reproduced using the low-density material image, execute a correction process for subtracting the reproduced image from the start image to generate a corrected image, and iterate the correction process using the corrected image as a start image; and an output unit configured to output a final corrected image generated.

Abstract: Disclosed is a technique for quickly removing and correcting a cone-beam artifact generated in a computed tomography (CT) image in consideration of bone and soft tissue regions when using a large-area X-ray detector in order to reduce a CT imaging time for large volumes in a cone-beam CT system. An apparatus includes an input unit configured to receive a start image including a cone-beam artifact, a computation unit configured to separate a high-density material image and a low-density material image from the start image received by the input unit, generate a reproduced image in which the cone-beam artifact is reproduced using the low-density material image, execute a correction process for subtracting the reproduced image from the start image to generate a corrected image, and iterate the correction process using the corrected image as a start image; and an output unit configured to output a final corrected image generated.

Abstract: A method for imaging an object in a computed tomography (CT) system with a plurality of sources comprising a first source and a second source, wherein the plurality of sources together with a detector array are mounted on a rotatable gantry, and wherein an intensity of the second source has unknown fluctuations is provided. Projection data is collected using the first source in a first gantry position. Projection data is collected using the second source in a second gantry position, wherein projection data from the first source in the first gantry position substantially overlaps projection data from the second source in the second gantry position. Data from the first source at the first gantry position is used to correct for source fluctuations of the second source at the second gantry position.

Abstract: A method for imaging unknown objects in a computed tomography (CT) system, comprising determining ray gain for a known object is provided. A CT reconstruction is performed with the known object to obtain reconstructed values. Ideal values are obtained for pixels of the known object. An error related to a difference between the reconstructed values and the ideal values is generated. A ray gain is estimated that reduces the error.

Abstract: A method for imaging an object in a computed tomography (CT) system with a plurality of sources comprising a first source and a second source, wherein the plurality of sources together with a detector array are mounted on a rotatable gantry, and wherein an intensity of the second source has unknown fluctuations is provided. Projection data is collected using the first source in a first gantry position. Projection data is collected using the second source in a second gantry position, wherein projection data from the first source in the first gantry position substantially overlaps projection data from the second source in the second gantry position. Data from the first source at the first gantry position is used to correct for source fluctuations of the second source at the second gantry position.

Abstract: A method for imaging unknown objects in a computed tomography (CT) system, comprising determining ray gain for a known object is provided. A CT reconstruction is performed with the known object to obtain reconstructed values. Ideal values are obtained for pixels of the known object. An error related to a difference between the reconstructed values and the ideal values is generated. A ray gain is estimated that reduces the error.