Image processing device and image processing method
AssigneeHamamatsu Photonics K.K.
InventorFumio HASHIMOTO
Life of this patent
Estimating the term…
Abstract
An image processing apparatus includes a sinogram creation unit, a CNN processing unit, a convolution integration unit, a forward projection calculation unit, a CNN training unit, a storage unit, and an image reconstruction unit. The forward projection calculation unit performs forward projection calculation on an output image to create a calculated sinogram. In a first processing step, the CNN training unit trains a CNN based on an error between a reconstructed image created by the image reconstruction unit and the output image. In a subsequent second processing step, the CNN training unit trains the CNN based on an error between a measured sinogram and the calculated sinogram.
Claims23
An image processing apparatus for creating a tomographic image of a subject based on coincidence information collected by a radiation tomography apparatus including a plurality of detectors arranged around a measurement space in which the subject into which an RI source is injected is placed, the image processing apparatus comprising:
- an image reconstruction unit configured to create a reconstructed image by using an analytical image reconstruction method or a statistical image reconstruction method based on the coincidence information collected by the radiation tomography apparatus;
- a sinogram creation unit configured to create a sinogram based on the coincidence information collected by the radiation tomography apparatus;
- a CNN processing unit configured to input an input image to a convolutional neural network, and create an output image by the convolutional neural network;
- a forward projection calculation unit configured to perform forward projection calculation on the output image to create a sinogram;
- and
- a CNN training unit configured to train the convolutional neural network, wherein
- in a first processing step,
- the CNN training unit is configured to use an evaluation function including an error evaluation term representing an evaluation value related to an error between the reconstructed image and the output image, and train the convolutional neural network based on a value of the evaluation function, and
- respective processes of the CNN processing unit and the CNN training unit are repeatedly performed a plurality of times, and
- in a second processing step following the first processing step,
- the CNN training unit is configured to use an evaluation function including an error evaluation term representing an evaluation value related to an error between the sinogram created by the sinogram creation unit and the sinogram created by the forward projection calculation unit, and train the convolutional neural network based on a value of the evaluation function, and
- the output image after respective processes of the CNN processing unit, the forward projection calculation unit, and the CNN training unit are repeatedly performed a plurality of times is set as the tomographic image of the subject.
An image processing method for creating a tomographic image of a subject based on coincidence information collected by a radiation tomography apparatus including a plurality of detectors arranged around a measurement space in which the subject into which an RI source is injected is placed, the image processing method comprising:
- an image reconstruction step of creating a reconstructed image by using an analytical image reconstruction method or a statistical image reconstruction method based on the coincidence information collected by the radiation tomography apparatus;
- a sinogram creation step of creating a sinogram based on the coincidence information collected by the radiation tomography apparatus;
- a CNN processing step of inputting an input image to a convolutional neural network, and creating an output image by the convolutional neural network;
- a forward projection calculation step of performing forward projection calculation on the output image to create a sinogram;
- and
- a CNN training step of training the convolutional neural network, wherein
- in a first processing step,
- in the CNN training step, an evaluation function including an error evaluation term representing an evaluation value related to an error between the reconstructed image and the output image is used, and the convolutional neural network is trained based on a value of the evaluation function, and
- respective processes of the CNN processing step and the CNN training step are repeatedly performed a plurality of times, and
- in a second processing step following the first processing step,
- in the CNN training step, an evaluation function including an error evaluation term representing an evaluation value related to an error between the sinogram created in the sinogram creation step and the sinogram created in the forward projection calculation step is used, and the convolutional neural network is trained based on a value of the evaluation function, and
- the output image after respective processes of the CNN processing step, the forward projection calculation step, and the CNN training step are repeatedly performed a plurality of times is set as the tomographic image of the subject.
Dependencies are inferred from the claim text.