US 12,458,301 B2
X-ray CT apparatus and high-quality image generation device
Kana Kobayashi, Chiba (JP); and Taiga Goto, Chiba (JP)
Assigned to FUJIFILM Corporation, Tokyo (JP)
Filed by FUJIFILM Healthcare Corporation, Kashiwa (JP)
Filed on May 8, 2023, as Appl. No. 18/144,281.
Claims priority of application No. 2022-078043 (JP), filed on May 11, 2022.
Prior Publication US 2023/0363724 A1, Nov. 16, 2023
Int. Cl. A61B 6/03 (2006.01); G06T 11/00 (2006.01)
CPC A61B 6/03 (2013.01) [G06T 11/005 (2013.01)] 12 Claims
OG exemplary drawing
 
1. An X-ray CT apparatus comprising:
a scan gantry unit configured to rotate an X-ray source and an X-ray detector around a subject in a state in which the X-ray source and the X-ray detector face each other with the subject interposed therebetween, and acquire measurement data output by the X-ray detector by detecting X-rays emitted from the X-ray source and transmitted through a subject;
an image reconstruction unit configured to generate a CT image of the subject by using the measurement data; and
a high-quality image generation unit including a learned model and configured to obtain a high-quality image output by the learned model by receiving the CT image reconstructed by the image reconstruction unit and inputting the CT image to the learned model,
wherein the learned model is a model after learning, and in said learning, in which at least one low-quality image generated in advance is input data, and at least one high-quality image higher in image quality than the at least one low-quality image is training data,
wherein the at least one low-quality image and the at least one high-quality image are obtained based on same learning measurement data or learning projection data obtained by logarithmically converting the learning measurement data, and the learning measurement data is data output by a learning X-ray detector by detecting X-rays emitted from a learning X-ray source and transmitted through a learning subject, the learning X-ray source and the learning X-ray detector being rotated around the learning subject in a state in which the learning X-ray source and the learning X-ray detector face each other with the learning subject interposed therebetween, and
wherein each of the at least one low-quality image is a CT image reconstructed from data obtained by extracting partial data obtained by dividing from the learning measurement data or the learning projection data in any one of a view direction, a column direction, and a channel direction of the learning X-ray detector, and each of the at least one high-quality image is a CT image obtained by reconstructing the learning projection data.