US 12,482,095 B2
Medical image diagnostic apparatus
Takashi Ida, Kawasaki (JP); and Kenzo Isogawa, Yokohama (JP)
Assigned to CANON MEDICAL SYSTEMS CORPORATION, Tochigi (JP)
Filed by CANON MEDICAL SYSTEMS CORPORATION, Tochigi (JP)
Filed on Apr. 29, 2022, as Appl. No. 17/733,290.
Application 17/733,290 is a continuation of application No. 16/431,240, filed on Jun. 4, 2019, granted, now 11,348,226.
Claims priority of application No. 2018-109558 (JP), filed on Jun. 7, 2018.
Prior Publication US 2022/0254021 A1, Aug. 11, 2022
Int. Cl. G01R 33/48 (2006.01); A61B 5/055 (2006.01); G06T 7/00 (2017.01)
CPC G06T 7/0012 (2013.01) [A61B 5/055 (2013.01); G01R 33/4818 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20084 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A magnetic resonance imaging apparatus comprising:
a memory configured to store a learned model which is taught to generate a first denoise image upon receiving an input of a first magnetic resonance image generated based on first magnetic resonance data, the first denoise image having a reduced amount of noise compared to the first magnetic resonance image and the learned model being a neural network; and
processing circuitry configured to read and execute the learned model,
wherein the processing circuitry is configured to
directly input a g map to an intermediate layer in the neural network and input a second magnetic resonance image to an input layer in the neural network, the second magnetic resonance image generated based on second magnetic resonance data different from the first magnetic resonance data, the g map indicating distribution of a g-factor calculated in relation to the second magnetic resonance data,
adjust at least one of parameters of the learned model based on the g map; and
generate, using the adjusted learned model, a second denoise image having a reduced amount of noise compared to the second magnetic resonance image.