	US 12,014,449 B2
	Computed tomography (CT) image reconstruction from polychromatic projection data
Marina Valerievna Chukalina, Moscow (RU); Anastasia Sergeevna Ingacheva, Moscow (RU); and Dmitry Petrovich Nikolaev, Moscow (RU)
Assigned to Smart Engines Service, LLC, Moscow (RU)
Filed by Smart Engines Service, LLC, Moscow (RU)
Filed on Oct. 6, 2021, as Appl. No. 17/495,617.
Claims priority of application No. 2021106628 (RU), filed on Mar. 15, 2021.
Prior Publication US 2022/0292736 A1, Sep. 15, 2022
Int. Cl. G06N 3/08 (2023.01); G06T 11/00 (2006.01)

CPC G06T 11/005 (2013.01) [G06T 2210/41 (2013.01)]

10 Claims

1. A method comprising using at least one hardware processor to:

receive polychromatic projection data acquired by a computed tomography (CT) system, wherein the polychromatic projection data has at least three dimensions comprising a number of detector rows, a number of detector columns, and a number of rotation angles;

determine an optimal correction value for linearization of the polychromatic projection data, wherein determining the optimal correction value comprises

extracting a portion of the polychromatic projection data,

for each of a plurality of power values within a range of power values,

correcting a line from the portion of the polychromatic projection data based on the power value,

calculating a Radon invariant for every rotation angle in the number of rotation angles,

calculating an average of the Radon invariants across all rotation angles in the number of rotation angles, and

calculating an error measure of a ratio between the Radon invariant for each rotation angle and the average Radon invariant, and

determining the optimal correction value based on the error measures calculated for all of the plurality of power values;

linearize the polychromatic projection data according to the determined optimal correction value; and

reconstruct an image from the linearized projection data.