Systems, methods, and devices for generating a corrected image
Systems, methods, and devices for generating a corrected image are provided. A first robotic arm may be configured to orient a source at a first pose and a second robotic arm may be configured to orient a detector at a plurality of second poses. An image dataset may be received from the detector at each of the plurality of second poses to yield a plurality of image datasets. The plurality of datasets may comprise an initial image having a scatter effect. The plurality of image datasets may be saved. A scatter correction may be determined and configured to correct the scatter effect. The correction may be applied to the initial image to correct the scatter effect.
1 . A system for generating a corrected image, comprising:
an imaging device comprising a source configured to emit a wave and a detector configured to receive a signal indicative of the emitted wave;
a first robotic arm configured to orient the source at a first pose;
a second robotic arm configured to orient the detector at a plurality of second poses, wherein each second pose and the first pose define an angle between the source and the detector and a source detector distance extending between the source and the detector;
at least one processor; and
a memory storing data for processing by the at least one processor, the data, when processed, causes the at least one processor to:
receive an image dataset from the detector at each of the plurality of second poses to yield a plurality of image datasets, the plurality of image datasets comprising an initial image having a scatter effect;
save the plurality of image datasets;
determine a scatter correction configured to correct the scatter effect; and
apply the scatter correction to the initial image to correct the scatter effect.
2 . The system of claim 1 , wherein the initial image is a three-dimensional image and the scatter correction corrects the scatter effect for a volume.
3 . The system of claim 1 , wherein the memory includes further data configured to cause the at least one processor to:
train a scatter correction model using a Monte-Carlo simulation to simulate a plurality of photon paths that form at least one of a historical image or a simulated image, wherein determining the scatter correction uses the trained scatter correction model.
4 . The system of claim 1 , wherein determining the scatter correction comprises providing the image dataset to a trained scatter correction model.
5 . The system of claim 4 , wherein the scatter correction model is trained using a plurality of input image datasets, and wherein an output of the scatter correction model comprises the scatter correction.
6 . The system of claim 5 , wherein the scatter correction model averages two or more input image datasets of the plurality of input image datasets.
7 . The system of claim 4 , wherein the scatter correction model is trained using at least one of one or more historical image datasets or one or more simulated image datasets, and wherein an output of the scatter correction model comprises the scatter correction.
8 . The system of claim 1 , wherein the memory includes further data configured to cause the at least one processor to:
calculate a magnification factor based on each image dataset of the plurality of image datasets and the corresponding source detector distance; and
scale the initial image using the magnification factor.
9 . The system of claim 8 , wherein the angle and the source detector distance is determined by subtracting a pose of the source from a pose of the detector.
10 . The system of claim 9 , wherein the pose of the source and the pose of the detector is determined from pose information received from a first sensor of the first robotic arm and a second sensor of the second robotic arm.
11 . The system of claim 1 , wherein the plurality of second poses are at different elevations.
12 . The system of claim 1 , wherein the imaging device is an X-ray device.
13 . A system for generating a corrected image, comprising:
an imaging device comprising a source configured to emit a wave and a detector configured to receive a signal indicative of the emitted wave;
a first robotic arm configured to orient the source at a one or more first poses;
a second robotic arm configured to orient the detector at a plurality of second poses, wherein each second pose and each first pose define an angle between the imaging device and an object and a source detector distance extending between the source and the detector;
at least one processor; and
a memory storing data for processing by the at least one processor, the data, when processed, causes the at least one processor to:
receive an image dataset from the detector where the source is at each of the one or more first poses and the detector is at each of the plurality of second poses to yield a plurality of image datasets, the plurality of image datasets comprising an initial image having a scatter effect;
save the plurality of image datasets;
determine a scatter correction configured to correct the scatter effect; and
apply the scatter correction to the initial image to correct the scatter effect.
14 . The system of claim 13 , wherein the initial image is a three-dimensional image and the scatter correction corrects the scatter effect for a volume.
15 . The system of claim 13 , wherein determining the scatter correction includes determining a first set of photons and a second set of photons, the first set of photons corresponding to un-scattered photons and the second set of photons corresponding to scattered photons.
16 . The system of claim 13 , wherein the memory includes further data configured to cause the at least one processor to:
calculate a magnification factor based on each image dataset of the plurality of image datasets and the corresponding source detector distance; and
scale the initial image using the magnification factor.
17 . The system of claim 16 , wherein the memory includes further data configured to cause the at least one processor to:
train a scatter correction model using a Monte-Carlo simulation to simulate a plurality of photon paths that form at least one of a historical image or a simulated image.
18 . The system of claim 16 , wherein determining the scatter correction comprises using a trained scatter correction model.
19 . The system of claim 18 , wherein the scatter correction model is trained using a plurality of input image datasets and an output of the scatter correction model comprises the scatter correction.
20 . A system for generating a corrected image comprising:
an imaging device comprising a source configured to emit a wave and a detector configured to receive a signal indicative of the emitted wave;
a first robotic arm configured to orient the source at one or more first poses, wherein for each first pose, the source is positioned at a different angle relative to an object;
a second robotic arm configured to orient the detector at a plurality of second poses for each first pose of the one or more first poses, wherein at each second pose the detector is at a different angle relative to the source and at a different source detector distance defined by a distance between the detector and the source;
at least one processor; and
a memory storing data for processing by the at least one processor, the data, when processed, causes the at least one processor to:
receive an image dataset from the detector where the source is at each of the one or more first poses and the detector is at each of the plurality of second poses to yield a plurality of image datasets, the plurality of image datasets comprising an initial three-dimensional image having a scatter effect;
save the plurality of image datasets;
determine a scatter correction configured to correct the scatter effect; and
apply the scatter correction to the initial three-dimensional image to correct the scatter effect.