Artificial-intelligence-assisted surgery
Supported by artificial intelligence, an object is classified in an X-ray projection image. A 3D representation as well as a localization of the classified object can be determined by matching a model of the classified object to a visualization of the classified object in the X-ray image.
1 . A system for determining a 3D representation and localization of an object in an X-ray projection image with respect to a coordinate system, the system comprising a processing unit configured to execute a computer program product including sets of instructions causing the system to perform the following method:
receiving one X-ray projection image, the X-ray projection image comprising an image characteristic including a pillow effect,
classifying an object in the X-ray projection image,
receiving a model of the classified object,
determining a 3D representation of the classified object based on the X-ray projection image of the object and on the model of the classified object, and
localizing the classified object with respect to the coordinate system, by applying the model to match the classified object in the X-ray image, wherein the step of localizing comprises determining of a 3D orientation of the object with respect to the coordinate system and determining of a 2D spatial position of a projection of the object onto a projection plane of the X-ray projection image, wherein matching of the model with the classified object takes into account the image characteristic of the X-ray projection image;
providing aspects of the 3D representation and localization of the classified object, as determined based on the X-ray projection image, as a priori information; and
performing at least one of a transparent visualization or a 3D reconstruction of the classified object based on the 3D representation and the localization of the classified object.
2 . The system of claim 1 , further comprising an X-ray imaging device.
3 . The system of claim 1 , further comprising a database.
4 . A non-transitory computer readable medium comprising processor-executable instructions for reading data from a processor in communication with an X-ray imaging device, the processor-executable instructions when executed on the processor in a device configure the device to:
receiving one X-ray projection image, the X-ray projection image comprising an image characteristic including a pillow effect;
classifying an object in the X-ray projection image;
receiving a model of the classified object;
determining a 3D representation of the classified object based on the X-ray projection image of the object and on the model of the classified object; and
localizing the classified object with respect to the coordinate system, by applying the model to match the classified object in the X-ray image, wherein the step of localizing comprises determining of a 3D orientation of the object with respect to the coordinate system and determining of a 2D spatial position of a projection of the object onto a projection plane of the X-ray projection image; and
accounting for the image characteristic when matching the model with the classified object;
providing aspects of the 3D representation and localization of the classified object, as determined based on the X-ray projection image, as a priori information; and
performing at least one of a transparent visualization or a 3D reconstruction of the classified object based on the 3D representation and the localization of the classified object.
5 . The non-transitory computer readable medium of claim 4 , wherein the X-ray projection image comprises an image characteristic from a group including a curvature, noise, distortion or a combination thereof.
6 . The non-transitory computer readable medium of claim 4 , wherein the classified object comprises an object characteristic selected from a group including X-ray attenuation, absorption, deflection or a combination thereof, the method further comprising accounting for the object characteristic when matching the model with the classified object in the X-ray projection image.
7 . The non-transitory computer readable medium of claim 4 , further configuring the device to detecting at least part of the outline of the classified object in the X-ray projection image.
8 . The non-transitory computer readable medium of claim 4 , further configuring the device to localizing a further object that is not visible or only partially visible in the X-ray image.
9 . The non-transitory computer readable medium of claim 4 , further configuring the device to transferring geometrical aspects from the model to the object.
10 . The non-transitory computer readable medium of claim 9 , further configuring the device to defining a scale based on the geometrical aspects, for measuring dimensions in the X-ray projection image.
11 . The non-transitory computer readable medium of claim 4 , wherein matching of the classified object in the X-ray projection image with the model further comprises adapting image characteristics of the X-ray projection image to image characteristics of a virtual projection of the model and/or an adaptation of image characteristics of the virtual projection of the model to image characteristics of the X-ray projection image.
12 . The non-transitory computer readable medium of claim 4 , wherein the classified object comprises an object characteristic from a group including wobbling of mechanical interfaces, material of implants, material of tools, bone fractures, or a combination thereof, and matching of the object in the X-ray projection image with the model further comprises accounting for the object characteristic.
13 . The non-transitory computer readable medium of claim 4 , further configuring the device to receiving another one X-ray projection image generated with a different imaging direction, wherein the model is applied in both X-ray images to match the classified object so as to determine a 3D representation of the classified object and to localize the classified object with respect to the coordinate system.
14 . The non-transitory computer readable medium of claim 13 , further configuring the device to providing aspects of the 3D representation and localization of the classified object, as determined based on a first X-ray projection image, as a priori information when processing the further X-ray image so as to perform a 3D reconstruction of the classified object.
15 . The non-transitory computer readable medium of claim 13 , further configuring the device to
classifying another object in both X-ray projection images, wherein a model of the other object is deterministic,
determining a 3D representation and localization of the other object by applying the deterministic model, and
taking into account aspects of the 3D representation and localization of the other object when applying the model in both X-ray images to match the classified object.