Abstract:
A computer-implemented method of determining image perspective score values (s1) for X-ray projection images (110) representing a region of interest (120) in a subject, is provided. The method includes: receiving (SI 10) a plurality of X-ray projection images (110), the X-ray projection images representing the region of interest (120) from a plurality of different perspectives of an X-ray imaging system (130) respective the region of interest; inputting (S120) the X-ray projection images into a neural network (NN1); and in response to the inputting, generating (S130) a predicted image perspective score value (s1) for each of the X-ray projection images.
Abstract:
A controller (220) for determining a shape of an interventional medical device in an interventional medical procedure based on a location of the interventional medical device includes a memory (221) that stores instructions and a processor (222) that executes the instructions. The instructions cause a system (200) that includes the controller (220) to implement a process that includes obtaining (S320) the location of the interventional medical device (201) and obtaining (S330) imagery of a volume that includes the interventional medical device. The process also includes applying (S340), based on the location of the interventional medical device (201), image processing to the imagery to identify the interventional medical device (201) including the shape of the interventional medical device (201). The process further includes (S350) segmenting the interventional medical device (201) to obtain a segmented representation of the interventional medical device (201). The segmented representation of the interventional medical device (201) is overlaid (S360) on the imagery.
Abstract:
A controller for reducing noise in an ultrasound environment includes memory that stores instructions; and a processor that executes the instructions. When executed by the processor, the instructions cause the controller to execute a process that includes controlling emission, by an ultrasound probe, of multiple beams each at a different combination of time of emission and angle of emission relative to the ultrasound probe. The process also includes identifying repetitive noise from a first source received with the imaging beams at a sensor on an interventional medical device, including a rate at which the repetitive noise from the first source repeats and times at which the repetitive noise from the first source is received. The process also includes interpolating signals based on the imaging beams received at the sensor to offset the repetitive noise from the first source at the times at which the repetitive noise from the first source is received.
Abstract:
A method for tracking an interventional medical device in a patient includes interleaving, by an imaging probe external to the patient, a pulse sequence of imaging beams and tracking beams to obtain an interleaved pulse sequence. The method also includes transmitting, from the imaging probe to the interventional medical device in the patient, the interleaved pulse sequence. The method further includes determining, based on a response to the tracking beams received from a sensor on the interventional medical device, a location of the sensor in the patient.
Abstract:
A controller (250) for identifying out-of-plane motion of a passive ultrasound sensor (S1) relative to an imaging plane from an ultrasound imaging probe includes a memory (391) that stores instructions and a processor (392) that executes the instructions. When executed by the processor, the instructions cause a system that includes the controller (250) to implement a process that includes obtaining (S710), from a position and orientation sensor (212) fixed to the ultrasound imaging probe (210), measurements of motion of the ultrasound imaging probe (210) between a first point in time and a second point in time. The process implemented by the controller (250) also includes obtaining (S720) intensity of signals received by the passive ultrasound sensor (S1) at the first point in time and at the second point in time based on emissions of beams from the ultrasound imaging probe (210), and determining (S730), based on the measurements of motion and the intensity of signals, directionality of and distance from the passive ultrasound sensor (S1) to the imaging plane.
Abstract:
An ultrasound (US) system (10) includes a US scanner (14) and a US probe (12) operatively connected to the US scanner. At least one electronic processor (20) is programmed to: control the US scanner and US probe to acquire a series of preoperative images of a tumor and surrounding blood vessels in a region of interest (ROI) of a patient; provide a graphical user interface (GUI) (26) via which the acquired preoperative images are labeled with contours of the tumor and the surrounding blood vessels in the ROI; tune a trained neural network (30) for the patient using the labeled preoperative images to generate a patient-tuned trained neural network; perform live imaging by controlling the US scanner and US probe to acquire live images of the tumor and the surrounding blood vessels in the ROI of the patient; input the live images to the patient-tuned trained NN to output live contours of the tumor and the surrounding blood vessels; and control a display device (24) to display the live images with the live contours superimposed.
Abstract:
A system (200) performs a medical procedure in a region of interest of a patient. The system includes an interventional medical device (214) insertable into the region of interest, and a sensor (215) attached to a portion of the interventional device, the sensor being configured to convert an ultrasonic wave from an ultrasound imaging probe (211) to a corresponding electrical radio frequency (RF) signal. The corresponding RF signal is received by a wireless receiver (209) outside the region of interest, enabling determination of a location of the sensor within the region of interest.
Abstract:
A method for aligning spatially different subvolumes of ultrasonic data of a blood vessel comprising: acquiring temporally discrete signals of a blood vessel with elements of a two dimensional array of ultrasonic transducer elements from spatially different depths of scanning opposed by each transducer element, said array being located in a first position with respect to the blood vessel during the acquiring; Doppler processing the temporally discrete signals received from each transducer element to produce spectral Doppler data of the scanning depth opposed by each transducer element; producing a first three dimensional map of the spectral Doppler data in spatial relationship to the position of the array with respect to the blood vessel; acquiring temporally discrete signals of the blood vessel with elements of the two dimensional array of ultrasonic transducer elements from spatially different depths of scanning opposed by each transducer element, said array being located in a second position with respect to the blood vessel during the acquiring; Doppler processing the temporally discrete signals received from each transducer element to produce spectral Doppler data of the scanning depth opposed by each transducer element; producing a second three dimensional map of the spectral Doppler data in spatial relationship to the position of the array with respect to the blood vessel; aligning the first three dimensional map with the second three dimensional map on the basis of one or more regions of matching spectral Doppler data of the two map; and producing a combined three dimension map of the blood flow of the vessel from the aligned first and second three dimensional maps.
Abstract:
A computer-implemented method of providing a temporal sequence of 3D angiographic images (110) representing a flow of a contrast agent through a region of interest (120),is provided. The method includes: inputting (S130) volumetric image data (130a, 130b), and atemporal sequence of 2D angiographic images (140) into a neural network (NN1); and generating (S140) the predicted temporal sequence of 3D angiographic images (110) representing the flow of the contrast agent through the region of interest (120) in response to the inputting.
Abstract:
A computer-implemented method of predicting a status of an embolization procedure on an aneurism, includes: receiving (S110) projection image data (110) representing temporal blood flow in a region of the anatomy including the aneurism during the embolization procedure; inputting(S120) the received projection image data (110) into a neural network (120) trained to predict temporal blood flow (130), wherein the neural network (120) is trained to predict temporal blood flow(130) using training data (140) representing temporal blood flow in a region of the anatomy that does not include an aneurism; and in response to the inputting (S120): generating (S130) an output (160)indicative of the status of the embolization procedure based on the predicted temporal blood flow.