Carestream Health, Inc.

Other

University of Rochester

William J Sehnert

Yuan Lin

Xiaohui Wang

David H Foos

Hui Luo

Levon O Vogelsang

Karin Toepfer

Zhimin Huo

John Yorkston

Peter D Burns

Lori L Barski

Zeljko Ignjatovic

Samuel Richard

Michael D Heath

Nathan J Packard

Jacquelyn S Ellinwood

Richard T Scott

Eliot L Siegel

Dharmendu Damany

Jovan Mitrovic

A machine learning network is trained to generate a noise field image from a radiographic (x-ray) image. The training includes accessing a number of previously acquired radiographic images, duplicating the previously acquired radiographic images, and conditioning each of the duplicated images with simulated noise content to form a plurality of simulated low-exposure images. Each of the simulated low-exposure images is paired with its corresponding previously acquired image to form a learning pair. The machine learning network is trained to generate a noise field image using the learning pairs of images. A noise suppressed image of an object can be generated by applying a scaling factor to at least a portion of the corresponding noise field image and combining the scaled noise field image with a current captured image of the object.

Noise suppression using deep convolutional networks

A method for radiographic imaging of a patient directs imaging radiation to an anatomy of the patient using a radiographic imaging apparatus. A first image of the patient anatomy is captured in a digital detector, and one or more image acquisition factors are electronically stored. A second radiographic image of the same patient anatomy is captured by accessing and using the stored one or more image acquisition factors. A combination of the first and second radiographic images is displayed or transmitted.

Physiological analysis from video x-ray imaging

A radiographic imaging system may be deployed in an ICU unit of a medical facility that may benefit from isolating patients and health care providers. The radiography system provides a plurality of patient beds each having a digital radiographic detector positioned therein. An x-ray source is operable to be selectively positioned relative to each of the patient beds using a remote control system. The remote control system also controls firing of the x-ray source.

Remote and automated intensive care unit

A transducer transmits into the bone a first plurality of excitation pulses at a plurality of frequencies and measures a plurality of echoes corresponding to the plurality of excitation pulses. An ultrasound machine calculates a plurality of energies each corresponding to a respective one of the plurality of echoes and identifies a lowest echo corresponding to a lowest of the plurality of energies. The ultrasound machine matches the lowest echo to a corresponding one of the first plurality of excitation pulses, the corresponding one of the first plurality of excitation pulses having a chosen frequency. The ultrasound machine generates an acoustic impulse response by deconvolving the corresponding one of the first plurality of excitation pulses with the lowest echo, and generates an updated sensing matrix by convolving the initial sensing matrix with the acoustic impulse response. Subsequent ultrasounds use the updated sensing matrix.

System and method for ultrasound imaging of tissue through bone

A mobile radiography apparatus is configured to sparsely sample radiographic projection images to generate high resolution tomosynthesis volume images using a digital radiographic detector that is mechanically uncoupled from the x-ray source and an artificial intelligence network. The artificial intelligence network is trained to correct a volume image generated from sparsely sample projection images to generate the high resolution tomosynthesis volume images.

Low dose digital tomosynthesis system and method using artificial intelligence

A mobile radiography apparatus has radio-opaque markers, each marker coupled to a portion of the mobile radiography apparatus, wherein each of the markers is in a radiation path that extends from an x-ray source or x-ray sources. A detector is mechanically uncoupled from the x-ray source or x-ray sources for positioning behind a patient. Processing logic is configured to calculate a detector position with relation to the x-ray source or x-ray sources according to identified marker positions in acquired projection images, and to reconstruct a volume image according to the acquired projection images.

Self-calibrating technique for x-ray imaging scanners

A mobile radiography apparatus includes radiopaque markers disposed in a radiation path that extends from an x-ray source to a digital radiographic detector, which detector is mechanically uncoupled from the x-ray source or x-ray sources. A processing system calculates a position of the detector relative to the x-ray source or x-ray sources according to identified marker positions in acquired x-ray projection images, and reconstructs a volume image according to the acquired x-ray projection images.

A method for scattered radiation correction acquires radiographic projection image data for a first portion of a subject that lies within a field of view of an imaging apparatus and characterizes the surface contour of the subject that includes at least a second portion of the subject that lies outside the field of view of the imaging apparatus. The surface contour of the subject is characterized according to the reflectance images. The surface contour characterization is registered to the field of view. Scattered radiation is estimated according to the projection image data and the surface contour characterization. The acquired radiographic projection image data is updated according to the estimated scattered radiation. An image of the field of view is displayed according to the conditioned acquired radiographic projection image data.

Apparatus and method for scattered radiation correction

A mobile radiography apparatus has radio-opaque markers, each marker coupled to a portion of the mobile radiography apparatus, wherein each of the markers is in a radiation path that extends from an x-ray source. A detector is mechanically uncoupled from the x-ray source for positioning behind a patient. Processing logic is configured to calculate a detector position with relation to the x-ray source according to identified marker positions in acquired projection images, and to reconstruct a volume image according to the acquired projection images.

A method rotates a radiation source and a detector over a sequence of acquisition angles about a subject and acquires, at each acquisition angle, a 2D projection image. A simulation subset is formed that contains some, but not all, of the acquired 2D projection images, wherein subset membership is determined according to relative signal change between successive 2D projection images. Scatter is characterized for the acquired sequence of projection images according to the formed simulation subset. One or more of the acquired sequence of projection images is corrected using the scatter characterization. An image volume is reconstructed and stored according to the sequence of scatter corrected projection images. One or more images of the reconstructed image volume are rendered to a display or transmitting the stored image volume data.

Variance reduction for monte carlo-based scatter estimation

A position sensor has one or more fiducials formed of radio-opaque material and mounted along a surface of a radio-translucent body. A sensor element is coupled to the radio-translucent body and is spaced apart from the one or more fiducials and is energizable to acquire image content during receipt of exposure energy from an X-ray source to the position sensor. The sensor element is in signal communication with a processor and is energizable to generate data that is indicative of a relative position of the X-ray source. A radio-opaque covering is coupled against an outer surface of the radio-translucent body.

Self-calibrating device for X-ray imaging scanners

A method acquires reflectance image content from patient anatomy that is within a volume of an imaging apparatus defined between a radiation source and a detector and generates a surface contour image from the acquired reflectance image content. The generated surface contour image is compared with surface contour image metrics stored for the imaging apparatus and a recommended adjustment to the position of the patient anatomy is reported according to the comparison.

Patient position monitoring system based on 3D surface acquisition technique

A method for X-ray spectral calibration acquires X-ray projections of a calibration phantom formed of known materials. The X-ray spectrum of an X-ray source is calculated according to the acquired X-ray projections. The calculated X-ray spectrum can be stored, transmitted, or displayed.

X-ray spectral calibration technique for cone-beam CT

A method for reducing metal artifacts in a volume radiographic image acquires a first set of projection images of an object on a radiographic detector at different acquisition angles. An initial estimate of the volume that includes the object using the acquired projection images is generated. The estimated volume is updated by one or more iterations of generating a second set of scatter-corrected projection images using the acquired first set of projection images and the estimated volume; generating a third set of estimated projection images using forward ray-tracing through the estimated volume; and reconstructing the estimated volume according to a signal quality factor obtained from analysis of the detector signal and used in a comparison of the second set of scatter-corrected projection images with the third set of estimated projection images. One or more images rendered from the updated estimated volume are displayed.

Growing community of inventors

Fairport, NY, United States of America

William J Sehnert