Various embodiments are described herein for methods, devices and systems that can be used to determine a breast density value from an input image of patient's breast. In one example embodiment, the breast density value is calculated by receiving an input image corresponding to the digital mammogram, removing metadata information from the input image to generate an intermediate image, generating a region of interest (ROI) image based on the intermediate image, extracting values for predictor variables based on the metadata information, the intermediate image and the ROI image, and calculating breast density based on the values of the predictor variables. The breast density value is calculated based on a breast density model.

Abstract systems and methods of biopsy control include reconstructing a 3D volume from a plurality of tomosynthesis projection images and producing a plurality of synthetic stereo images from the plurality of tomosynthesis projection images. At least the synthetic stereo images are presented on a graphical display to a clinician to facilitate at least one input of a biopsy location for biopsy control.

A process for deploying an anti-scattering grid in a mammograph is provided. The mammograph comprises a radiation source configured to emit radiation for taking mammographic images of a patient, a radiation detector comprising a network of sensors arranged periodically with a first pitch, and an anti-scattering grid arranged between the source and the detector, the anti-scattering grid comprising radiation adsorbing strips arranged parallel to each other and distributed periodically with a second pitch. The process comprises: displacing the anti-scattering grid relative to the detector or displacing the detector relative to the anti-scattering grid during emission of radiation; adapting the second pitch to the first pitch, wherein displacement is perpendicular to the direction of the strips of the anti-scattering grid, the strips being arranged parallel to a side of the anti-scattering grid positioned against the patient, and altering the positions of the return points between successive periods of the displacement motion.

A method and apparatus for deep learning based automatic bone removal in medical images, such as computed tomography angiography (CTA) volumes, is disclosed. Bone structures are segmented in a 3D medical image of a patient by classifying voxels of the 3D medical image as bone or non-bone voxels using a deep neural network trained for bone segmentation. A 3D visualization of non-bone structures in the 3D medical image is generated by removing voxels classified as bone voxels from a 3D visualization of the 3D medical image.

A method, including, receiving three-dimensional tomographic data with respect to a body of a living subject, and using the data to generate a representation of an external surface of the body and displaying the representation on a screen. The method further includes inserting an invasive instrument into a region of the body and identifying a position of the instrument in the body. The method also includes rendering an area of the external surface surrounding the identified position of the instrument locally transparent in the displayed representation, so as to make visible on the screen an internal structure of the body in a vicinity of the identified position.

According to one embodiment, a medical image processing apparatus, includes: a first acquisition unit; a second acquisition unit; and a part-removed image generation unit, wherein the first acquisition unit is adapted to acquire a first radiograph that is a virtual radiograph generated to have a specified part or a predetermined part, among parts included in volume data indicative of a three-dimensional structure of an inside of a body of a patient, being emphasized, the second acquisition unit is adapted to acquire a second radiograph of the inside of the body of the patient, and the part-removed image generation unit is adapted to generate a part-removed image by removing the specified or predetermined part or parts other than the specified or predetermined part from the second radiograph with reference to the first radiograph.

Provided is a radiation imaging apparatus including: an image acquiring unit configured to acquire a first radiation image, which is photographed by irradiating an object with radiation under a state in which a subject is not in an imaging range, and a second radiation image, which is photographed by radiating radiation under a state in which the subject and the object are in the imaging range; and an image processing unit configured to perform correction for deleting image information on the object from the second radiation image by using the first radiation image.

Various embodiments are described herein for methods, devices and systems that can be used to determine a breast density value from an input image of patient's breast. In one example embodiment, the breast density value is calculated by receiving an input image corresponding to the digital mammogram, removing metadata information from the input image to generate an intermediate image, generating a region of interest (ROI) image based on the intermediate image, extracting values for predictor variables based on the metadata information, the intermediate image and the ROI image, and calculating breast density based on the values of the predictor variables. The breast density value is calculated based on a breast density model.

A system and method are provided for obtaining an improved visualization of bone objects comprised in a projection X-ray image. The projection X-ray image comprises bone objects which at least in part overlap. According to the system and method, a number of the bone objects are delineated by a contour, thereby obtaining a number of delineated bone objects. For each of the number of delineated bone object, a bone suppression technique is applied to the image to obtain respective bone image data individually showing the respective delineated bone object while suppressing shadows of obstructing objects. The bone image data generated for each of the number of delineated bone objects is used to generate an output image in which the bone objects do not overlap. An advantage of the system and method is that a non-overlapping, shadow-suppressed, presentation of the bone objects may be created from an X-ray image which was obtained by projectional radiography.

A radiography system includes: a radiography apparatus including a first radiation detector and a second radiation detector which is provided so on a side of the first radiation detector from which the radiation is transmitted and emitted, and a grid that is configured to remove scattered radiation included in the radiation transmitted through a subject; and an acquisition unit that is configured to acquire, using the grid, a first radiographic image captured by the first radiation detector and a second radiographic image captured by the second radiation detector; and a removal unit that is configured to detect and remove a first grid image, which is an image of the grid, from the first radiographic image acquired by the acquisition unit, and to remove the image of the grid from the second radiographic image acquired by the acquisition unit, using the first grid image.