A method for processing breast tissue image data includes obtaining image data of a patient's breast tissue, processing the image data to generate a set of image slices, the image slices collectively depicting the patient's breast tissue; feeding image slices of the set through each of a plurality of object-recognizing modules, each of the object-recognizing modules being configured to recognize a respective type of object that may be present in the image slices; combining objects recognized by the respective object-recognizing modules to generate a synthesized image of the patient's breast tissue; and displaying the synthesized image.

The present invention relates to a method and system for the transformation of raw mammograms to normalised presentation and where the pixel values are independent of imaging conditions. The performed method includes: contrast enhancement, for improved visibility of the breast tissue composition, whereby a region of the breast is segmented and a contrast-stretching algorithm applied to the segmented region to preferably create an enhanced raw image or mammogram; local ‘maximum’ transform, whereby a 2-dimensional first filter is designed to extract the maximum pixel value from a region of interest (ROI) to preferably create a local maximum image or map; ratio map derivation, whereby the pixel value of the ratio map measures a relative response of the said pixel to its local maximum thus capturing the difference between breast composition regardless of mammogram variations.

Systems and methods are provided for a multi-scale deep learning-based digital breast tomosynthesis (DBT) image reconstruction that mitigates the superposition of breast tissue along with the limited angular artifacts, and improves in-depth resolution of the resulting images. A multi-scale deep neural network may be used where a first network may focus on a first parameter, such as limited angular artifacts reduction, and a second network may focus on a second parameter, such as image detail refinement. The output from the first neural network may be used as the input for the second neural network. The systems and methods may reduce the sparse-view artifacts in DBT via deep learning without losing image sharpness and contrast. A deep neural network may be trained in a way to reduce training-time computational cost. An ROI loss method may be used for further improvement on the resolution and contrast of the images.

An imaging system, such as a DBT system, capable of providing an operator of the system with information concerning the location, magnitude and direction of motion detected by the system during performance of the scan to enhance image processing. The imaging system provides the motion information to the operator directly in conjunction with the images processed by the imaging system thereby providing the operator with sufficient information for decisions regarding the need for additional images for completing the scan with the imaging system before the patient is discharged, or even before the breast is decompressed.

Methods and systems for identifying a region of interest in breast tissue utilize artificial intelligence to confirm that a target lesion identified during imaging the breast tissue using a first imaging modality (e.g. x-ray imaging) has been identified using a second imaging modality (e.g. ultrasound imaging). A computing system operating a lesion matching engine utilizes a machine learning classifier algorithm trained on cases of x-ray images and corresponding ultrasound images in which lesions were identified for further analysis. The lesion matching engine analyzes a target lesion identified with x-ray imaging and a potential lesion identified with ultrasound imaging to determine a likelihood that the target lesion is the same as the potential lesion. A confidence level indicator for the lesion match is presented on a display of a computing device to aid a healthcare provider in locating a lesion in breast tissue.

Digital Breast Tomosynthesis allows for the acquisition of volumetric mammography images. The present invention allows for novel ways of viewing such images to detect microcalcifications and obstructions. In an embodiment a method for displaying volumetric images comprises computing a projection image using a viewing direction, displaying the projection image and then varying the projection image by varying the viewing direction. The viewing direction can be varied based on a periodic continuous mathematical function. A graphics processing unit can be used to compute the projection image and bricking can be used to accelerate the computation of the projection images.

An image processing device acquires a plurality of projection images, inputs the acquired plurality of projection images to a tomographic image estimation model, which is a trained model generated by performing machine learning on a machine learning model using learning data composed of a set of correct answer data that is three-dimensional data indicating a three-dimensional structure and of a plurality of virtual projection images, onto which the three-dimensional structure has been projected by performing pseudo-projection on the three-dimensional structure with radiation at a plurality of virtual irradiation positions using the three-dimensional data, and which receives the plurality of projection images as an input and outputs an estimated tomographic image group, and acquires the estimated tomographic image group output from the tomographic image estimation model.

An image generation method is described, comprising obtaining a plurality of 2D images through an object to be imaged, obtaining a 3D image data set of the object to be imaged, and registering the 2D images with the 3D image data set. The method then further includes defining an image reconstruction plane internal to the object, being the plane of an image to be reconstructed from the plurality of 2D images. Then, for a pixel in the image reconstruction plane, corresponding pixel values from the plurality of 2D images are mapped thereto, and the mapped pixel values are combined into a single value to give a value for the pixel in the image reconstruction plane. Another aspect of the method provides for chatter removed from the image. In a medical imaging context this can provide for “de-boned” images, allowing soft tissue to be more clearly seen.

A method and system for acquiring, processing, storing, and displaying x-ray mammograms Mp tomosynthesis images Tr representative of breast slices, and x-ray tomosynthesis projection images Tp taken at different angles to a breast, where the Tr images are reconstructed from Tp images

A method for planning an examination of an examination object by a tomosynthesis machine includes: Raw data of the examination object are acquired from defined acquisition angles. An auxiliary data set is reconstructed from the raw data. Depth data are calculated based on the auxiliary data set calculating a number of projections from the perspective of a respectively defined projection center from the auxiliary data set or from the raw data. Each of the projections has a number of image points each linked with associated depth data. The projections are displayed and at least one projection is chosen. A position of an examination region of the examination object is marked therein. A real three-dimensional position of the examination region is calculated using the marked position and its depth data, and an examination path to the examination region is calculated.