This invention is related to a method to adjust the starting position of an acquisition trajectory of a mobile X-ray device that is to perform a portable X-ray tomography acquisition sequence. The invention supports an operator in positioning a mobile X-ray device such that it can subsequently successfully and autonomously perform a digital tomosynthesis exam. Alternatively may an operator provide visual input on a camera image on where he desires the tomosynthesis acquisition to be performed, allowing the mobile X-ray device to adjust its initial starting position autonomously.

Various systems are provided for non-uniform thickness and/or sampling of slabs of the breast to present DBT acquisitions. A method for generating a patient image as a set of slabs representing an imaged object, the method comprising acquiring a tomosynthesis projection, reconstructing a series of slab images, each slab representing a portion of a breast, and a plurality of slabs of non-uniform thickness and/or non-uniform sampling in a 3D reconstructed domain defined by x-, y-, and z-axes.

A medical image processing apparatus of an embodiment includes processing circuitry. The processing circuitry is configured to acquire medical image data on the basis of tomosynthesis imaging of a test object, and input the acquired medical image data of the test object to a trained model to acquire a two-dimensional image data, the trained model being generated by learning of two-dimensional image data on the basis of X-ray imaging of a person and image data on the basis of tomosynthesis imaging of the person who is subjected to the X-ray imaging.

A method for processing breast tomosynthesis images includes: obtaining multiple breast images, performing binarization operation and pooling operation to at least one marked breast image to obtain a lesion mask; training a convolutional neural network (CNN) according to the breast images and the lesion mask; obtaining multiple cropped images from the breast images of different layers according to a particular two-dimensional position, and inputting each cropped image into the CNN to obtain cropped heat maps; inputting the cropped heat maps into a recurrent neural network (RNN) in an order of the levels to obtain output heat maps, and combining the output heat maps to obtain a integrated heat map, and training the RNN according to the integrated heat map and the lesion mask.

An image processing system comprising includes: an acquisition unit that acquires a plurality of projection images obtained by tomosynthesis imaging in which radiation is emitted from a radiation source to a breast at different irradiation angles and a projection image is captured at each irradiation angle by a radiation detector; a tomographic image generation unit that generates a plurality of tomographic images in each of a plurality of tomographic planes of the breast, from the plurality of projection images; a composite two-dimensional image generation unit that generates a composite two-dimensional image from a plurality of images selected from among the plurality of projection images and the plurality of tomographic images; an information generation unit that generates correspondence relationship information representing a correspondence relationship between a position in the composite two-dimensional image and a depth of a tomographic plane corresponding to the position; a display controller that performs control of causing a display device to display the composite two-dimensional image; an acceptance unit that accepts region information representing a designated region designated with respect to the composite two-dimensional image displayed on the display device; and a designated tomographic image generation unit that generates, as a designated tomographic image, a tomographic image in a tomographic plane at a depth which corresponds to the designated region in the composite two-dimensional image and is specified on the basis of the correspondence relationship information, in a case where the acceptance unit accepts the region information, wherein in a case where the designated tomographic image is generated, the display controller further performs control of causing the display device to display the generated designated tomographic image.

A common area derivation unit derives a common area common to at least a part of a plurality of projection images corresponding to a plurality of radiation source positions which are generated by causing an imaging apparatus to perform tomosynthesis imaging in which a radiation source is moved relative to a detection unit to irradiate a subject with radiation at the plurality of radiation source positions according to movement of the radiation source. A display control unit emphasizes effective image areas, corresponding to the common area, of at least a part of a plurality of tomographic images representing a plurality of tomographic planes of the subject which are generated by reconstructing the plurality of projection images, or a composite two-dimensional image generated from the plurality of tomographic images, and displays at least the part of the tomographic images or the composite two-dimensional image on a display.

Methods and systems for identifying internal motion of a breast of a patient during an imaging procedure. The method may include compressing the breast of the patient in a mediolateral oblique (MLO) position. During compression of the breast, a first tomosynthesis MLO projection frame for a first angle with respect the breast is acquired and a second tomosynthesis MLO projection frame for a second angle with respect to the breast is acquired. Boundaries of the pectoral muscle are identified in the projection frames and boundary representations are generated. A difference between the first representation and the second representation is determined. A motion score is then generated based on at least the difference between the first representation and the second representation.

Systems and methods for real-time target validation during radiation treatment therapy based on real-time target displacement and radiation dosimetry measurements.

A processor generates a structure-highlighted synthesized two-dimensional image from a plurality of tomographic images and detects a structure of interest from the plurality of tomographic images and the structure-highlighted synthesized two-dimensional image. The processor sets at least some of the plurality of tomographic images as storage-required images or non-storage-required images according to a result of comparison between the structure of interest detected from the plurality of tomographic images and the structure of interest detected from the structure-highlighted synthesized two-dimensional image.

A processor is configured to set whether or not to generate a structure-highlighted synthesized two-dimensional image from a plurality of tomographic images and to set at least some of the plurality of tomographic images as storage-required images or non-storage-required images according to a result of the setting of whether or not to generate the structure-highlighted synthesized two-dimensional image.