One or more example embodiments of the present invention relates to a computer-implemented method for providing an outline of a lesion in digital breast tomosynthesis includes receiving input data, wherein the input data comprises a reconstructed tomosynthesis volume dataset based on projection recordings, a virtual target marker within a lesion being in the tomosynthesis volume dataset; applying a trained function to at least a part of the tomosynthesis volume dataset to establish an outline enclosing the lesion, the part of the tomosynthesis volume dataset corresponding to a region surrounding the virtual target marker in the tomosynthesis volume dataset; and providing output data, wherein the output data is an outline of a two-dimensional area or a three-dimensional volume surrounding the target marker.

A method for determining an abnormality in a medical device from a medical image is provided. The method for determining an abnormality in a medical device comprises receiving a medical image, and detecting information on at least a part of a target medical device included in the received medical image.

An intraoral x-ray system mountable to a dentist’s office wall including components movable to compensate for defects in the wall’s flatness or the wall not being sufficiently perpendicular to the floor. The system also includes monitoring and compensation capabilities to compensate for drift in the position of the system’s x-ray source or patient movement before and during x-ray imaging, thereby avoiding the need for the taking of additional x-ray images and exposing the patient unnecessarily to extra x-ray dose. Additionally, the system further includes a data/signal processing unit that allows the x-ray source to be precisely moved along a predetermined trajectory and allows the system to perform computed tomosynthesis examinations of a patient. In addition, the x-ray source is attachable/detachable from the system’s robotic arm, with the system compensating automatically for the change in weight at the robotic arm’s end due to removal of the x-ray source.

An approach for improving determining a significant slice associated with a tumor from a volume of medical images is disclosed. The approach is based on the annotation of tumor range and the slice index in which the tumor appears to have the largest area. The approach infer a tumor growth classifier on sliding window of the volume slices and creates a discrete integral function out of the classifier predictions. The approach applies post processing on the discrete integral function which can include a smoothing function and a bias correction. The approach selects the slice index of maximum value from the post processing step.

Methods and systems for deep learning based image reconstruction are disclosed herein. An example method includes receiving a set of imaging projections data, identifying a voxel to reconstruct, receiving a trained regression model, and reconstructing the voxel. The voxel is reconstructed by: projecting the voxel on each imaging projection in the set of imaging projections according to an acquisition geometry, extracting adjacent pixels around each projected voxel, feeding the regression model with the extracted adjacent pixel data to produce a reconstructed value of the voxel, and repeating the reconstruction for each voxel to be reconstructed to produce a reconstructed image.

Digital tomosynthesis (DT) gives better diagnostic information than 2D X-ray, rivalling CT. However, tomosynthesis reconstruction requires sophisticated algorithms and a powerful computer, and can take several minutes to complete. The present invention takes a single x-ray image of a body 50 using multiple sources. In normal tomography and tomosynthesis imaging, such overlapping cones would lead to un-reconstructable data as significant overlap, in general, can’t be deconvolved and is not soluble. However, here, for the detection and localization of dense, compact objects 40, a location of an object 40 may be determined in three spatial dimensions from a single two-dimensional image. That is, processor-intensive reconstruction of a three-dimensional volume may be avoided.

A radiography apparatus is provided in which delays in it do not occur due to the influence of preliminary preparation of a radiation detector. The FPD 4 receives a signal from an X-ray tube control unit 6 and then completes preliminary preparation for the detection of radiation during accelerated movement of an X-ray tube 3 or the FPD 4. That is, the accelerated movement of the X-ray tube 3 or the FPD 4 and the preliminary preparation for the detection of radiation are carried out simultaneously. This enables imaging to be started immediately after the start of constant speed movement of the X-ray tube 3 or the FPD 4 without having to wait for constant speed movement thereof to start preliminary preparation of the FPD 4 as in conventional apparatuses. As a result, delays in imaging do not affect the radiation image.

An imaging system may include an imaging detector to capture an image of human tissue and a compression paddle situated apart from the imaging detector to compress the human tissue between the compression paddle and the imaging detector. A force sensor may generate a force signal indicating a measure of force applied superior to the human tissue. A movement detection circuit may filter a movement signal from the force signal indicating a measure of movement of the compressed human tissue. A movement analysis module may determine that the movement signal is beyond a movement threshold. An image correction module to perform a corrective action based upon the determination that the movement signal is beyond a movement threshold.

A system and method for constructing fluoroscopic-based three dimensional volumetric data from two dimensional fluoroscopic images including a computing device configured to facilitate navigation of a medical device to a target area within a patient and a fluoroscopic imaging device configured to acquire a fluoroscopic video of the target area about a plurality of angles relative to the target area. The computing device is configured to determine a pose of the fluoroscopic imaging device for each frame of the fluoroscopic video and to construct fluoroscopic-based three dimensional volumetric data of the target area in which soft tissue objects are visible using a fast iterative three dimensional construction algorithm.

A system and method using an inflatable jacket over the compression paddle of a mammography and/or tomosynthesis system to enhance imaging and improve patient comfort in x-ray breast imaging.