Systems and method for automatically generating structures, such as target volumes, in a treatment image using structure-guided deformation to propagate the structures from a planning image onto the subsequently acquired treatment image.

An attention mechanism-based low-dose dual-tracer PET reconstruction method. The method achieves low-dose dual-tracer PET image reconstruction by an attention mechanism-based convolution network model, and estimates the standard dose and separates dual-tracer PET signals in a sinogram. With the help of deep learning, a feature extraction tool, the method can reconstruct standard-dose single-tracer PET images in a PET Low-Dose Dual-Tracer Sinogram.

This disclosure relates to an intraoperative localisation system for total joint replacement of a joint of a patient by a surgeon, the joint being associated with a bone. The localisation system comprises: an X-ray imaging device to create a digital X-ray image of the joint and a localisation object during a total joint replacement surgery; a computer system configured to: store a surgical plan comprising a digital three-dimensional model; receive the digital X-ray image of the joint and the localisation object during the total joint replacement surgery; determine a pose of the localisation object relative to the bone or the joint, based on the digital X-ray image; assess the pose of the localisation object against the surgical plan; and provide an indication of a clinical consequence of the pose in relation to the surgical plan to the surgeon.

This disclosure relates to an intraoperative guidance system. The guidance system comprises: an X-ray imaging device to create a two-dimensional digital image of a joint and an implant component; and a computer system configured to: store an initial three-dimensional model of the joint and the implant component; receive two or more two-dimensional digital images of the joint and the implant component; create a digital three-dimensional model of the joint and the implant component based on the two or more two-dimensional digital images; perform registration between the digital three-dimensional model and the initial three-dimensional model to determine a placement of the implant component; determine an intraoperative simulated performance metric by simulating movement of the digital three-dimensional model based on the placement; and provide an indication to a surgeon of the intraoperative simulated performance metric as an assessment of a current placement of the implant component.

Method include emitting x-rays from an x-ray source, directing a first portion of the x-rays through an object grating situated adjacent to an object while the object is scanned relative to the object grating along a scan direction, directing a second portion of the x-rays through the object and subsequently through a detector grating without transmitting through the object grating, wherein the object grating and detector grating are adjacently arranged in a field of view of the x-rays sequentially with respect to each other in the scan direction, and receiving the first portion transmitted through the object and object grating with a first portion of a detector and receiving the second portion transmitted through the object and the detector grating with a second portion of the detector adjacent to the first portion of the detector. Systems are also disclosed, along with related techniques for beam hardening correction.

Disclosed is a linear array ultra-fast scanning x-ray imaging device. The linear array x-ray imaging device is single photon sensitive, operating in frame output mode and including a pixel array Application Specific Integrated Circuit including the readout pixel array. The ASIC includes digital control logic and sufficient memory to accumulate digital output frames in various modes of operation prior to output from the ASIC, permitting advanced imaging functionalities directly on the ASIC, while maintaining a dynamic range of 16 bits and single photon sensitivity. The effective or secondary frames output from the pixel array ASIC can be tagged with user provided external triggers synchronizing the effective frames to the x-ray beam energy and/or to the movement of the x-ray source or imaged object. This enables dual energy imaging and ultra-fast scanning, without complex and costly conventional photon counting x-ray imaging sensors. The system architecture is simpler and higher performance.

Segmentation of multi-energy CT data, including data in three or more energy bands. A user is enabled to input one or more region indicators in displayed CT data. Probability maps are generated and may be refined using distance metrics, which may include geodesic and Euclidean distance metrics. Segmentation may be based on the probability maps and/or refined probability maps. Segmentation of medical image data is also disclosed.

Systems and methods of visualizing a current view of a tool relative to a lesion by processing current fluoroscopic images from a current fluoroscopic sweep occurring after an initial fluoroscopic sweep. The processing includes determining the locations and/or orientations of a tool and a lesion in a current 3D reconstruction of the current fluoroscopic images or in a subset of the current fluoroscopic images, generating a 3D rendering based on the locations and/or orientations of the tool and the lesion, and displaying the 3D rendering. The locations and/or orientations of the tool and the lesion may be obtained from a user interface enabling a user to mark the current locations and/or orientations in the current 3D reconstruction or in a subset of the current fluoroscopic images, or by segmenting the current 3D reconstruction or a subset of the current fluoroscopic images.

A medical image processing apparatus includes an acquisition unit and a processing unit. The acquisition unit acquires volume data of a subject. The processing unit displays a three-dimensional image by rendering the acquired volume data, on a display unit. The processing unit displays a first object showing (i) a point on a body surface of the subject and (ii) a direction to the volume data in the three-dimensional image, and displays a two-dimensional image of a surface including the point on the body surface and being defined based on the direction, in the volume data. The processing unit acquires information of a first operation to change display of the two-dimensional image, and moves the point on the body surface along the body surface of the subject based on the first operation to update display of the first object and the two-dimensional image.

The medical image processing apparatus according to the present embodiment includes processing circuitry. The processing circuitry is configured to acquire volume data generated based on tomosynthesis imaging of a subject. The processing circuitry is configured to set a virtual focal point at a position different from a focal position in the tomosynthesis imaging. The processing circuitry is configured to generate a pseudo projection image based on the virtual focal point and the volume data.