The present application provides a method for acquiring aorta based on deep learning and a storage medium, comprising: acquiring a database of slices of an aortic layer and a database of slices of a non-aortic layer; performing deep learning on the database of slices of the aortic layer and the database of slices of the non-aortic layer, to obtain a deep learning model; acquiring CT sequence images to be processed or three-dimensional data of CT sequence images to be processed; extracting feature data from the CT sequence images to be processed or the three-dimensional data of the CT sequence images to be processed; acquiring an image of the aorta from the CT sequence images based on the deep learning model and the feature data.

A procedure is performed with respect to a skeletal portion within a body with a tool mounted upon a steerable arm. 3D image data is acquired of the skeletal portion. First and second x-ray images of the tool and the skeletal portion are acquired from respective first and second views. A computer processor (i) registers the first and second images to the image data, (ii) identifies a location of the tool with respect to the skeletal portion, within the first and second images, (iii) determines the tool's location with respect to the image data, (iv) compares the tool's location with a designated locational element, (v) calculates the 3D difference between the tool's location and the locational element, and (vi) generates steering instructions for the arm such that the tool is moved toward the locational element. Other applications are also described.

Method of segmenting anatomical structures such as organs in 3D scans in an architecture that combines U-net, time-distributed convolutions and bidirectional convolutional LSTM.

System and method of more efficiently identifying and segmenting anatomical structures from 2-D cone beam CT images, rather than from reconstructed 3-D volume data, is disclosed. An image processing system receives, from a cone beam CT device, at least one 2-D x-ray image, which is part of a set of x-ray images taken from a 360 degree scan of a patient with a cone beam CT imaging device. The x-ray image contains at least one anatomical structure such as vertebral bodies to be segmented. The received x-ray is then analyzed in order to identify and segment the anatomical structure contained in the x-ray image based on a stored model of anatomical structures. Once the 360 degree spin is completed, a 3-D image volume from the x-ray image set is created. The identification and segmentation information derived from the x-ray image is then added to the created 3-D image volume.

A system for surgical planning and assessment of spinal pathology or spinal deformity correction in a subject, the system comprises a control unit configured to align one or more vertebral bodies of a biomechanical model to one or more vertebral bodies of the radiograph. The control unit is configured to receive one or more spinal correction inputs. The control unit is configured to, based on the received one or more spinal correction inputs, simulate the biomechanical model in a predetermined posture. The control unit is configured to provide for display one or more characteristics of the simulated biomechanical model.

An image alignment system and method which generates X-ray aligned patient specific 3D models. In particular, the image alignment system combines a CT scan and an X-ray into a single patient specific 3D model that, leveraging the benefits of both types of images and providing a surgeon with a single model for diagnosing a spinal deformity, for engaging and education a patient about the spinal deformity, and for preparing for spinal surgery. The system allows the CT scan to be done with the patient in the prone condition while the X-ray can be done with the patient in a vertical, e.g., standing, position to capture impacts on the spine from that vertical position.

Systems and methods for visualization of a surgical site are disclosed. An imaging device provides image data of the surgical site. A computing device detects, in the image data, at least one obstruction. The computing device filters the image data to remove the at least one obstruction by being configured to alter pixels related to the at least one obstruction based on at least one of (i) one or more buffered frames and (ii) one or more pixels adjacent to the pixels related to the at least one obstruction. The computing device generates an output from the filtered image data. A display device presents the output for visualization of the surgical site.

Using a first imaging device, 3D image data of a skeletal portion is acquired. A second imaging device is positioned in a first position, and a starting image is generated by either, (a) generating based on the 3D image data a first 2D projection image corresponding to the first position, or (b) acquiring with the second device, from the first position, an acquired 2D image of the skeletal portion and, using a computer processor (22), registering the acquired 2D image with the 3D image data. The second device is moved to a second position, and without acquiring a 2D image with the second device from the second position, using the at least one computer processor, generating based on the 3D image data a subsequent image that is a 2D projection image that corresponds to the second position of the second device. Other embodiments are also described.

Systems and methods for tracking movement of an anatomical element are provided. A marker may be coupled to an anatomical element and may be tracked by a navigation system. Movement of the marker may be detected by the navigation system and a pose of the marker may be determined based on the movement. The pose of the marker may be validated when the pose substantially matches a desired predetermined pose.

Systems and methods for registering one or more anatomical elements are provided. The system may comprise an imaging device and a navigation system configured to track a pose of a marker coupled to an object and configured to identify the marker. A first image may be received from a surgical plan. Pose information describing the pose of the marker and a marker identification of the marker may be obtained from the navigation system. An object identification based on the marker identification may be retrieved from a database. Image data of a second image depicting an anatomical element and the object may be obtained from the imaging device. The image data, the pose information, and the object identification may be input into a registration model. The registration model may be configured to register the anatomical element to the first image based on the pose information and the object identification.