The present invention relates to a method and apparatus for evaluating inspiration-level quality of a chest radiographic image, wherein the method includes extracting a lung region from a chest radiographic image, detecting a rib cage from the extracted lung region, analyzing a degree of inspiration when the chest radiographic image is captured, and evaluating quality of the chest radiographic image. It is possible for the present invention to be applied to other embodiments.

Proposed are an apparatus and method for spinal surgery planning, the spinal surgery planning method including: acquiring a two-dimensional (2D) spinal image of a patient through a medical imaging apparatus; calculating a registration relationship between coordinates in an image space and coordinates in a surgical space by registering the image space for the spinal image and the surgical space where spinal surgery is performed on the patient; generating a virtual three-dimensional (3D) figure in the surgical space; projecting the 3D figure onto the spinal image based on the registration relationship; adjusting the 3D figure so that the 3D figure can correspond to a predetermined landmark on the spinal image; and setting an insertion position and insertion path of a spinal prosthesis based on the spinal image and the 3D figure.

A machine-based learning method estimates a probability of bone fractures in a 3D image, more specifically vertebral fractures. The method and system utilizing such method utilize a data-driven computational model to learn 3D image features for classifying vertebra fractures. A three-dimensional medical image analysis system for predicting a presence of a vertebral fracture in a subject includes a 3D image processor for receiving and processing 3D image data of a 3D image of the subject, producing two or more sets of 3D voxels. Each of the sets of 3D voxels corresponds to an entirety of the 3D image and each of the sets of 3D voxels consists of equal 3D voxels of different dimensions. The system also includes a voxel classifier for assigning the 3D voxels one or more class probabilities each of the 3D voxels contains a fracture using a computational model, and a fracture probability estimator for estimating a probability of the presence of a vertebral fracture in the subject.

Apparatuses, systems, and techniques to train and apply a first machine learning model to identify a plurality of regions of interest within an input image, and to train and apply a plurality of second machine learning models to identify one or more objects within each region of interest identified by the first machine learning model.

Various methods and systems are provided for automatically registering and stitching images. In one example, a method includes entering a first image of a subject and a second image of the subject to a model trained to output a transformation matrix based on the first image and the second image, where the model is trained with a plurality of training data sets, each training data set including a pair of images, a mask indicating a region of interest (ROI), and associated ground truth, automatically stitching together the first image and the second image based on the transformation matrix to form a stitched image, and outputting the stitched image for display on a display device and/or storing the stitched image in memory.

A computer vision system and method for an orthopedic assessment of the human spine condition. The system uses frontal and sagittal images of the human spine to detect the vertebrae of the spine. More specifically, four edges of each and every vertebra are detected, and the corresponding straight lines, which can be used for assessment, diagnosis and evaluation of various spinal disorders and diseases by orthopedic doctors, are exported. The system has two phases. In phase one, deep learning algorithm for object detection is applied to detect and localize each and every vertebra of frontal and sagittal images of the human spine. In phase two, the system extracts straight lines that correspond to each of the four edges. Using the straight lines, metrics for the spinal assessment, such as the curvature of the spine, the distance of consecutive vertebrae, and crucial angles such as the Cobb angle, can be determined.

A navigated surgery system includes at least one processor that is operative to obtain a 2D medical image slice of anatomical structure of a patient. The operations further obtain a 3D graphical model of anatomical structure. The operations determine a pose of a virtual cross-sectional plane extending through the 3D graphical model of the anatomical structure that corresponds to the anatomical structure of the 2D medical image slice. The operations control the XR headset to display the 2D medical image slice of the anatomical structure of the patient, display the 3D graphical model of the anatomical structure, and display a graphical object oriented with the pose relative to the 3D graphical model of the anatomical structure.

An image processing apparatus obtains segment definition information that defines a plurality of segments obtained by dividing a human body along a body axis, and obtains a three-dimensional image including a plurality of slice images indicating cross sections of a subject. The image processing apparatus identifies, based on the segment definition information, a segment to which a cross section corresponding to at least one slice image among the slice images included in the image belongs, and calculates a coordinate value of the at least one slice image, based on the identified segment and a reference coordinate system in which a coordinate value is defined for each of the segments.

3D image data of a skeletal portion is acquired. A location of a proximal portion of a tool is calculated and a location is derived of a distal portion of the tool with respect to the skeletal portion, with respect to the 3D image data. A display indicates the derived location. First and second 2D images of the distal portion of the tool are acquired from two different poses of a 2D imaging device with respect to the subject and registered with the 3D image data. The location of the distal portion with respect to the 3D image data of the skeletal portion is determined based on the registration and an identified location of the distal portion within the 2D x-rays. Based upon the determined location, the display updates the indicated location of the distal portion. Other embodiments are also described.

A surgical navigation system includes: a tracker (125) for real-time tracking of a position and orientation of a robot arm (191); a source of a patient anatomical data (163) and a robot arm virtual image (166); a surgical navigation image generator (131) generating a surgical navigation image (142A) including the patient anatomy (163) and the robot arm virtual image (166) in accordance to the current position and/or orientation data provided by the tracker (125); a 3D display system (140) showing the surgical navigation image (142A).