A method of the present disclosure includes performing, by a processing device, a first image registration between a reference image of a patient and a motion image of the patient to perform alignment between the reference image and the motion image, wherein the reference image and the motion image include a target position of the patient. The method further includes performing, by the processing device, a second image registration between the reference image and a motion x-ray image of the patient, via a first digitally reconstructed radiograph (DRR) for the reference image of the patient. The method further includes tracking at least a translational change in the target position based on the first registration and the second registration.

A method comprises identifying a treatment planning image of a target subject, the treatment planning image comprising information associated with an arrangement of structures within the target subject. The method further comprises generating, based on the information, a set of reference data associated with the target subject, the reference data indicating a plurality of positions of the target subject. The method further comprises generating target-subject-specific models based on the reference data and modifying one or more hyper-parameters of the target-subject-specific mode to generate second target-subject-specific models corresponding to a second position of the plurality of positions. The method further comprises controlling a radiation treatment delivery device based on the second target-subject-specific model to deliver a radiation treatment to the target subject.

A computer platform is provided for computer assisted navigation during surgery. The computer platform includes at least one processor that is operative to transform pre-operative images of a patient obtained from a first imaging modality to an estimate of the pre-operative images of the patient in a second imaging modality that is different than the first imaging modality. The at least one processor is further operative to register the estimate of the pre-operative images of the patient in the second imaging modality to intra-operative navigable images or data of the patient.

A failed-image decision support apparatus includes a hardware processor and an outputter. The hardware processor performs, among multiple types of failed-image determination processes, at least one failed-image determination process on a medical image, thereby generating a determination result and determination basis information indicating a basis for the determination result. The outputter outputs the determination result and the determination basis information. Another failed-image decision support apparatus includes a hardware processor. The hardware processor performs, among multiple types of failed-image determination processes, at least one failed-image determination process on a medical image, thereby generating a determination result and determination basis information indicating a basis for the determination result, and controls output of the determination result and the determination basis information.

A computer implemented method for determining a two dimensional DRR referred to as dynamic DRR based on a 4D-CT, the 4D-CT describing a sequence of three dimensional medical computer tomographic images of an anatomical body part of a patient, the images being referred to as sequence CTs, the 4D-CT representing the anatomical body part at different points in time, the anatomical body part comprising at least one primary anatomical element and secondary anatomical elements, the computer implemented method comprising the following steps: acquiring the 4D-CT; acquiring a planning CT, the planning CT being a three dimensional image used for planning of a treatment of the patient, the planning CT being acquired based on at least one of the sequence CTs or independently from the 4D-CT, acquiring a three dimensional image, referred to as undynamic CT, from the 4D-CT, the undynamic CT comprising at least one first image element representing the at least one primary anatomical element and second image elements representing the secondary anatomical elements; acquiring at least one trajectory, referred to as primary trajectory, based on the 4D-CT, the at least one primary trajectory describing a path of the at least one first image element as a function of time; acquiring trajectories of the second image elements, referred to as secondary trajectories, based on the 4D-CT; for the image elements of the undynamic CT, determining trajectory similarity values based on the at least one primary trajectory and the secondary trajectories, the trajectory similarity values respectively describing a measure of similarity between a respective one of the secondary trajectories and the at least one primary trajectory; determining the dynamic DRR by using the determined trajectory similarity values, and, in case the planning CT is acquired independently from the 4D-CT, further using a transformation referred to as planning transformation from the undynamic CT to the planning CT, at least a part of image values of image elements of the dynamic DRR being determined by using the trajectory similarity values.

The present disclosure is related to systems and methods for orthosis design. The method includes obtaining a three-dimensional (3D) model associated with a subject. The method includes obtaining one or more reference images associated with the subject. The method includes determining, based on the 3D model and the one or more reference images, orthosis design data for the subject. The orthosis design data may be used to determine an orthosis for the subject.

Multi-task deep learning method for a neural network for automatic pathology detection, comprising the steps: receiving first image data (I) for a first image recognition task; receiving (S2) second image data (V) for a second image recognition task; wherein the first image data (I) is of a first datatype and the second image data (V) is of a second datatype, different from the first datatype; determining (S3) first labeled image data (I.sub.L) by labeling the first image data (I) and determining second synthesized labeled image data (I.sub.SL) by synthesizing and labeling the second image data (V); training (S4) the neural network based on the received first image data (I), the received second image data (V), the determined first labeled image data (I.sub.L) and the determined second labeled synthesized image data (ISL); wherein the first image recognition task and the second image recognition task relate to a same anatomic region where the respective image data is taken from and/or relate to a same pathology to be recognized in the respective image data.

An image generation method is described, comprising obtaining a plurality of 2D images through an object to be imaged, obtaining a 3D image data set of the object to be imaged, and registering the 2D images with the 3D image data set. The method then further includes defining an image reconstruction plane internal to the object, being the plane of an image to be reconstructed from the plurality of 2D images. Then, for a pixel in the image reconstruction plane, corresponding pixel values from the plurality of 2D images are mapped thereto, and the mapped pixel values are combined into a single value to give a value for the pixel in the image reconstruction plane. Another aspect of the method provides for chatter removed from the image. In a medical imaging context this can provide for “de-boned” images, allowing soft tissue to be more clearly seen.

The present invention relates to a method and apparatus for X-ray phase contrast imaging. The method comprises the following steps: from the measured phase gradient and overall attenuation information, an electron density is computed; the contribution p.sub.c of the Compton scattering to the overall attenuation is estimated from the electron density; the contribution pp of the photo-electric absorption to the overall attenuation is estimated from the overall attenuation and the contribution p.sub.c; the values p.sub.c and p.sub.p are used to reconstruct a Compton image and a photo-electric image; by linear combination of these two images, a monochromatic image at a desired energy is obtained.

An image processing apparatus includes: a base period extracting unit extracting a first target region period based on a first periodic change being a periodic change of a target region in a base moving image acquired by a base moving image acquiring unit; a reference period extracting unit extracting a second target region period based on a second periodic change being a periodic change of the target region in a reference moving image acquired by a reference moving image acquiring unit; a period adjusting unit performing period adjusting processing of synchronizing, for the first target region period or the second target region period, the first periodic change and the second periodic change with each other at a particular phase; and a display image generating unit generating a display image allowing for comparison between the base moving image and the reference moving image after the period adjusting processing is performed.