Abstract: The present invention relates to a system and a method for detecting pain experienced by a patient in relation to a pose of the patient. The system comprises a pose estimation unit configured to estimate the pose of the patient and a pain detection unit configured to detect pain experienced by the patient. The system further comprises a processing unit configured to determine a correlation between the detected pain experienced by the patient and the estimated pose of the patient. The determined correlation can be displayed on a display unit to a physician.

Abstract: The invention relates to an X-ray image processing system (4) comprising an X-ray image input interface (8), a computing unit (9) and an X-ray image output interface (11). The X-ray image input interface (8) is configured to receive original X-ray images taken by an X-ray imaging system (1) comprising an X-ray source (2) and an X-ray detector (3). The computing unit (9) is connected to the X-ray image input interface (8) and is configured to obtain at least one original X-ray image from the X-ray image input interface (8), obtain information relating to the relative detector pose of the X-ray detector (3) relative to the X-ray source (2) and obtain a point of interest (P) in the original X-ray image, wherein the point of interest (P) is an anatomical structure or a part within an anatomical structure.

Abstract: A computer-implemented method of compensating for image quality issue in an image study. The method includes acquiring a current image study, measuring, via a processor, a patient positioning parameter indicating a deviation of a patient position in the current image study to an optimal patient position for an image exam type of the current image study and analyzing, via an analysis module, the current image study and the determined patient positioning parameter to determine a relationship between positioning errors and a grading of a diagnostic finding for the current image study, wherein the grading of the diagnostic finding includes one of a severity of the diagnostic finding or a certainty classification of the diagnostic finding.

Abstract: The present invention relates to patient positioning. In order to facilitate patient positioning, an apparatus is provided that comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive an X-ray image of an anatomy of interest of a patient obtained from a first image acquisition and a target set of pose parameters describing a target position of the anatomy of interest for image acquisition. The processing unit is configured to detect the anatomy of interest in the X-ray image, to determine a set of pose parameters describing a current position of the detected anatomy of interest in the first image acquisition, to determine a difference between the determined set of pose parameters and the target set of pose parameters, and to construct a trajectory that defines a sequence of sets of pose parameters for bringing the anatomy of interest from the current position to the target position, if the difference is equal to or greater than a pre-defined threshold.

Abstract: Technology provides baseline images for diagnostic applications, including receiving a diagnostic image relating to a condition of a patient, the diagnostic image reflecting one of a normal state or an abnormal state of the condition, and generating a baseline image via a neural network using the diagnostic image, where the neural network is trained to generate a prediction of the diagnostic image reflecting a normal state of the condition. The neural network can include a generative adversarial network (GAN) trained only on image data with a normal state of the condition, where generating the baseline image includes an optimization process to maximize a similarity between the diagnostic image and a response of the GAN. Generating the baseline image can include selecting a portion of the diagnostic image, and adjusting a relevance weighting to be applied to the selected portion of the diagnostic image in the optimization process.

Abstract: In order to enhance enhanced X-ray image inhalation quality monitoring, a metric is proposed hat reproducibly provides an index of ribs visible to be used in the assessment of the inhalation state. In an example, a detected diaphragm in a chest X-ray image may be projected into an atlas that contains labels for all intercostal spaces, namely spaces between rib centerlines. A spatial representation of both the clavicle and the ribs is provided in the atlas, a cumulative histogram is built for all points, i.e. pixels, of the diaphragm, for every point a rib label counter of the rib in the rib label map at that point is incremented as well as all ribs above it, the rib label counter is normalized by a division by the number of points, the median (or a different quantile) may be taken of this distribution serving as an inhalation index. An objective metric of inhalation state is thus achieved.

Abstract: The present invention provides a retrospective analysis of subject and/or implant positioning. Provided is a method and device for assisting positioning of a subject having an implant in X-ray imaging. The method comprises the steps of receiving (S1) X-ray image data of the subject including the implant, receiving (S2) exam request data indicating at least an exam type to be performed for the specific implant, and determining at least one set of image features being assigned to the requested exam type and indicative for positioning of the subject and/or the implant relative to an X-ray imaging device. Further, the method comprises analyzing (S3) an image content of the received X-ray image data for the determined set of image features, and determining (S4), from the analysis of the image content, a feedback being indicative for positioning the subject and the X-ray imaging device to each other with respect to a target positioning, to be provided for assisting the positioning.

Abstract: The present invention relates to prospective analysis of subject and/or implant positioning. Provided is a computer-im-plemented method for assisting positioning of a subject having an orthopedic implant in X-ray imaging. The method comprises applying one or more radiofrequency, RF, signals to an anatomy of interest of the subject where the orthopedic implant is located. The method further comprises detecting a response signal and/or signal change in response to the applied RF signal impacting the orthopedic implant and tissue being adjacent to and/or surrounding the implant, and determining, from the detected response signal and/or signal change, an implant positioning estimation relative to an X-ray imaging device. Further, the method comprises determining, from the implant positioning estimation, a feedback being indicative for positioning the X-ray imaging device and the subject to each other with respect to a target positioning, to be provided for assisting the positioning.

Abstract: The present invention relates to medical imaging. In order to reduce repeat images, it is proposed to enable automated prediction of quality metrics prior to image formation by exploiting data from sensors. This may greatly improve the quality of medical image data acquired in the actual imaging examination, thereby leading to fewer retakes, less delayed treatment to patients, shortened workflow, and higher patient rate. In X-ray and CT exams, fewer retakes may also reduce radiation doses for patients.

Abstract: The invention relates to a method (100) for supervised training of an artificial neural network for medical image analysis. The method comprises acquiring (SI) first and second sets of training samples, wherein the training samples comprise feature vectors and associated predetermined labels, the feature vectors being indicative of medical images and the labels pertaining to anatomy detection, to semantic segmentation of medical images, to classification of medical images, to computer-aided diagnosis, to detection and/or localization of biomarkers or to quality assessment of medical images. The accuracy of predetermined labels may be better for the second set of training samples than for the first set of training samples. The neural network is trained (S3) by reducing a cost function, which comprises a first and a second part.

Abstract: An X-ray imaging system (100) includes an X-ray source (110) and an X-ray detector (120) that are separated by an examination region (150) for performing an X-ray imaging operation on an object (160). A processor (140) is configured to identify (S120) one or more internal structures (180) within the object (160), based on a comparison of depth sensor data representing a three-dimensional surface (170) of the object (160), with an anatomical model comprising the one or more internal structures (180). The processor (140) is also configured to compute (S130), using the depth sensor data and the identified one or more internal structures (180), a surface projection (190) of the one or more internal structures, on the surface (170) of the object (160), from a perspective of the X-ray source (110); and to output (S140) an image representation of the surface projection (190) for displaying as an overlay on the surface (170) of the object (160).

Abstract: The invention is related to a method for providing guidance data (30, 41) for positioning a region of interest (20, 31, 41, 56) of a subject (54), an X-ray source (52), and an X-ray detector (21, 34, 53). The method comprises: obtaining, by a processor (11), current positioning data of at least one palpable bony landmark (23, 33) derived from a palpation; obtaining current positioning data of the X-ray source (52) and of the X-ray detector (21, 34, 53) (S20); determining guidance data (30, 41) for positioning the region of interest (20, 31, 41, 56), the X-ray source (52) and the X-ray detector (21, 34, 53) and providing, by the processor (11), the guidance data (30·41) (S40).

Abstract: 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 (IL) by labeling the first image data (I) and determining second synthesized labeled image data (ISL) 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 (IL) 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 recogni

Abstract: There is provided a computer-implemented method for determining rotation of a patient's chest in a medical image. The method comprises: receiving the medical image of the patient; processing the medical image to determine scapular spatial data relating to the patient's scapula; and determining rotation of the patient's chest with respect to at least one reference axis using the scapular spatial data.

Abstract: There is provided a computer-implemented method of estimating lung volume from radiographic images. The method comprises: registering (102) a two dimensional radiographic image (12) of a patients chest to a three dimensional radiographic image (14) of the patients chest to estimate data describing projection geometry (16) of an imaging setup used to capture the two dimensional radiographic image; using the projection geometry to estimate (104) at least one radiographic magnification factor (18) relating to the imaging setup; and calculating (106) an estimated lung volume (20) using the two dimensional radiographic image and the at least one radiographic magnification factor.

Abstract: Concepts for generating a dark X-ray (DAX) model adapted to represent relations between a DAX signal, a respiratory state, and a respiratory disease grade, as well as concepts for using the DAX model are proposed. In particular, as relations between these variables are modelled, the difference between a DAX signal of a subject at a respiratory state, compared to a DAX signal of a subject at a reference respiratory state may be assessed. Thus, the diagnostic accuracy of DAX imaging may be improved.

Abstract: The present disclosure provides a medical system (100) comprising at least one data processing unit (111, 121, 130), a mechanical ventilator (110), configured to be operated to cause a ventilation status at a to-be-ventilated subject, and a medical imaging device (120), configured as a mobile device. The at least one data processing unit (111, 121, 130) is configured to obtain, from the mechanical ventilator (110), ventilation status information associated with the ventilation status of the to-be-ventilated subject. Further, the at least one data processing unit (111, 121, 130) is further configured to trigger acquisition of a first image if the ventilation status meets a first image acquisition criterion. Furthermore, the at least data processing unit (111, 121, 130) is further configured to trigger acquisition of at least one subsequent, further image if the ventilation status meets a second image acquisition criterion.

Abstract: There is provided a computer-implemented method of estimating lung volume from radiographic images. The method comprises: registering (102) a two dimensional radiographic image (12) of a patients chest to a three dimensional radiographic image (14) of the patients chest to estimate data describing projection geometry (16) of an imaging setup used to capture the two dimensional radiographic image; using the projection geometry to estimate (104) at least one radiographic magnification factor (18) relating to the imaging setup; and calculating (106) an estimated lung volume (20) using the two dimensional radiographic image and the at least one radiographic magnification factor.

Abstract: In order to enhance enhanced X-ray image inhalation quality monitoring, a metric is proposed hat reproducibly provides an index of ribs visible to be used in the assessment of the inhalation state. In an example, a detected diaphragm in a chest X-ray image may be projected into an atlas that contains labels for all intercostal spaces, namely spaces between rib centerlines. A spatial representation of both the clavicle and the ribs is provided in the atlas, a cumulative histogram is built for all points, i.e. pixels, of the diaphragm, for every point a rib label counter of the rib in the rib label map at that point is incremented as well as all ribs above it, the rib label counter is normalized by a division by the number of points, the median (or a different quantile) may be taken of this distribution serving as an inhalation index. An objective metric of inhalation state is thus achieved.

Abstract: A system and related method for image processing. The system comprises an input (IN) interface for receiving two segmentation maps for an input image. The two segmentation maps (11,12) obtained by respective segmentors, a first segmentor (SEG1) and a second segmentor (SEG2). The first segmentor (SEG1) implements a shape-prior-based segmentation algorithm. The second segmentor (SEG2) implements a segmentation algorithm that is not based on a shape-prior, or at least the second segmentor (SEG2) accounts for one or more shape priors at a lower weight as compared to the first segmentor (SEG1). A differentiator (DIF) configured to ascertain a difference between the two segmentation maps. The system may allow detection of abnormalities.