Abstract: According to an aspect, there is provided a computer implemented method in a central sewer of selecting a training dataset with which to train a model using a distributed machine learning process, wherein the training dataset is to comprise medical data that satisfies one or more clinical requirements and wherein training data in the training dataset is located at a plurality of clinical sites. The method comprises requesting (302) from each of the clinical sites, metadata describing features of matching data at the respective clinical site that satisfies the one or more clinical requirements. The method then comprises determining (304), from the metadata, a measure of variation of the features of the matching data. Based on the measure of variation, the method then comprises selecting (306) training data for the training dataset from the matching data using the metadata.

Abstract: According to an aspect, there is provided a method of training a model to perform a task on medical data using a distributed machine learning process whereby a global model is updated based on training performed on local copies of the model at a plurality of clinical sites. The method comprises a) sending (302) information to the plurality of clinical sites to enable each of the plurality of clinical sites to create a local copy of the model and train the respective local copy of the model on training data at the respective clinical site. The method then comprises b) receiving (304), from each of the plurality of clinical sites, i) a local update to a parameter in the model obtained by training the local copy of the model on the training data at the respective clinical site and ii) metadata related to a quality of the training performed at the respective clinical site; and c) updating (306) the parameter in the global model, based on the received local updates to the parameter and the received metadata.

Abstract: Presented are concepts for detecting subject motion in medical imaging of a subject. One such concept obtains a motion classification model representing relationships between motion of image features and subject motion values. For each of a plurality of medical slice images of an imaged volume of the subject, an image feature of the medical slice image is extracted. Based on the extracted image feature for each of the plurality of medical slice images, motion information for the image feature is determined. Based on the motion information for the image feature and the obtained motion classification model, a subject motion value is determined.

Abstract: There is provided a computer-implemented method (200) for obscuring one or more facial features of a subject in an image. A head of the subject is detected in the image (202) and a location of one or more facial features of the subject is identified in the image (204). A region of the image to modify is determined based on the location of the one or more facial features (206). The determined region comprises a part of the head on which the one or more facial features are located. The image within the determined region is modified to obscure the one or more facial features (208).

Abstract: Presented are concepts for detecting subject motion in medical imaging of a subject. One such concept obtains a motion classification model representing relationships between motion of image features and subject motion values. For each of a plurality of medical slice images of an imaged volume of the subject, an image feature of the medical slice image is extracted. Based on the extracted image feature for each of the plurality of medical slice images, motion information for the image feature is determined. Based on the motion information for the image feature and the obtained motion classification model, a subject motion value is determined.

Abstract: There is provided a computer-implemented method (200) for obscuring one or more facial features of a subject in an image. A head of the subject is detected in the image (202) and a location of one or more facial features of the subject is identified in the image (204). A region of the image to modify is determined based on the location of the one or more facial features (206). The determined region comprises a part of the head on which the one or more facial features are located. The image within the determined region is modified to obscure the one or more facial features (208).

Abstract: There is provided an apparatus (104) for storing medical imaging data. The apparatus comprises a processor configured to acquire a medical imaging study relating to a subject; identify elements in the medical imaging study that are indicative of the identity of the subject; anonymize the medical imaging study by removing the identified elements from the medical imaging study; deliver the anonymized medical imaging study for storage at a first location; and deliver data relating to the identified elements for storage at a second location. An apparatus for retrieving medical imaging data from storage, associated methods and a computer program product are also disclosed.

Abstract: A method for automatically detecting pulmonary embolism (PE) candidates within medical image data using an image processing device includes administering radiocontrast into a patient. A sequence of computed tomography (CT) images is acquired. A level of radiocontrast at a pulmonary artery trunk of the patient is determined. One or more PE candidates are detected within a pulmonary artery tree of the patient based on the determined level of radiocontrast at the pulmonary artery trunk. The one or more detected PE candidates are displayed.

Abstract: A method of detecting blood vessel shadows in an anterior posterior x-ray radiograph comprising the steps of: generating candidate sub areas of the radiograph showing changes in contrast above a threshold level; supressing rib shadow edges; eliminating lung tissue shadow edges, and categorizing and eliminating nodule shadows.

Abstract: A method of detecting lung nodules in an anterior posterior x-ray radiograph comprising the steps of: generating candidate regions in image showing changes in contrast above a threshold level, and eliminating false positives by eliminating edges assignable to organs by: identifying edges; categorizing and eliminating rib edges; categorizing and eliminating lung tissue edges, and categorizing and eliminating blood vessels.

Abstract: A medical imaging system is used to recognize an internal structure from a three-dimensional image. The image includes image sub-volumes. An image sub-volume is selected using a non-linear search pattern. The selected image sub-volume is analyzed for the presence of the internal structure. The steps of selecting an image sub-volume using the non-linear search pattern and analyzing the selected sub-volume for the presence of the internal structure are repeated until the internal structure is found in an image sub-volume. Bounds of the internal structure are identified based on the location of the image sub-volume within which the internal structure is found.

Abstract: A method for automatically detecting pulmonary embolism (PE) candidates within medical image data using an image processing device includes administering radiocontrast into a patient. A sequence of computed tomography (CT) images is acquired. A level of radiocontrast at a pulmonary artery trunk of the patient is determined. One or more PE candidates are detected within a pulmonary artery tree of the patient based on the determined level of radiocontrast at the pulmonary artery trunk. The one or more detected PE candidates are displayed.

Abstract: A method of detecting lung nodules in an anterior posterior x-ray radiograph comprising the steps of: generating candidate regions in image showing changes in contrast above a threshold level, and eliminating false positives by eliminating edges assignable to organs by: identifying edges; categorizing and eliminating rib edges; categorizing and eliminating lung tissue edges, and categorizing and eliminating blood vessels.

Abstract: A method of detecting blood vessel shadows in an anterior posterior x-ray radiograph comprising the steps of: generating candidate sub areas of the radiograph showing changes in contrast above a threshold level; supressing rib shadow edges; eliminating lung tissue shadow edges, and categorizing and eliminating nodule shadows.

Abstract: A method and apparatus for estimating a depth of a crack from ultrasound scan data are provided. The method includes mapping multiple amplitude responses from the ultrasound scan data, each mapped amplitude response being representative of a signal from one of the sensors. The method further includes locating multiple linear responses among the mapped amplitude responses, each linear response being an indicator of a reflected signal from the crack. One or more sensor that corresponds to the linear responses from a given crack is identified. The depth of the crack is estimated using data from the identified sensors.

Abstract: A medical imaging system is used to recognize an internal structure from a three-dimensional image. The image includes image sub-volumes. An image sub-volume is selected using a non-linear search pattern. The selected image sub-volume is analyzed for the presence of the internal structure. The steps of selecting an image sub-volume using the non-linear search pattern and analyzing the selected sub-volume for the presence of the internal structure are repeated until the internal structure is found in an image sub-volume. Bounds of the internal structure are identified based on the location of the image sub-volume within which the internal structure is found.