Abstract: A method implemented using at least one processor includes receiving a target image and a reference image. The target image is a distorted magnetic resonance image and the reference image is an undistorted magnetic resonance image. The method further includes selecting an image registration method for registering the target image to the reference image, wherein the image registration method uses an image transformation. The method further includes performing image registration of the target image with the reference image, wherein the image registration provides a plurality of optimized parameters of the image transformation. The method also includes generating a corrected image based on the target image and the plurality of optimized parameters of the image transformation.

Abstract: The present approaches relate to frequency-split iterative reconstruction approaches. In some embodiment, such approaches provide for the combination of the low frequency components of an analytical reconstruction (e.g., a filtered back projection) and the high frequency components of an iterative reconstruction. In certain embodiments, frequency-split iterative reconstruction is used for generating region of interest images.

Abstract: Embodiments of the invention provide systems and methods for evaluating treatment parameters for a patient undergoing radiotherapy. The method includes the step of generating a portal dosimetry image showing differences between a planning image obtained prior to a treatment session and a portal image obtained during the treatment session. A database of prior portal dosimetry results is accessed, and a processor is used to perform a similarity measurement between the portal dosimetry image and the prior portal dosimetry results. Based on the similarity measurement, the system determines whether radiation was delivered as planned during the treatment session.

Abstract: The invention relates to technologies for eye based biometric authentication. The invention provides methods, apparatuses and computer programs for initiating an action based on characteristics of acquired biometric information. In an embodiment, the invention comprises (i) receiving at least one image comprising an image of at least part of an eye, (ii) determining whether the at least part of an eye has birefringent characteristics, and (iii) initiating a predefined action responsive to (a) the at least part of an eye exhibiting birefringent characteristics that are inconsistent with a predefined set of birefringent characteristics or (b) a determined lack of birefringent characteristics typical of a real eye, wherein the predefined action comprises any one or more of denying biometric enrollment, denying biometric authentication, denying access to a resource, denying a request for unlocking of a resource, or transmitting or recording information identifying a spoof.

Abstract: A processor identifies a first set of characteristic models of a structure in cross-plane images acquired at a first acquisition period. The processor identifies a second set of characteristic models of the structure in cross-plane images acquired at a second subsequent acquisition period. The processor determines an amount of rotation of the structure based at least in part on a difference in shape of the first set of characteristic models and the second set of characteristic models. The system and method may include determining a labor progress based at least in part on the determined amount of rotation of the structure. The structure may be a fetal head. The cross-plane images acquired at the first acquisition period may be acquired simultaneously by a single ultrasound device. The cross-plane images acquired at the second subsequent acquisition period may be acquired simultaneously by a single ultrasound device.

Abstract: In part, the disclosure relates to method for identifying regions of interest in a blood vessel. The method includes the steps of: providing OCT image data of the blood vessel; applying a plurality of different edge detection filters to the OCT image data to generate a filter response for each edge detection filter; identifying in each edge detection filter response any response maxima; combining the response maxima for each edge detection filter response while maintaining the spatial relationship of the response maxima, to thereby create edge filtered OCT data; and analyzing the edge filtered OCT data to identify a region of interest, the region of interest defined as a local cluster of response maxima. In one embodiment, one or more indicia are positioned in one or more panels to emphasize a reference vessel profile as part of a user interface.

Abstract: A method for processing and communicating breast tissue image data includes obtaining image data of a patient's breast tissue, processing the image data to form a first subset thereof, transmitting the first subset of the image data to a user computer, receiving a user request from the user computer based on the one or more lower resolution images, processing the image data to form a second subset thereof, and transmitting the second subset of the image data to the user computer. The second subset of the obtained image data is responsive to the user request. The first and second subsets of obtained image data are sufficient to generate one or more respective lower and higher resolution images of respective portions of the patient's breast tissue.

Abstract: An image processing apparatus which extracts a lesion having a ground glass opacity from an image includes a change unit which changes a pixel value corresponding to a candidate region for the ground glass opacity to a predetermined pixel value range, a first feature amount extraction unit which obtains a first feature amount from the image, the pixel value of which is changed, and an extraction unit which extracts the lesion from the image based on the first feature amount.

Abstract: A system and method is disclosed to reduce variation of the clinical decision making process when an image reporting and data system (IRADS) for medical diagnosis is used. Image reporting and data systems provide guidelines for an operator to identify images as belonging to one of a number of categories and specific clinical actions are then recommended based upon such categories. Some clinical actions such as biopsies may be recommended by IRADS even when they are not necessary. The present inventive concept is configured to utilize a Computer-Assisted Diagnosis (CAD) system that is specifically programmed to minimize discrepancies between the recommended clinical actions of an individual or specific group of experts using the standard IRADS process and the optimum clinical actions based on correlation with biopsy proven data. The resulting CAD system reduces the number of unnecessary clinical actions such as biopsies based on the operator's error profile.

Abstract: An image processing device 20 acquires captured images obtained by imaging a sample including a target cell, sets an object region for detecting the target cell in the captured images, extracts a plurality of cell regions each including a cell from a peripheral region including a region other than the object region, sets a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions, and determines whether or not the target cell is included in the object region when the feature quantity obtained from the object region is included in the set range of the feature quantity.

Abstract: A method for reducing metal artifacts in a volume radiographic image reconstructs a first 3-D-image using measured projection images and forms a 3-D image metal mask that contains metal voxels. For each measured projection image, a projection metal mask is a projection of the 3-D image metal mask. A 3-D prior image contains voxels within the 3-D image metal mask. Voxel values of the first 3-D image outside the 3-D image metal mask are replaced with a value representative of air or soft tissue. Non-metal voxels of the 3-D prior image are modified according to a difference between a pixel value related to the nonmetal voxel and the corresponding pixel value in a calculated projection image. Composite projection images are formed by replacing measured projection image data for pixels within the projection metal mask with calculated projection image data. A metal artifact reduced 3-D image is reconstructed from composite projections.

Abstract: There is provided an optical coherence tomography device provided with: an OCT optical system configured to output OCT signal; and an analysis processing unit configured to process the OCT signal and generate motion contrast data of the specimen. The analysis processing unit is provided with: a first image data generation unit configured to process multiple OCT signals to generate first image data representing phase difference information of the multiple OCT signals, and a second image data generation unit configured to process the OCT signal to generate second image data representing amplitude information of the OCT signal. The analysis processing unit generates the motion contrast data based on the phase difference information in the first image data and the amplitude information in the second image data.

Abstract: Described here are systems and methods for estimating bulk rotation and translation of an imaged subject between different blades in a PROPELLER MRI or similar sequence. Correlations between unique pairs of blades are calculated and the relative shift values that maximize the correlation between each pair of blades are identified as relative shift values to be applied for motion correction. Using this method, no reference blade is required, nor does a computationally expensive iterative process need to be performed.

Abstract: Methods, systems, and processor-readable media for detecting the side window of a vehicle. A spatial probability map can be calculated, which includes data indicative of likely side window locations of a vehicle in an image. A side window detector can be run with respect to the image of the vehicle to determine detection scores. The detection scores can be weighted based on the spatial probability map. A detected region of interest can be extracted from the image as extracted image patch. An image classification can then be performed with respect to the extracted patch to provide a classification that indicates whether or not a passenger is in the vehicle or no-passenger is in the vehicle.

Abstract: A method for determining the stock of notes of value in a device (12) for receiving notes of value includes determining the orientation of a note of value before it is fed to the device (12) and storing the order in which the notes of value are received in the device (12). For at least a part of the received notes of value their respective orientation is stored such that it is unambiguously assigned to the note of value. For determining the stock, the respective orientation of a predetermined number of successively removed notes of value is determined. These determined orientations are compared with the stored orientations and dependent on the result of the comparison the stock of notes of value in the device (12) is determined.

Abstract: A camera and method identify moving objects of interest in a field of view of the camera. The method includes: capturing two or more images successively over a time period, each image being associated with different times during the time period; obtaining binary image from each successive pair of images, the binary image comprising a binary value at each pixel indicating whether a change in pixel values of at least a predetermined magnitude has occurred at that pixel between the time associated with the first image of the success pair of images and time associated with the second image of the successive pair of images; deriving one or more motion boxes each encapsulating one or more nearby pixels in binary image; processing motion boxes of each binary image to obtain refined motion boxes; and classifying refined motion boxes each into categories representative of one moving object of interest.

Abstract: Systems and methods for processing distribution items having unique identifiers affixed thereon. The unique identifiers can include computer readable codes and written alphanumeric strings generated by a user. A system receives the unique identifier and requests payment information from a user, and stores an association between the unique identifier and the payment information, and processes the item according to the payment information.

Abstract: A mobile computing device-implemented method of imaging an object to read information, includes capturing, by running an image capturing thread, a plurality of raw images of the object by an image capturing component of the mobile computing device and placing in an image queue in a first memory location; processing, by running an image processing thread, one or more raw images to extract one or more potential machine readable zone (MRZ) candidates and placing in a MRZ candidate queue in a second memory location; analyzing, by running an image analysis thread, an MRZ candidate to detect an MRZ and placing in an MRZ queue in a third memory location; and creating a composite MRZ if a timer has expired, or the MRZ queue has reached a predetermined threshold.

Abstract: A food recognition assistant system includes technologies to recognize foods and combinations of foods depicted in a digital picture of food. Some embodiments include technologies to estimate portion size and calories, and to estimate nutritional value of the foods. In some embodiments, data identifying recognized foods and related information are generated in an automated fashion without relying on human assistance to identify the foods. In some embodiments, the system includes technologies for achieving automatic food detection and recognition in a real-life setting with a cluttered background, without the images being taken in a controlled lab setting, and without requiring additional user input (such as user-defined bounding boxes). Some embodiments of the system include technologies for personalizing the food classification based on user-specific habits, location and/or other criteria.

Abstract: A method of updating a scene model for a foreground segmentation of an input image captured from a camera, is disclosed. One or more visual elements of the input image are determined. A spatial relationship between at least one of the visual elements and the scene model for a foreground segmentation of the input image is determined. The method updates the scene model for determining the foreground segmentation of the input image based on the determined spatial relationship.