Abstract: Techniques are described for estimating intentions of pedestrians and other road users in vicinity of a vehicle. In certain embodiments, the techniques comprise obtaining, by a computer system of a vehicle equipped with one or more sensors, a sequence of video frames corresponding to a scene external to the vehicle, detecting one or more vulnerable road users (VRUs) in the sequence of video frames, wherein the detecting comprises estimating pose of each of the detected one or more VRUs. The techniques further include generating a segmentation map of the scene using one or more of the video frames; estimating one or more intention probabilities using estimated pose of the one or more VRUs and the segmentation map, each intention probability corresponding to one of the detected one or more VRUs, and adjusting one or more automated driving actions based on the estimated one or more intention probabilities.

Abstract: A method for forming a virtual 3D mathematical model of a dental system, including receiving DICOM files representing the dental system; identifying number and location of voxels of tissues of the dental system; combining the voxels of the tissues into voxels of organs of the dental system; combining the organs into the virtual 3D mathematical model of the dental system, wherein the virtual 3D mathematical models supports linear, non-linear and volumetric measurements of the dental system; and presenting the virtual 3D mathematical model to a user. The DICOM files can be cone beam or multispiral computed tomography, MRT, PET and/or ultrasonography. The tissues include enamel, dentin, pulp, cartilage, periodontium, and/or jaw bone. The organs include teeth, gums, temporomandibular joint and/or jaw. A size of the voxels is typically between 40 ?m and 200 ?m.

Abstract: The present disclosure relates to a method, system and non-transitory computer readable medium. In some embodiments, the method includes: acquiring image data of a target subject positioned on a scanning table of an imaging device; determining, by a processor, first position information of the target subject by inputting the image data into a first machine learning model, the first position information of the target subject including a posture of the target subject relative to the imaging device; determining, by the processor, second position information related to a scan region of the target subject by inputting the image data into a second machine learning model, the second position information including a position of the scan region relative to the scanning table and the imaging device; and causing the imaging device to scan the target subject based on the first position information and the second position information.

Abstract: Some embodiments of the present disclosure provide a pneumothorax detection method performed by a computing device. The method may comprise obtaining predicted pneumothorax information, predicted tube information, and a predicted spinal baseline with respect to an input image from a trained pneumothorax prediction model; determining at least one pneumothorax representative position for the predicted pneumothorax information and at least one tube representative position for the predicted tube information, in a prediction image in which the predicted pneumothorax information and the predicted tube information are displayed; dividing the prediction image into a first region and a second region by the predicted spinal baseline; and determining a region in which the at least one pneumothorax representative position and the at least one tube representative position exist among the first region and the second region.

Abstract: A surgical system includes a robotic device, a surgical tool mounted on the robotic device, and a processing circuit. The processing circuit is configured to receive image data of an anatomy, generate a virtual bone model based on the image data, identify a soft tissue attachment point on the virtual bone model, plan placement of an implant based on the soft tissue attachment point, generate a control object based on the placement of the implant, and control the robotic device to confine the surgical tool within the control object.

Abstract: According to one embodiment, a medical image processing apparatus includes processing circuitry. The processing circuitry designates a region of interest in a first tomogram among multiple tomograms which are based on tomosynthesis imaging performed with a subject compressed in a first direction. The processing circuitry specifies a second tomogram corresponding to the region of interest from among multiple tomograms which are based on tomosynthesis imaging performed with the subject compressed in a second direction different from the first direction.

Abstract: A method for detecting a finger occlusion image includes: N first original occlusion images and M first non-occlusion images are acquired, and first training data set is generated based on first original occlusion images and first non-occlusion images; first training is performed, based on first training data set, on neural network model for detection of finger occlusion image; L second original occlusion images and K second non-occlusion images are acquired, and second training data set is generated based on second original occlusion images and second non-occlusion images; linear classifier in neural network model having completed first training is replaced with iterative training module to form finger occlusion image detection model; second training is performed on finger occlusion image detection model based on second training data set; image to be detected is input into trained finger occlusion image detection model, to determine whether image to be detected is finger occlusion image.

Abstract: A method for measuring the motion response of a dummy in a crash test comprises: acquiring images of a measurement mark by a camera during the crash test, wherein the measurement mark is fixed on a part to be measured of the dummy, and the dummy is set in association with a preset platform; determining first coordinate positions of the measurement mark in the images; determining corresponding second coordinate positions of the first coordinate positions in a static coordinate system according to a preset conversion relationship, wherein the X-axis of the static coordinate system is parallel to the motion direction of the preset platform, the Y-axis of the static coordinate system is perpendicular to the motion direction of the preset platform; and determining a motion response trajectory of the part to be measured according to an initial position of the part to be measured and the second coordinate positions.

Abstract: A method including, accessing an occupancy of the workspace. The method also includes, in response to the occupancy status indicating vacancy: at a first time, recording a first image and a second image of the workspace, the first image and the second image characterized by a first resolution; and executing an arrival detection model based on the first and second image. The method further includes, in response to detecting arrival at the workspace: at a third time, recording a third image of the workspace, the third image characterized by a second resolution greater than the first resolution; and executing an occupancy detection model based on the third image. The method additionally includes, in response to detecting occupancy of the workspace: updating the occupancy status to indicate occupancy; and transmitting the occupancy status to a remote scheduling system.

Abstract: Methods and systems are provided for adaptive scan control. In one embodiment, a method includes processing acquired projection data of a monitoring area of a subject to measure a first contrast signal of a contrast agent administered to the subject via a first injection, initializing a contrast scan of the subject according to a fallback scan prescription, determining when each of a plurality of zones of the contrast scan are estimated to occur based on the contrast signal, generating a personalized scan prescription for the contrast scan based on when each of the plurality of zones are estimated to occur, and performing the contrast scan according to the personalized scan prescription after a second injection of the contrast agent.

Abstract: Provided is an artificial intelligence (AI) system simulating functions of a human brain, such as recognition and decision, by using a machine learning algorithm, such as deep-learning. Image display apparatuses are more convenient for a user, by performing user authentication by using an authentication image set generated based on an object recognized from content viewed by the user.

Abstract: Systems and methods for generating a segmentation mask of an anatomical structure, along with a measure of uncertainty of the segmentation mask, are provided. In accordance with one or more embodiments, a plurality of candidate segmentation masks of an anatomical structure is generated from an input medical image using one or more trained machine learning networks. A final segmentation mask of the anatomical structure is determined based on the plurality of candidate segmentation masks. A measure of uncertainty associated with the final segmentation mask is determined based on the plurality of candidate segmentation masks. The final segmentation mask and/or the measure of uncertainty are output.

Abstract: For controlling reconstruction in emission tomography, the quality of data for detected emissions and/or the application controls the settings used in reconstruction. For example, a count density of the detected emissions is used to control the number of iterations in reconstruction to more likely avoid over and under fitting. The count density may be adaptively determined by re-binning through pixel size adjustment to find a smallest pixel size providing a sufficient count density. As another example, the detected data may have poor quality due to motion or high body mass index (BMI) of the patient, so the reconstruction is set to perform differently (e.g., less smoothing for high motion or a different number of iterations for high BMI). The quality of the data may be used in conjunction with the application or task for imaging the patient to control the reconstruction.

Abstract: A material generation apparatus includes an acquisition unit configured to acquire a plurality of camera images, and a material data generation unit configured to generate, based on a camera image selected from among the camera images, at least one of a foreground image and a background image as material data to be used for generation of an image corresponding to a designated viewpoint.

Abstract: Methods and systems for angiographic imaging with optical coherence tomography (OCT) are described using ratio-based and angiographic deviation based calculations. In using these calculations to determine motion, arbitrary interframe permutations may be used, post- calculated, non-linear results for projection visualization may be averaged, poor matches may be eliminated on an A-line by A-line basis, windowing functions may be used to improve results, partial spectrums may be used when capturing data, and a minimum intensity threshold may be used for determining which pixels to use.

Abstract: Aspects of the present disclosure relate to machine learning techniques for identifying collections of items, such as furniture items, that are visually complementary. These techniques can rely on computer vision and item imagery. For example, a first portion of a machine learning system can be trained to extract aesthetic item qualities or attributes from pixel values of images of the items. A second portion of the machine learning system can learn correlations between these extracted aesthetic qualities and the level of visual coordination between items. Thus, the disclosed techniques use computer vision machine learning to programmatically determine whether items visually coordinate with one another based on pixel values of images of those items.

Abstract: This disclosure describes how to identify objects in an augmented reality environment. More specifically, the various systems and methods described herein describe how an augmented reality device can recognize objects within a real world environment, determine where the object is located, and also identify the various surfaces of the object in real time or substantially real time.

Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.

Abstract: The accuracy of an intervention site in surgery is predicted and the predicted intervention site is presented to a surgeon. A surgery support apparatus includes a prediction data generation unit that generates prediction data predicting an intervention site based on data before an intervention using an artificial intelligence algorithm. The artificial intelligence algorithm is an artificial intelligence algorithm learning an intervention site by analyzing data before the intervention and intervention site data for an object, and outputs coordinates, a region, or a shape of one point of the intervention site as prediction data. Data before the intervention used for learning of the artificial intelligence algorithm and input data input to the artificial intelligence algorithm to generate prediction data correspond to image data, a segment image, a feature point, etc. The prediction data is displayed on a display apparatus together with an image of a patient acquired in advance.

Abstract: A method for medical image segmentation. The method includes accessing and updating a knowledge-base in accordance with embodiments of the present invention. The techniques include: receiving a medical image and computing a sparse landmark signature based on the medical image content. Next, a knowledge-base is searched for representative matches to form a base set, wherein the base set comprises a plurality of reference image sets. A portion of the plurality of reference image sets of the base set is deformed to generate mappings from the base set to the medical image set. Finally a weighted average segmentation for each structure of interest of the medical image set is determined.