Abstract: A medical image processing device includes a storage and a processor. The storage stores notification setting information for setting a notification content regarding which method a notification is performed in accordance with lesion information indicating content of a lesion, part information representing a part, or procedure information representing a procedure performed at a time of acquisition of a medical image. The processor is configured to acquire the medical image including a subject; perform image analysis processing on the medical image; select use-notification setting information from the notification setting information by using the lesion information, the part information or the procedure information; and perform the notification to notify a user of a result of the image analysis processing with different methods of the notifications for different lesion information, part information or procedure information according to the use-notification setting information.

Abstract: A non-transitory computer-readable recording medium having stored an image processing program that causes a computer to execute a process, the process includes extracting a plurality of consecutive pixels corresponding to a first part or a second part of a body, from a pixel column in a predetermined direction of an image of the body, obtaining a statistical value of pixel values of the plurality of consecutive pixels, and identifying a part corresponding to the plurality of consecutive pixels, among the first part or the second part, based on the statistical value.

Abstract: An information processing method includes: obtaining sensing data; determining a synthesis region in the sensing data in which recognition target data is to be synthesized with the sensing data; generating composite data by synthesizing the recognition target data into the synthesis region, the recognition target data having same or similar characteristics perceived by a human sensory system as the sensing data; obtaining recognition result data by providing the composite data to a model which has been trained using machine learning to recognize a recognition target; making a second determination based on the recognition result data and reference data including at least the synthesis region, the second determination being to determine whether to make a first determination, the first determination being to determine training data for the model based on the composite data; and making the first determination when it is determined in the second determination to make the first determination.

Abstract: Various methods for reducing artifacts in OCT images of an eye are described. In one exemplary method, three dimensional OCT image data of the eye is collected. Motion contrast information is calculated in the OCT image data. A first image and a second image are created from the motion contrast information. The first and the second images depict vasculature information regarding one or more upper portions and one or more deeper portions, respectively. The second image contains artifacts. Using an inverse calculation, a third image is determined that can be mixed with the first image to generate the second image. The third image depicts vasculature regarding the same one or more deeper portions as the second image but has reduced artifacts. A depth dependent correction method is also described that can be used in combination with the inverse problem based method to further reduce artifacts in OCT angiography images.

Abstract: A weakly supervised image semantic segmentation method based on an intra-class discriminator includes: constructing two levels of intra-class discriminators for each image-level class to determine whether pixels belonging to the image class belong to a target foreground or a background, and using weakly supervised data for training; generating a pixel-level image class label based on the two levels of intra-class discriminators, and generating and outputting a semantic segmentation result; and further training an image semantic segmentation module or network by using the label to obtain a final semantic segmentation model for an unlabeled input image. By means of the new method, intra-class image information implied in a feature code is fully mined, foreground and background pixels are accurately distinguished, and performance of a weakly supervised semantic segmentation model is significantly improved under the condition of only relying on an image-level annotation.

Abstract: An image processing device includes a detector, a setting unit, a calculator, an estimator, and a determining unit. The detector sets a three-dimensional object region by detecting a three-dimensional object. The setting unit sets a first image region corresponding to the three-dimensional object region, a second image region including a left end of and partly overlapping the first image region, and a third image region including a right end of and partly overlapping the first image region. The calculator calculates representative values of parallax-related values in pixel columns in the image regions, and calculates an approximate line of the representative values in each of the image regions. The estimator estimates a continuous structure degree, from a slope value of the approximate line of each of the image regions. The determining unit determines whether the three-dimensional object is a vehicle, from the continuous structure degree.

Abstract: Image rotation in an endoscopic hyperspectral imaging system is described. A system includes an emitter for emitting pulses of electromagnetic radiation and an image sensor comprising a pixel array for sensing reflected electromagnetic radiation. The system includes a rotation sensor for detecting an angle of rotation of a lumen relative to a handpiece of an endoscope. The system is such that at least a portion of the pulses of electromagnetic radiation emitted by the emitter comprises electromagnetic radiation having a wavelength from about 513 nm to about 545 nm, from about 565 nm to about 585 nm, or from about 900 nm to about 1000 nm.

Abstract: Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.

Abstract: An embodiment relates to a computer-implemented method for generating a combined tissue-vessel representation. The method includes receiving imaging data of a tissue; receiving imaging data of a vessel; generating a tissue representation based on the imaging data of the tissue; generating a vessel representation based on the imaging data of the vessel; and generating a combined tissue-vessel representation based on the vessel representation and the tissue representation, the vessel representation being overlaid over the tissue representation.

Abstract: The present invention relates generally to the field of computer-based image recognition. More particularly, the invention relates to methods and systems for the identification, and optionally the quantitation of, discrete objects of biological origin such as cells, cytoplasmic structures, parasites, parasite ova, and the like which are typically the subject of microscopic analysis. The invention may be embodied in the form of a method for training a computer to identify a target biological material in a sample. The method may include accessing a plurality of training images, the training images being obtained by light microscopy of one or more samples containing a target biological material and optionally a non-target biological material. The training images are cropped by a human or a computer to produce cropped images, each of which shows predominantly the target biological material.

Abstract: The invention relates to a control device (1) for a vehicle for determining the perceptual load of a visual and dynamic driving scene. The control device is configured to: ?receive a sensor output (101) of a sensor (3), the sensor (3) sensing the visual driving scene, ?extract a set of scene features (102) from the sensor output (101), the set of scene features (102) representing static and/or dynamic information of the visual driving scene, ?determine the perceptual load (104) of the set of extracted scene features (102) based on a predetermined load model (103), the load model (103) being predetermined based on reference video scenes each being labelled with a load value, ?map the perceptual load to the sensed driving and ?determine a spatial and temporal intensity distribution of the perceptual load across the sensed driving scene. The invention further relates to a vehicle, a system and a method.

Abstract: An annotation method and device and a storage medium are provided. The annotation method includes operations as follows. A first probability value that a first sample image is annotated with an Nth tag when the first sample image is annotated with an Mth tag is determined based on first tag information of a first image set. M and N are unequal and are positive integers. The first probability value is added to second tag information of a second sample image annotated with the Mth tag in a second image set.

Abstract: Provided are a method, an apparatus, and a device for identifying human body, including: acquiring a first original picture captured; adjusting a resolution according to the acquired picture to obtain a target picture; processing the target picture based on a preset model for human body feature point detection to determine whether the target picture includes human body information; if the target picture includes the human body information, determining human body area information in the original picture according to the human body information and inputting the human body area information into a filter, enabling that the filter determines target human body area information according to the human body area information; acquiring a next original picture captured; and determining a possible human body area in the next original picture according to the target human body area information, and performing the step of adjusting the resolution according to the possible human body area.

Abstract: Disclosed are systems, methods, and computer program products for tumor lesion identification, segmentation, tracking and analysis, wherein a 3D spatial distribution of the tumor lesions in a target organ forms a unique 3D point structure for a patient.

Abstract: Techniques for removing artefacts, such as RF interference and/or noise, from magnetic resonance data. The techniques include: obtaining input magnetic resonance (MR) data using at least one radio-frequency (RF) coil of a magnetic resonance imaging (MRI) system; and generating an MR image from input MR data at least in part by using a neural network model to suppress at least one artefact in the input MR data.

Abstract: An image processing apparatus includes an extraction portion and a fusion portion. The extraction portion extracts a first object from each of a plurality of pieces of image data that include the first object and a second object, the first object including a handwritten object, the second object including a non-handwritten object. The fusion portion generates a fusion image by fusing a plurality of first objects extracted from the plurality of pieces of image data into the second object that is common to the plurality of pieces of image data.

Abstract: A system configured to reduce false positives when performing human presence detection is provided. In addition to calculating a Human Detection (HD) confidence score during human presence detection, the system may use human keypoint detection (HKD) techniques to calculate a true positive (TP) confidence score and detect false positives based on a combination of the two confidence scores. For example, the device system may generate keypoint data, which indicates a location and maximum confidence value for individual keypoints associated with a human body. The system may input the keypoint data to a model configured to generate the TP confidence score, such as a logistic regression model that is configured to receive numerical values as inputs (e.g., HD confidence score and 17 keypoint confidence values) and generate the TP confidence score. The system then detects false positives using the TP confidence score and may remove corresponding bounding boxes.

Abstract: A mobile device includes a rangefinder to measure ranges to points external to the device; a tracking sensor; and a controller connected with the rangefinder and the tracking sensor, the controller configured to: track successive poses of the mobile device in a frame of reference via the tracking sensor; responsive to a first activation of the rangefinder at a first one of the poses, generate a first position, in the frame of reference, of a first external point based on a first range from the rangefinder and the first pose; responsive to a second activation of the rangefinder at a second one of the poses, generate a second position, in the frame of reference, of a second external point based on a second range from the rangefinder and the second pose; and determine a distance between the first and second external points based on the first and second positions.

Abstract: Provided are a cell image evaluation device, method, and program which are capable of more accurate and high reliable evaluation even though a captured image of each part to be observed within a container deteriorates. The cell image evaluation device includes an image evaluation unit that evaluates a state of a cell included in a captured image obtained by capturing an inside of the container that contains the cell based on the captured image, and a deterioration determination unit that determines whether or not the captured image deteriorates. The image evaluation unit changes an evaluation method of the captured image according to a determination result of the deterioration determination unit.

Abstract: Novel tools and techniques are provided for implementing digital microscopy imaging using deep learning-based segmentation and/or implementing instance segmentation based on partial annotations. In various embodiments, a computing system might receive first and second images, the first image comprising a field of view of a biological sample, while the second image comprises labeling of objects of interest in the biological sample. The computing system might encode, using an encoder, the second image to generate third and fourth encoded images (different from each other) that comprise proximity scores or maps. The computing system might train an AI system to predict objects of interest based at least in part on the third and fourth encoded images. The computing system might generate (using regression) and decode (using a decoder) two or more images based on a new image of a biological sample to predict labeling of objects in the new image.