Abstract: Systems and methods are disclosed for receiving digital images of a pathology specimen from a patient, the pathology specimen comprising tumor tissue, the one or more digital images being associated with data about a plurality of biomarkers in the tumor tissue and data about a surrounding invasive margin around the tumor tissue; identifying the tumor tissue and the surrounding invasive margin region to be analyzed for each of the one or more digital images; generating, using a machine learning model on the one or more digital images, at least one inference of a presence of the plurality of biomarkers in the tumor tissue and the surrounding invasive margin region; determining a spatial relationship of each of the plurality of biomarkers identified in the tumor tissue and the surrounding invasive margin region to themselves and to other cell types; and determining a prediction for a treatment outcome and/or at least one treatment recommendation for the patient.

Abstract: A method of analysing data from an angiographic scan that provides three-dimensional information about blood vessels in a patient's brain, the method comprising the steps of: processing the data (26) to produce a three-dimensional image; extracting the system of blood vessels inside the skull, so as to obtain a vessel mask (28); skeletonising (30) the vessel mask with a thinning algorithm to produce a skeleton mask performing a central plane extraction; analysing (32) the skeleton mask to identify voxels that have more than two neighbours, indicating a fork, bifurcation or branch; detecting the most proximal location of each of the three main supplying arteries of the head in the skeleton mask to identify starting positions; and then starting from each starting position in turn, and walking along the line representing the corresponding blood vessel to detect (34) a plurality of anatomical markers within the network of blood vessels.

Abstract: Provided are a diagnostic device and a diagnostic method for predicting fractional flow reserve (FFR) and diagnosing coronary artery lesions via a coronary angiography-based machine learning algorithm. A deep learning-based diagnostic method for diagnosing an ischemic lesion includes: obtaining an angiography image of a patient's blood vessel; extracting a region of interest (ROI) from the angiography image; acquiring diameter information of the blood vessel in the ROI; extracting morphological features of the blood vessel based on the diameter information; and obtaining a predictive FFR value by inputting the morphological features to an artificial intelligence (AI) model and determining whether a lesion is an ischemic lesion.

Abstract: The present invention concerns identifying matching tissue objects in two sections of a tissue block, as imaged using a microscope, for the purpose of mapping the biomarker-specific staining in one section onto the other section. The invention is useful because, in many workflows, it is not possible to add a sufficient number of different biomarker-specific stains to a single slide. By staining instead multiple slides, and mapping the staining data obtained across the slides, one obtains a data set that is similar to what one would be able to obtain by staining a single slide with all those stains. The invention first identifies a set of obviously correct matches, then propagates from those matches, using a priority queue driven process, to optimally match up all fibers in the two sections. The matching is based on the shape and neighborhood configuration of each tissue object.

Abstract: The present disclosure provides a method of volumetric imaging of a sample. The method comprises providing a plurality of depth images of a region of interest of the sample using a volumetric imaging system. The region of interest is below a surface area of interest of the sample. Each depth image is associated with a layer or slice of the region of interest and the plurality of depth images together forming a volumetric image of the region of interest. The method further comprises providing a surface image of the surface area of interest of the sample and identifying a surface image property of a surface feature of the surface area of interest. The method also comprises processing the plurality of depth images of the region of interest using the surface image property of the surface feature to improve a property of the depth images of the region of interest.

Abstract: Systems and methods are disclosed for performing probabilistic segmentation in anatomical image analysis, using a computer system. One method includes receiving a plurality of images of an anatomical structure; receiving one or more geometric labels of the anatomical structure; generating a parameterized representation of the anatomical structure based on the one or more geometric labels and the received plurality of images; mapping a region of the parameterized representation to a geometric parameter of the anatomical structure; receiving an image of a patient's anatomy; and generating a probability distribution for a patient-specific segmentation boundary of the patient's anatomy, based on the mapping of the region of the parameterized representation of the anatomical structure to the geometric parameter of the anatomical structure.

Abstract: Techniques are provided for determining a cell count within a whole slide pathology image. The image is segmented using a global threshold value to define a tissue area. A plurality of patches comprising the tissue area are selected. Stain intensity vectors are determined within the plurality of patches to generate a stain intensity image. The stain intensity image is iteratively segmented to generate a cell mask using a local threshold value that is and gradually reduced after each iteration. A chamfer distance transform is applied to the cell mask to generate a distance map. Cell seeds are determined on the distance map. Cell segments are determined using a watershed transformation, and a whole cell count is calculated for the plurality of patches based on the cell segments. A client device may be configured for real-time cell counting based on the whole cell count.

Abstract: Disclosed herein are methods for simulating the results of a visual field (VF) test using an optical coherence tomography (OCT) system. The disclosed methods may utilize structural information extracted from OCT image datasets, such as thickness measurements, or may utilize functional information, such as blood perfusion measurements, extracted from OCT angiography (OCTA) image datasets. Other embodiments may be described and claimed.

Abstract: The present disclosure relates to medical instruments, and in particular to a method and device for state display during a ventilation process, a ventilator, a computer device, and a computer-readable storage medium. A method for state display during a ventilation process can include determining, by a processor, a monitoring parameter regarding a user. The method can also include displaying a first image corresponding to the monitoring parameter according to a pre-set correlation.

Abstract: Methods, systems, and computer programs are presented for adding new features to a network service. An example method includes accessing an image from a user device to determine a salient object count of a plurality of objects in the image. A salient object count of the plurality of objects in the image is determined. An indicator of the salient object count of the plurality of objects in the image is caused to be displayed on the user device.

Abstract: An automated screening system using retinal imaging to identify individuals with early-stage Age-related Macular Degeneration (AMD) and identify individuals at risk for developing late AMD.

Abstract: In certain embodiments, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set based on one or more logos or other graphics. In some embodiments, graphics information associated with a logo or graphic (e.g., to be recognized via a recognition model) may be obtained. Media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. In some embodiments, the media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the media items). The recognition model may be updated based on (i) the generated predictions and (ii) corresponding reference indications (related to recognition of the logo for the media items).

Abstract: A non-label diagnosis apparatus for a hematologic malignancy may include a 3-D refractive index cell imaging unit configured to generate a 3-D refractive index slide image of a blood smear specimen by capturing a 3-D refractive index image in the form of the blood smear specimen in which blood (including a bone-marrow or other body fluids) of a patient has been smeared on a slide glass, an ROI detection unit configured to sample a suspected cell segment in the blood smear specimen based on the 3-D refractive index slide image and to determine, as ROI patches, cells determined as abnormal cells, and a diagnosis unit configured to determine a sub-classification of a cancer cell corresponding to each of the ROI patches using a cancer cell sub-classification determination model constructed based on a deep learning algorithm and to generate hematologic malignancy diagnosis results by gathering sub-classification results of the ROI patches.

Abstract: Aspects of the invention include ultrasound systems that suppress grating lobe artifacts arising due to high frequency operation of an array transducer probe which is operated at a frequency higher than its pitch limitation.

Abstract: An information processing apparatus according to the invention includes: an acquisition unit that acquires a two-dimensional image of a person and a three-dimensional registered image of a registrant; and a generation unit that, when superimposing the two-dimensional image and the three-dimensional registered image to generate a composite image, performs an editing process for changing an appearance of the person or the registrant for at least one of the two-dimensional image, the three-dimensional registered image, and the composite image.

Abstract: A neural network is trained to segment interferogram images. A first plurality of interferograms are obtained, where each interferograms corresponds to data acquired by an OCT system using a first scan pattern, annotating each of the plurality of interferograms to indicate a tissue structure of a retina, training a neural network using the plurality of interferograms and the annotations, inputting a second plurality of interferograms corresponding to data acquired by an OCT system using a second scan pattern and obtaining an output of the trained neural network indicating the tissue structure of the retina that was scanned using the second scan pattern. The system and methods may instead receive a plurality of A-scans and output a segmented image corresponding to a plurality of locations along an OCT scan pattern.

Abstract: In one embodiment, a fluorescence histo-tomography (FHT) system is disclosed. The FHT system includes an imaging housing, a fluorescence camera located within the housing, a white light camera located within the imaging housing, and a fluorescence light source located within the imaging housing. The FHT system further includes a support mount configured to support the imaging housing within a chamber of a slicing apparatus such that the cameras and fluorescence light source are aimed towards a block face of a tissue specimen retained within the chamber.

Abstract: A method and a device of extracting a label in a medical image are provided. The method includes: performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image; determining at least one target area defined by the edge information; performing a fitting process on the at least one target area, to obtain a fitting area; and extracting the label in the medical image by selecting, from the fitting areas, at least one target fitting area matching a preset condition, wherein the preset condition is set based on a characteristic of the fitting area.

Abstract: A method for dynamically evaluating a tear fluid layer using an interference fringe image of the tear fluid layer composed of a plurality of consecutive frames, and includes: an image creation step of creating at least one break detection image of a first break detection image, a second break detection image, a third break detection image, and a fourth break detection image, which are images for detecting a breaking site of the tear fluid layer; a determination step of determining whether the break detection image created by the image creation step corresponds to a predetermined breakup pattern; a tally step of tallying the determination results determined by the determination step; and an evaluation step of evaluating, on the basis of a tallied result by the tally step, a breakup pattern of the interference fringe image of the tear fluid layer.

Abstract: Introduced here are diagnostic platforms able to optimize computer-aided diagnostic (CADx) models by simulating the optical performance of an imaging device based on its mechanical components. For example, a diagnostic platform may acquire a source image associated with a confirmed diagnosis of a medical condition, simulate optical performance based on design data corresponding to a virtual prototype of the imaging device, generate a training image by altering the source image based on the optical performance, apply a diagnostic model to the training image, and then determine whether the performance of the diagnostic model meets a specified performance threshold. If the diagnostic model fails to meet the specified performance threshold, the diagnostic platform can automatically optimize the diagnostic model for the imaging device by altering its underlying algorithm(s).