Deep learning methods and systems for detecting biomarkers within optical coherence tomography volumes using such deep learning methods and systems are provided. Embodiments predict the presence or absence of clinically useful biomarkers in OCT images using deep neural networks. The lack of available training data for canonical deep learning approaches is overcome in embodiments by leveraging a large external dataset consisting of foveal scans using transfer learning. Embodiments represent the three-dimensional OCT volume by “tiling” each slice into a single two dimensional image, and adding an additional component to encourage the network to consider local spatial structure. Methods and systems, according to embodiments are able to identify the presence or absence of AMD-related biomarkers on par with clinicians. Beyond identifying biomarkers, additional models could be trained, according to embodiments, to predict the progression of these biomarkers over time.

A program and the like that make a catheter system relatively easy to use. The program including a non-transitory computer-readable medium (CRM) storing computer program code executed by a computer processor that executes a process comprising: acquiring a tomographic image generated using a diagnostic imaging catheter inserted into a lumen organ; and inputting the acquired tomographic image to a first model configured to output types of a plurality of objects included in the tomographic image and ranges of the respective objects in association with each other when the tomographic image is input, and outputting the types and ranges of the objects output from the first model.

An image processing apparatus selects one or a plurality of examinations to which a medical image belongs, determines image processing candidate examinations based on the selected one or plurality of examinations, displays medical images belonging to the determined image processing candidate examinations on a display unit, and executes image processing using, of the displayed medical images, a plurality of medical images selected by a user, wherein, when the one examination is selected, the selected one examination and one or a plurality of examinations obtained by a search based on the selected one examination are determined as the image processing candidate examinations, and when the plurality of examinations are selected, in the determining, the selected plurality of examinations are determined as the image processing candidate examinations.

An image processing method performed by a processor and including detecting positions of plural vortex veins in a fundus image of an examined eye, and computing a center of distribution of the plural detected vortex vein positions.

Disclosed is an intraluminal imaging system, including an intraluminal imaging catheter or guidewire configured to be positioned within an anatomy of a patient, and a processor circuit in communication with the imaging catheter or guidewire, wherein the processor circuit is configured to receive a plurality of cross-sectional images of the anatomy from the imaging catheter or guidewire. The processor is further configured to compute, using image processing of at least one of the cross-sectional images, a value of the anatomy, estimate a cross-sectional shape of the anatomy to be circular, calculate a diameter of the anatomy based on the computed value and the estimated circular shape, and output the diameter of the anatomy to a display.

A method of processing a sequence of images of a retina acquired by an ophthalmic device to generate retinal position tracking information indicative of retina movement during acquisition. The method includes (i) receiving one or more images of the retina; (ii) calculating a cross-correlation between a reference image and an image based on the received image(s) to acquire an offset between the image and reference image; and repeating processes (i) and (ii) to acquire, as the tracking information, respective offsets for images that are based on the respective received image(s). Another step includes modifying the reference image during the repeating, by determining a measure of similarity between correspondingly located regions of pixels in two or more received images and accentuating features in the reference image representing structures of the imaged retina in relation to other features in the reference image based on the determined measure of similarity.

The present invention relates to accurately determining a contour of a depolarizing region.

An image processing apparatus extracts a depolarizing region in a polarization-sensitive tomographic image of a subject's eye, and detects, in a tomographic intensity image of the subject's eye, a region corresponding to the extracted depolarizing region. The tomographic intensity image corresponds to the polarization-sensitive tomographic image,

The present technology relates to an image processing device, a method of image processing, and a surgical microscope that can detect and report a dangerous condition on the basis of a tomographic image during eye surgery. An image processing device includes: a dangerous condition detection unit configured to detect a dangerous condition on the basis of a tomographic image of an eye acquired during surgery of the eye; and a control information generation unit configured to generate and output control information used to manage the detected dangerous condition. The present technology is applicable to, for example, a surgical system used for eye surgery or other surgical procedures.

Embodiments discussed herein facilitate segmentation of vascular plaque, training a deep learning model to segment vascular plaque, and/or informing clinical decision-making based on segmented vascular plaque. One example embodiment accessing vascular imaging data for a patient, wherein the vascular imaging data comprises a volume of interest; pre-process the vascular imaging data to generate pre-processed vascular imaging data; provide the pre-processed vascular imaging data to a deep learning model trained to segment a lumen and a vascular plaque; and obtain segmented vascular imaging data from the deep learning model, wherein the segmented vascular imaging data comprises a segmented lumen and a segmented vascular plaque in the volume of interest.

Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.