The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, perform computational fluid dynamics analysis, facilitate assessment of risk of heart disease and coronary artery disease, enhance drug development, determine a CAD risk factor goal, provide atherosclerosis and vascular morphology characterization, and determine indication of myocardial risk, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.

Embodiments of the disclosure provide methods and systems for representation learning from a biomedical image with a sparse convolution. The exemplary system may include a communication interface configured to receive the biomedical image acquired by an image acquisition device. The system may further include at least one processor, configured to extract a structure of interest from the biomedical image. The at least one processor is also configured to generate sparse data representing the structure of interest and input features corresponding to the sparse data. The at least one processor is further configured to apply a sparse-convolution-based model to the biomedical image, the sparse data, and the input features to generate a biomedical processing result for the biomedical image. The sparse-convolution-based model performs one or more neural network operations including the sparse convolution on the sparse data and the input features.

An image display method executed by a processor comprises displaying a screen including a two-dimensional fundus image of an examined eye and a three-dimensional eyeball image of the examined eye, finding a second region in the three-dimensional eyeball image that corresponds to a first region specified in the two-dimensional fundus image, and displaying a mark indicating the second region in the three-dimensional eyeball image.

Various methods for the detection and enhanced visualization of a particular structure or pathology of interest in a human eye are discussed in the present disclosure. An example method to visualize a given pathology (e.g., CNV) in an eye includes collecting optical coherence tomography (OCT) image data of the eye from an OCT system. The OCT image data is segmented to identify two or more retinal layer boundaries located in the eye. The two or more retinal layer boundaries are located at different depth locations in the eye. One of the identified layer boundaries is moved and reshaped to optimize visualization of the pathology located between the identified layer boundaries. The optimized visualization is displayed or stored or for a further analysis thereof.

A method for processing an intravascular image including a plurality of image frames acquired during a pullback of an imaging catheter inserted into a vessel. The method includes obtaining positions of lumen borders detected in the intravascular image and positions of stent-struts detected in the intravascular image. Determining, at different positions in a range, a stent expansion value of the stent implanted in the vessel, based on the first information and the second information, wherein each image frame from image frames in which stent-struts are detected corresponds to a different position along the range. The method may also include displaying an image including positions of lumen borders and positions of the stent-struts detected and a first indicator indicating a level along the range, of the stent expansion value, with the image.

A computer-implemented method of searching for a region indicative of a pathology in an image of a portion of an eye acquired by an ocular imaging system, the method comprising: receiving image data defining the image; searching for the region in the image by processing the received image data using a learning algorithm; and in case a region in the image that is indicative of the pathology is found: determining a location of the region in the image; generating an instruction for an eye measurement apparatus to perform a measurement on the portion of the eye to generate measurement data, using a reference point based on the determined location for setting a location of the measurement on the portion of the eye; and receiving the measurement data from the eye measurement apparatus.

A 3-D imaging system including a computer determining a plurality of coherence factors measuring an intensity contrast between a first intensity of a first region of an interference comprising constructive interference between a sample wavefront and a reference wavefront, and a second intensity of a second region of the interference comprising destructive interference between the sample wavefront and the reference wavefront, wherein the interference between a reference wavefront and a reflection from different locations on a surface of an object. From the coherence factors, the computer determines height data comprising heights of the surface with respect to an x-y plane perpendicular to the heights and as a function of the locations in the x-y plane. The height data is useful for generating a three dimensional topological image of the surface.

The invention relates to a computer-assisted method for position determination for an intraocular lens supported by machine learning. The method comprises providing a scan result for an eye. The scan result here represents an image of an anatomical structure of the eye. The method further comprises use of a trained machine learning system for the direct determination of a final location of an intraocular lens to be fitted, wherein digital data of the scan of the eye is used as the input data for the machine learning system.

The invention relates to an assembly (10) comprising an OCT device (20) for scanning an object region volume (22) arranged in an object region (18) using an OCT scanning beam (21), an object (24) with a section, which can be arranged in the object region (18) and which can be located in the object region volume (22) by means of the OCT device (20), in the object region volume (22), and a calculating unit (60) which is connected to the OCT device (20) and contains a computer program for ascertaining a 3D reconstruction of the object region volume (22) and for ascertaining the position of the section of the object (24) in the object region volume (22) by processing OCT scanning information obtained by scanning the object region volume (22) using the OCT device (20). According to the invention, the computer program has a calculation routine for ascertaining a target area (90) in the 3D reconstruction of the object region volume (22), said calculation routine determining a reference variable for the object (24) relative to the target area (90). The object (24) is designed as a surgical instrument which has a capillary with an opening for discharging a medium. The calculation routine of the computer program is used to ascertain an actual value of the volume of the medium discharged through the opening of the capillary in the target area by comparing data of the target area in the 3D reconstruction of the object region volume (22) and/or by comparing scanning information of the target area obtained by scanning the object region volume (22) using the OCT device (20) prior to and while discharging the medium. The invention also relates to a computer program and to a method for determining the volume of a medium discharged in an object region (18) through an opening by means of a surgical instrument with a capillary.

A single-shot differential phase contrast quantitative phase imaging method based on color multiplexing illumination. A color multiplexing illumination solution is used to realize single-shot differential phase contrast quantitative phase imaging. In the single-shot color multiplexing illumination solution, three illumination wavelengths of red, green, and blue are used to simultaneously illuminate a sample, and the information of the sample in multiple directions is converted into intensity information on different channels of a color image. By performing channel separation on this color image, the information about the sample at different spatial frequencies can be obtained. Such a color multiplexing illumination solution requires only one acquired image, thus enhancing the transfer response of the phase transfer function of single-shot differential phase contrast imaging in the entire frequency range, and achieving real-time dynamic quantitative phase imaging with a high contrast, a high resolution, and a high stability. In addition, an alternate illumination strategy is provided, so that a completely isotropic imaging resolution at the limit acquisition speed of the camera can be achieved.