There is provided a method of training a machine learning model, comprising: for each set of sample medical images depicting calcification within a target anatomical structure wherein each set includes non-contrast medical image(s) and contrast enhanced medical image(s), correlating between calcifications depicted in the target anatomical structure of the contrast enhanced image(s) with corresponding calcifications depicted in the target anatomical structure of the non-contrast medical image(s), computing calcification parameter(s) for calcification depicted in the respective target anatomical structure, labelling each contrast enhanced medical image with the calcification parameter(s), and training the machine learning model on a training dataset that includes the contrast enhanced medical images of the sets, each labelled with ground truth label of a respective calcification parameter(s), for generating an outcome indicative of a target calcification parameter(s) for calcification depicted in the target anatomical structure of a target contrast enhanced medical image provided as input.

Methods and systems for identifying optimized ablation targets for treating and preventing arrhythmias sustained by reentrant circuits are described. The methods comprise receiving at least one mesh generated from one or more images of a patient's heart, receiving activation data generated from one or more simulations of electrical-signal propagation over the at least one mesh, generating at least one flow graph based on the activation data and the at least one mesh, and applying a max-flow min-cut algorithm to the at least one flow graph to determine at least one of a number, one or more dimensions, and one or more locations of one or more ablation targets. Non-transitory computer-readable media storing a set of instructions for treating and preventing arrhythmias sustained by reentrant circuits are also described.

There is disclosed herein examples of systems and methods of processing captured heart sounds with frequency-dependent normalization. Based on an amount of attenuation of a first heart sound, a second heart sound can be normalized by modifying portions of the second heart sound by amounts determined based on frequencies of the portions. Accordingly, the systems and methods disclosed herein can result in different amounts of modification of different portions of the second heart sound based on the different frequencies of the portions.

A diagnostic support program that is possible to display a movement of an organ is provided.

A diagnostic support program that analyzes images of an organ of a human and displays analysis results, the program causing a computer to execute a process comprising: processing of acquiring a plurality of frame images, processing of calculating a cyclic change that characterizes a state of an organ between each of the frame images, processing of Fourier-transforming the cyclic change that characterizes the state of the organ, processing of extracting a spectrum in a fixed band including a spectrum corresponding to a frequency of a movement of an organ out of a spectrum obtained after the Fourier-transforming, processing of performing inverse Fourier transform on the spectrum extracted from the fixed band, and processing of outputting each of the images after performing the inverse Fourier transform, is provided.

A non-transitory computer-readable recording medium stores therein a calculation program that causes a computer to execute a process including acquiring a first distributed representation of a partial image corresponding to a specific site of an object to be examined included in each of a plurality of images, by executing machine learning performed by an autoencoder using the partial image of an area corresponding to the specific site, for each of one or more specific sites, and acquiring a second distributed representation of the plurality of images, based on the first distributed representation and a result of machine learning performed by the autoencoder, using the plurality of images, wherein abnormality determination on the object to be examined included in an image to be determined is executed, based on the first distributed representation and the second distributed representation.

A non-transitory computer-readable recording medium has stored therein an evaluating program for causing a computer to execute a process including: specifying a wall of an inspection target in two or more moving images being obtained by photographing two types of cross sections of the inspection target, the two types of cross sections being orthogonal to each other; evaluating photographing quality of each of a plurality of first divisional regions obtained by dividing a region corresponding to the wall specified in a first image related to a first cross section among the two or more moving images; and evaluating photographing quality of each of a plurality of second divisional regions obtained by dividing a region corresponding to the wall specified in a second image related to a second cross section among the two or more moving images, the second cross section being different from the first cross section.

A high contrast instrument, such as a radiopaque portion, can be captured and/or viewed in an image that is acquired with an imaging system, such as with a fluoroscopic imaging system. A statistical model can be used to assist in identifying a possible or probable location of a target. A user may move the instrument coil to the statistically probable location of the target to, for example, perform a procedure or carry out a task.

A system for simultaneously detecting audio-characteristics within a body over multiple body surface locations comprising a coherent light source directing at least one coherent light beam toward the body surface locations, an imager acquiring a plurality of defocused images, each is of reflections of the coherent light beam from the body surface locations. Each image includes at least one speckle pattern, each corresponding to a respective coherent light beam and further associated with a time-tag. A processor, coupled with the imager, determines in-image displacements over time of each of a plurality of regional speckle patterns according to said acquired images. Each one of the regional speckle patterns is at least a portion of a respective speckle pattern. Each regional speckle pattern is associated with a respective different body surface location. The processor determines the audio-characteristics according to the in-image displacements over time of the regional speckle patterns.

Methods, apparatus, and systems are provided for facilitating the navigation of a catheter between first and second locations within a subject based on display of serial images corresponding to positions of the catheter at successive incremental times. Image production includes sensing catheter positions to produce location data for each time increment. For each position P.sub.i, the corresponding location data is processed to respectively produce an image I.sub.i reflecting the position of the catheter at a time T.sub.i. Each image I.sub.i is successively displayed at a time equal to T.sub.i+d, where d is an image processing visualization delay. Upon a condition that the catheter is displaced to a selected interim location between the first and second locations, the processing of the location data is switched from being performed by a first process associated with a first visualization delay to a second process associated with a second different visualization delay.

The present disclosure relates to a method for three-dimensionally modeling an organ through image segmentation. The three-dimensional modeling of an organ includes the operations of: receiving one or more pieces of medical image data for a specific bodily organ of a target object; setting a region of interest with respect to the bodily organ based on the one or more pieces of medical image data; forming one or more blocks corresponding to the region of interest, wherein the blocks include a portion of the bodily organ corresponding to the regions of interest; setting a segment algorithm for each of the blocks; generating first image data respectively performing 3D modeling of portions contained in the blocks based on algorithms set to the blocks; and merging the first image data, and generating a three-dimensional section image data with respect to the entire bodily organ.