A Generative Adversarial Network (GAN) can be trained, where the GAN includes an anomaly-removing Generator network configured to modify a medical image to remove a depiction of a biological anomaly and one or more Discriminator networks (each configured to discriminate between real and fake images). The anomaly-removing Generator network can then receive a medical image that depicts a particular biological anomaly (or pre-processed version thereof) and generate a modified image predicted to lack any depiction of the particular biological anomaly. The size of the particular biological anomaly may be estimated based on the modified image and the received image (or pre-processed version thereof).

An independent wearable biomedical imaging system for early tumor detection the system including a physician headset having a graphical display in wireless communication with a patient headset having a left and right camera. The physician headset includes a map template database disposed in the memory storage drive including data specifying anatomical location of a patient tumor using sclera scans of a patient sclera and iris received from the patient headset. The physician can visually access the sclera scans from the patient headset camera and overlay with the map template to compare patient scan biomarkers with the map data. The physician may use the results in indicating strong genotype predisposition to tumors and tumor formation. The system algorithm would continue to amass biodata in the datasets helping the physician to increase accuracy in generating eye reports and statistical probability of tumor as well as genetic marker predisposition of the same.

A method may include obtaining first image data relating to a region of interest (ROI) of a first subject. The first image data corresponding to a first equivalent dose level may be acquired by a first device. The method may also include obtaining a model for denoising relating to the first image data and determining second image data corresponding to an equivalent dose level higher than the first equivalent dose level based on the first image data and the model for denoising. In some embodiments, the method may further include determining information relating to the ROI of the first subject based on the second image data and ecording the information relating to the ROI of the first subject.

An image processing apparatus for evaluating cardiac images and a ventricular status identification method are provided. In the method, a region of interest (ROI) is determined from multiple target images, a variation in grayscale values of multiple pixels in the ROIs of each target image is determined, and one or more representative images are obtained according to the variation in the grayscale values. The target image is related to the pixels within an endocardial contour of a left ventricle. A boundary of the ROI is approximately located at two sides of a bottom of the endocardial contour. The ROI corresponds to a mitral valve. The variation in the grayscale values is related to a motion of the mitral valve. The representative image is for evaluating a status of the left ventricle.

The invention relates to a computer-implemented method (10) for determining the blood volume flow (I.sub.BI) through a portion (90.sub.i, i=1, 2, 3, . . . ) of a blood vessel (88) in an operating region (36) using a fluorophore. A plurality of images (80.sub.1, 80.sub.2, 80.sub.3, 80.sub.4, . . . ) are provided, which are based on fluorescent light in the form of light having wavelengths lying within a fluorescence spectrum of the fluorophore, and which show the portion (90.sub.i) of the blood vessel (88) at different recording times (t.sub.1, t.sub.2, t.sub.3, t.sub.4, . . . ). By processing at least one of the provided images (80.sub.1, 80.sub.2, 80.sub.3, 80.sub.4, . . . ), a diameter (D) and a length (L) of the portion (90.sub.i) of the blood vessel (88) and also a time interval for a propagation of the fluorophore through the portion (90.sub.i) of the blood vessel (88) are determined, which time interval describes a characteristic transit time (τ) for the fluorophore in the portion (90.sub.i) of the blood vessel (88), in which a blood vessel model (M.sub.B.sup.Q) for the portion (90.sub.i) of the blood vessel (88) is specified, which blood vessel model describes the portion (90.sub.i) of the blood vessel (88) as a flow channel (94) having a length (L), having a wall (95) with a wall thickness (d), and having a free cross section Q. A fluid flow model M.sub.F.sup.Q for the blood vessel model (M.sub.B.sup.Q) is assumed, which fluid flow model describes a local flow velocity (122) at different positions over the free cross section Q of the flow channel (94) in the blood vessel model (M.sub.B.sup.Q), and a fluorescent light model M.sub.L.sup.Q is assumed, which describes a spatial probability density for the intensity of the remitted light at different positions over the free cross section Q of the flow channel (94) in the blood vessel model (M.sub.B.sup.Q), which light is emitted by a fluid, which is mixed with fluorophore and flows through the free cross section Q of the flow channel (94) in the blood vessel model (M.sub.B.sup.Q), when said fluid is irradiated with fluorescence excitation light. The blood volume flow (I.sub.BI) is determined as a fluid flow guided through the flow channel (94) in the blood vessel model (M.sub.B.sup.Q), which fluid flow is calculated from the length (L) and the diameter (D) of the portion (90.sub.i) of the blood vessel (88) and from the characteristic transit time (τ) for the fluorophore in t

The invention relates to a method of identifying a biomarker in a tissue sample. The method comprises receiving an acquired image depicting a tissue sample, the pixel intensity values of the acquired image correlating with an autofluorescence signal or of an X-ray induced signal or a signal of a non-biomarker specific stain or a signal of a first biomarker specific stain adapted to selectively stain a first biomarker. The acquired image is input into a trained machine learning logic—MLL which automatically transforms the acquired image into an output image highlighting tissue regions predicted to comprise a second biomarker.

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.

A system and method for quantifying Alzheimer's disease (AD) risk using one or more interferometric micro-Doppler radars (IMDRs) and deep learning artificial intelligence to distinguish between cognitively unimpaired individuals and persons with AD based on gait analysis. The system utilizes IMDR to capture signals from both radial and transversal movement in three-dimensional space to further increase the accuracy for human gait estimation. New deep learning technologies are designed to complement traditional machine learning involving separate feature extraction followed-up with classification to process radar signature from different views including side, front, depth, limbs, and whole body where some motion patterns are not easily describable. The disclosed cross-talk deep model is the first to apply deep learning to learn IMDR signatures from two perpendicular directions jointly from both healthy and unhealthy individuals. Decision fusion is used to integrate classification results from feature-based classifier and deep learning AI to reach optimal decision.

A deep learning model and dimensionality reduction are applied to each of a plurality of records of physiological information to derive a plurality of feature vectors. A similarities algorithm is applied to the plurality of feature vectors to form a plurality of clusters, each including a set of feature vectors. An output comprising information that enables a display of one or more of the plurality of clusters is provided, and a mechanism for selecting at least one feature vector within a selected cluster of the plurality of clusters is enabled. Upon selection of a feature vector, an output comprising information that enables a display of the record of physiological information corresponding to the selected feature vector is provided, and a mechanism for assigning a label to the displayed record is enabled. The assigned label is then automatically assigned to the records corresponding to the remaining feature vectors in the selected cluster.

A standard image is extracted from a still image group or a moving image associated with medical test report data stored in a database, using the medical test report data. A frame image group is created from the still image group or the moving image that configures the standard image, a learning candidate image data set is extracted from the frame image group based on the standard image, and training data is sorted out from the learning candidate data set. Learning is performed using the training data which is sorted out.