Automated determination of muscle mass from images can be carried by performing a thresholding process to an image file to generate a contrasted image, and segmenting pixels of the contrasted image into bone and not bone. The system can distinguish muscle from organ for the pixels segmented as not bone by determining a location of a rib cage of the patient using the pixels segmented as bone, and removing pixels segmented as not bone that are located within the location of the rib cage. The system can calculate a volume of muscle based on remaining pixels segmented as not bone; calculate a total muscle mass based on the volume of muscle; and provide the total muscle mass of the patient. The total muscle mass of the patient can then be used for applications including calculating a glomerular filtration rate.

An ultrasound diagnostic apparatus includes an ultrasound probe (2) that scans a subject with an ultrasound beam, an image acquisition unit (8) that acquires ultrasound images of a plurality of frames corresponding to a plurality of different tomographic planes in the subject using the ultrasound probe (2), an image memory (9) that keeps the acquired ultrasound images of the plurality of frames, a bladder extraction unit (10) that extracts a bladder region from each of the ultrasound images of the plurality of frames, a feature value calculation unit (11) that calculates a feature value regarding the bladder region extracted in each of the ultrasound images of the plurality of frames, and a scanning success/failure determination unit (12) that analyzes change in feature value between frames continuous in time series and determines whether or not scanning of a bladder of the subject with an ultrasound beam is successful.

Generation of synthetic three-dimensional imaging from partial depth maps is provided. In various embodiments, an image of an anatomical structure is received from a camera. A depth map corresponding to the image is received from a depth sensor that may be a part of the camera or separate from the camera. A preliminary point cloud corresponding to the anatomical structure is generated based on the depth map and the image. The preliminary point cloud is registered with a model of the anatomical structure. An augmented point cloud is generated from the preliminary point cloud and the model. The augmented point cloud is rotated in space. The augmented point cloud is rendered. The rendered augmented point cloud is displayed to a user.

A system for monitoring organ health during treatment for cancer and the like makes use of physiological imaging of the kind used for treatment monitoring and organ-specific processing to provide a comprehensive assessment of treatment side-effects.

The present disclosure relates to an image processing method. The method may include: obtaining image data; reconstructing an image based on the image data, the image including one or more first edges; obtaining a model, the model including one or more second edges corresponding to the one or more first edges; matching the model and the image; and adjusting the one or more second edges of the model based on the one or more first edges.

A computer-implemented method is provided for classifying a malignancy risk of a kidney, in particular a human kidney. Imaging data of an anatomy of a subject patient at least partially includes a representation of a kidney of the subject patient. A first neural network segments at least one region of the kidney representation based on the imaging data. A second neural network detects one or more suspected lesions of the segmented kidney representation. A third neural network classifies the detected suspected lesion with a malignancy risk. The third neural network is a deep profiler.

A method to suppresses speckle noise in medical ultrasound images includes ultrasound envelope image matrix A formed from the medical ultrasound images and segmented into overlapping segments, to form a sub-matrix B for each overlapping segment. A Hermitian covariance matrix C is formulated from column vectors Z. A global covariance matrix G is formed by averaging the C. A Lanczos decomposition is applied to the G to generate an orthonormal vector matrix composed of orthonormal vectors. A tridiagonal matrix H is generated. The orthonormal vectors are sorted based on magnitude of each column. An orthogonal projection matrix P.sub.orth is formed based on the orthonormal vectors. An estimated vector signal {circumflex over (Z)} is obtained by projecting Z by P.sub.orth. An estimated despeckled segment is formed from the {circumflex over (Z)}. An estimated despeckled ultrasound image is reconstructed by averaging each pixel by the number of segment updates.

Systems and methods for processing electronic images from a medical device comprise receiving an image frame from the medical device, and determining a first color channel and a second color channel in the image frame. A location of an electromagnetic beam halo may be identified by comparing the first color channel and second color channel. Edges of an electromagnetic beam may be determined based on the electromagnetic beam halo, and size metrics of the electromagnetic beam may be determined based on the edges of the electromagnetic beam. A visual indicator on the image frame may be displayed based on the size metrics of the electromagnetic beam.

In a method for generating a surrogate marker based on medical image data mapping an image region, the medical image data is detected using a first interface, a first subregion of the image region is selected by segmenting a first structure included in the image region, a first property of the first subregion is extracted, the surrogate marker is determined based on the first property, and the surrogate marker is provided using a second interface.

A method for image segmentation comprises receiving volumetric image data for an anatomical region and generating a first volumetric patch from the volumetric image data. The method also comprises generating a second volumetric patch from the first volumetric patch by weighting a plurality of volumetric units in the first volumetric patch and receiving the second volumetric patch as an input to a convolutional neural network. The method also comprises conducting a down-sampling filter process and conducting an up-sampling filter process within the convolutional neural network.