A system and method for automatically estimating a hepatorenal index (HRI) from ultrasound images s provided. The method includes acquiring a sequence of ultrasound image data until a desired ultrasound image view is obtained. The method includes segmenting, a liver and a renal cortex in the obtained ultrasound image view. The method includes identifying valid samples in the liver and the renal cortex in the obtained ultrasound image view by excluding invalid samples. The method includes automatically positioning a liver region of interest and a renal cortex region of interest in the obtained ultrasound image view based on the valid samples and at least one criterion. The method includes determining an HRI and causing a display system to present the HRI.

Methods and systems are provided for segmenting and/or classifying images using convolutional neural networks (CNNs). In one embodiment, a method comprises, receiving an image having a first size, downsampling the image to produce a downsampled image of a pre-determined size, wherein the pre-determined size is less than the first size, feeding the downsampled image to a CNN, wherein a first convolutional layer of the CNN comprises a first plurality of convolutional filters, each of the first plurality of convolutional filters having a receptive field size larger than a threshold receptive field size, identifying one or more anatomical structures of the downsampled image using the first plurality of convolutional filters; and mapping the one or more anatomical structures to a segmentation map or image classification using one or more subsequent layers of the CNN. In this way, a number of encoding layers of the trained CNN may be substantially reduced.

The present invention relates to image analysis of pathology images. In order to improve reliability in image analysis of pathology images, a method is provided for providing support in identifying at least one feature of a tissue sample in a microscopic image. The method comprises the steps of providing a first image of a first microscopy 5 modality representing an area of the tissue sample, providing a second image of a second microscopy modality representing the said area of the tissue sample, generating a first high intensity image by applying a first high intensity filter to the first image or a first low intensity image by applying a first low intensity filter to the first image to obtain first information of the at least one feature, generating a second high intensity image by applying 10 a second high intensity filter to the second image or a second low intensity image by applying a second low intensity filter to the second image to obtain second information of the at least one feature, calculating a correlation of an image pair comprising one of the first high intensity image and the first low intensity image and one of the second high intensity image and the second low intensity image for correlating the first information and the second 15 information of the at least one feature, and outputting the calculated correlation for providing support in identifying the at least one feature of the tissue sample.

Disclosed in embodiments of the present application are a method and a product for AI processing of tumor based on VRDS 4D medical images, which is applied to medical imaging apparatuses, and the method includes: determining a bitmap BMP data source according to a plurality of scanned images associated with a target organ of a target user, generating target medical image data according to the BMP data source; determining abnormal data in target medical image data; determining the attribute information of a tumor of the target user according to the abnormal data; performing 4D medical imaging according to the target medical image data, and outputting the attribute information of the tumor. The embodiment of this application is facilitated to improve the accuracy and efficiency of tumor recognition.

A method for identifying a liver in a CT image of a patient is provided. The method includes applying a liver model to the CT image. The method further includes extracting an internal liver region and an external liver region from the CT image based on the applied liver model. The method also includes performing a graph cut algorithm on the CT image based on the internal liver region and the external liver region to produce a liver image. The performing of the graph cut algorithm on the CT image to produce the liver image may be further based on an internal heart and/or kidney region and an external heart and/or kidney region. A non-transitory computer-readable storage medium encoded with a program is provided.

A system for image segmentation is provided. The system may obtain a target image including an ROI, and segment a preliminary region representative of the ROI from the target image using a first ROI segmentation model corresponding to a first image resolution. The system may segment a target region representative of the ROI from the preliminary region using a second ROI segmentation model corresponding to a second image resolution. At least one model of the first and second ROI segmentation models may at least include a first convolutional layer and a second convolutional layer downstream to the first convolutional layer. A count of input channels of the first convolutional layer may be greater than a count of output channels of the first convolutional layer, and a count of input channels of the second convolutional layer may be smaller than a count of output channels of the second convolutional layer.

A method comprises obtaining an endoscope; obtaining a needle; inserting the endoscope into the needle to obtain a system; inserting the system into an animal body; and distinguishing components of the animal body using the endoscope and while the system remains in the animal body. A system comprises a needle; and an endoscope inserted into the needle and configured to: store a convolutional neural network (CNN); distinguish among a cortex of a kidney of an animal body, a medulla of the kidney, and a calyx of the kidney using the CNN; and distinguish between vascular tissue and non-vascular tissue in the animal body using the CNN.

A method of quantifying changes in a visceral organ comprises acquiring first (310) and second (410) medical scans of a visceral organ at first and second timepoints. At least part of the visceral organ in the first medical scan is parcellated into a first set of one or more subregions (420), based on image content, each subregion comprising a plurality of voxels. The first medical scan (310) is aligned to the second medical scan (410), before or after parcellating the first medical scan (310). Then the second medical scan is parcellated into a second set of one or more subregions. A metric is evaluated for a subregion in the first medical scan (310), and for the corresponding subregion in the second medical scan (410). A difference in the metric values provides a measure of a change that has occurred in the subregion, between the first and second timepoints.

A method of visualization, characterization, and detection of objects within an image by applying a local micro-contrast convergence algorithm to a first image to produce a second image that is different from the first image, wherein all like objects converge into similar patterns or colors in the second image.

A method and a product for AI endoscope analyzing of vein based on VRDS 4D medical images, which is applied to medical imaging apparatus, and the method includes: determining a bitmap (BMP) data source according to a plurality of scanned images of a target site of a target user, wherein the target site includes a target vein to be observed and an artery, a kidney and a hepatic portal associated with the target vein; generating first medical image data according to the BMP data source; generating second medical image data according to the first medical image data; processing the second medical image data to obtain target medical image data; extracting a data set of the target vein in the target medical image data; performing 4D medical imaging according to the data set of the target vein to display an internal image of the target vein.