Shanghai United Imaging Intelligence Co., Ltd.

United Imaging Intelligence (beijing) Co., Ltd.

Zhang Chen

Shanhui Sun

Terrence Chen

Xiao Chen

Yikang Liu

Ziyan Wu

Arun Innanje

Abhishek Sharma

Yimo Guo

Qiaoying Huang

Hanchao Yu

Pingjun Chen

Siyuan Dong

Shuo Han

Luojie Huang

Srikrishna Karanam

Puyang Wang

Li Chen

Junshen Xu

Daniel Hyungseok Pak

Lin Zhao

Chi Zhang

Xiaoling Hu

An apparatus may obtain a sequence of medical images of a target structure and determine, using a first ANN, a first segmentation and a second segmentation of the target structure based on a first medical image and a second medical image, respectively. The first segmentation may indicate a first plurality of pixels that may belong to the target structure. The second segmentation may indicate a second plurality of pixels that may belong to the target structure. The apparatus may identify, using a second ANN, a first subset of true positive pixels among the first plurality of pixels that may belong to the target structure, and a second subset of true positive pixels among the second plurality of pixels that may belong to the target structure. The apparatus may determine a first refined segmentation and a second refined segmentation of the target structure based on the true positive pixels.

Systems and methods for segmenting a medical image sequence

Disclosed herein are systems, methods, and instrumentalities associated with magnetic resonance (MR) image reconstruction. An under-sampled MR image may be reconstructed through an iterative process (e.g., over multiple iterations) based on a machine-learning (ML) model. The ML model may be obtained through a reinforcement learning process during which the ML model may be used to predict a correction to an input MR image of at least one of the multiple iterations, apply the correction to the input MR image to obtain a reconstructed MR image, determine a reward for the ML model based on the reconstructed MR image, and adjust the parameters of the ML model based on the reward. The reward may be determined using a pre-trained reward neural network and the ML model may also be pre-trained in a supervised manner before being refined through the reinforcement learning process.

Under-sampled magnetic resonance image reconstruction of an anatomical structure based on a machine-learned image reconstruction model

Digital breast tomosynthesis (DBT) may provide richer information than full-field digital mammography (FFDM). DBT data such as DBT slices may be processed based on deep learning techniques such as using a neural network, and the DBT slices may be divided into groups and a pre-determined number of representative images may be derived based on the grouping. The neural network may be configured to process the representative images to predict the presence or non-presence of a breast disease such as breast cancer.

Systems and methods for processing breast slice images through an artificial neural network to predict abnormalities in breasts

Deep learning-based systems, methods, and instrumentalities are described herein for MRI reconstruction and/or refinement. An MRI image may be reconstructed based on under-sampled MRI information and a generative model may be trained to refine the reconstructed image, for example, by increasing the sharpness of the MRI image without introducing artifacts into the image. The generative model may be implemented using various types of artificial neural networks including a generative adversarial network. The model may be trained based on an adversarial loss and a pixel-wise image loss, and once trained, the model may be used to improve the quality of a wide range of 2D or 3D MRI images including those of a knee, brain, or heart.

MRI reconstruction based on generative models

Described herein are systems, methods, and instrumentalities associated with using a multi-layer perceptron (MLP) neural network to process medical images of an anatomical structure. The processing may include padding an input image in accordance with the training of the MLP neural network, splitting the input image (e.g., the padded input image) into patches of a same size, and processing the patches through the MLP neural network over one or more iterations. During an iteration of the processing, the patches may be processed separately and re-combined into an intermediate image before the intermediate image is shifted to concatenate portions of the image that are derived from different patches. This way, global features of the anatomical structure may be learned and used to improve the quality of the image generated by the MLP neural network, without incurring significant computation or memory costs.

Systems and methods for processing medical images with multi-layer perceptron neural networks

Deblurring and denoising a medical image such as X-ray fluoroscopy images may be challenging, and deep-learning based techniques may be employed to meet the challenge. An artificial neural network (ANN) may be trained using training images with synthetic noise and as well as training images with real noise. The parameters of the ANN may be adjusted during the training based on at least a first loss designed to maintain continuity between consecutive medical images generated by the ANN and a second loss designed to maintain similarity of patches inside a medical image generated by the ANN. The parameters of the ANN may be further adjusted based on a third loss that may be calculated from ground truth associated with the synthetic training images. Transfer learning between the synthetic images and the real images may be accomplished using these techniques.

Systems and methods for deblurring and denoising medical images

Described herein are systems, methods, and instrumentalities associated with segmenting and/or determining the shape of an anatomical structure. An artificial neural network (ANN) is used to perform these tasks based on a statistical shape model of the anatomical structure. The ANN is trained by evaluating and backpropagating multiple losses associated with shape estimation and segmentation mask generation. The model obtained using these techniques may be used for different clinical purposes including, for example, motion estimation and motion tracking.

Image segmentation and tracking based on statistical shape model

Described herein are systems, methods, and instrumentalities associated with automatically detecting and enhancing multiple objects in medical scan images. The detection and/or enhancement may be accomplished utilizing artificial neural networks such as one or more classification neural networks and/or one or more graph neural networks. The neural networks may be used to detect areas in the medical scan images that may correspond to the objects of interest and cluster the areas belonging to a same object into a respective cluster. These tasks may be accomplished, for example, by representing the areas corresponding to the objects of interest and their interrelationships with a graph and processing the graph through the one or more graph neural networks so that the areas belonging to each object may be properly labeled and clustered. The clusters may then be used to enhance the objects of interests in one or more output scan images.

Detecting and enhancing objects in medical images

Described herein are systems, methods, and instrumentalities associated with tracking groups of small objects in medical images. The tracking may be accomplished by, for each one of a sequence of medical images, determining a plurality of candidate objects captured in the medical image, grouping the plurality of candidate objects into a plurality of groups of candidate objects and dividing the medical image into a plurality of regions that each surrounds a corresponding group of candidate objects. Each of the plurality of regions may be examined to extract respective features associated with each corresponding group of candidate objects. A match between a first group of candidate objects in a first medical image and a second group of candidate objects in a second medical image may be determined based on first features associated with the first group and second features associated with the second group.

Systems and methods for tracking groups of objects in medical images

Described herein are systems, methods, and instrumentalities associated with using an invertible neural network to complete various medical imaging tasks. Unlike traditional neural networks that may learn to map input data (e.g., a blurry reconstructed MRI image) to ground truth (e.g., a fully-sampled MRI image), the invertible neural network may be trained to learn a mapping from the ground truth to the input data, and may subsequently apply an inverse of the mapping (e.g., at an inference time) to complete a medical imaging task. The medical imaging task may include, for example, MRI image reconstruction (e.g., to increase the sharpness of a reconstructed MRI image), image denoising, image super-resolution, and/or the like.

Systems and methods for processing medical images with invertible neural networks

A 3D anatomical model of one or more blood vessels of a patient may be obtained using CT angiography, while a 2D image of the blood vessels may be obtained based on fluoroscopy. The 3D model may be registered with the 2D image based on a contrast injection site identified on the 3D model and/or in the 2D image. A fused image may then be created to depict the overlaid 3D model and 2D image, for example, on a monitor or through a virtual reality headset. The injection site may be determined automatically or based on a user input that may include a bounding box drawn around the injection site on the 3D model, a selection of an automatically segmented area in the 3D model, etc.

Systems and methods for medical image fusion

Described herein are systems, methods, and instrumentalities associated with image segmentation such as tubular structure segmentation. An artificial neural network is trained to segment tubular structures of interest in a medical scan image based on annotated images of a different type of tubular structures that may have a different contrast and/or appearance from the tubular structures of interest. The training may be conducted in multiple stages during which a segmentation model learned from the annotated images during a first stage may be modified to fit the tubular structures of interest in a second stage. In examples, the tubular structures of interest may include coronary arteries, catheters, guide wires, etc., and the annotated images used for training the artificial neural network may include blood vessels such as retina blood vessels.

Tubular structure segmentation

Described herein are systems, methods, and instrumentalities associated with medical image enhancement. The medical image may include an object of interest and the techniques disclosed herein may be used to identify the object and enhance a contrast between the object and its surrounding area by adjusting at least the pixels associated with the object. The object identification may be performed using an image filter, a segmentation mask, and/or a deep neural network trained to separate the medical image into multiple layers that respectively include the object of interest and the surrounding area. Once identified, the pixels of the object may be manipulated in various ways to increase the visibility of the object. These may include, for example, adding a constant value to the pixels of the object, applying a sharpening filter to those pixels, increasing the weight of those pixels, and/or smoothing the edge areas surrounding the object of interest.

Systems and methods for enhancing medical images

The present disclosure provides a system and method for fetus monitoring. The method may include obtaining ultrasound data relating to a fetus collected by an ultrasound imaging device; generating a 4D image of the fetus based on the ultrasound data; directing a display component of a virtual reality (VR) device to display the 4D image to an operator; detecting motion of the fetus based on the ultrasound data; and directing a haptic component of the VR device to provide haptic feedback with respect to the motion to the operator.

Systems and methods for fetus monitoring

Deep learning based systems, methods, and instrumentalities are described herein for registering images from a same imaging modality and different imaging modalities. Transformation parameters associated with the image registration task are determined using a neural ordinary differential equation (ODE) network that comprises multiple layers, each configured to determine a respective gradient update for the transformation parameters based on a current state of the transformation parameters received by the layer. The gradient updates determined by the multiple ODE layers are then integrated and applied to initial values of the transformation parameters to obtain final parameters for completing the image registration task. The operations of the ODE network may be facilitated by a feature extraction network pre-trained to determine content features shared by the input images. The input images may be resampled into different scales, which are then processed by the ODE network iteratively to improve the efficiency of the ODE operations.

Growing community of inventors

Brookline, MA, United States of America

Zhang Chen