Ge Precision Healthcare LLC

General Electric Company

Bhushan Dayaram Patil

Pavan Annangi

Deepa Anand

Arathi Sreekumari

Stephan W Anzengruber

Bipul Das

Utkarsh Agrawal

Jiang Hsieh

Krishna Seetharam Shriram

Rahul Venkataramani

Roshni Bhagalia

Prasad Sudhakara Murthy

Rajesh Langoju

Rajesh Veera Venkata Lakshmi Langoju

Peter Lamb

Systems and methods for self-supervised representation learning as a means to generate context-specific pretrained models include selecting data from a set of available data sets; selecting a pretext task from domain specific pretext tasks; selecting a target problem specific network architecture based on a user selection from available choices or any customized model as per user preference; and generating a pretrained model for the selected network architecture using the selected data obtained from the set of available data sets and a pretext task as obtained from domain specific pretext tasks.

Self-supervised learning framework to generate context specific pretrained models

Various methods and ultrasound imaging systems are provided for segmenting an object. In one example, a method includes accessing a volumetric ultrasound dataset, receiving an identification of a seed point for an object in an image generated based on the volumetric ultrasound dataset, and implementing a two-dimensional segmentation model on a first plurality of parallel slices based on the seed point to generate a first plurality of segmented regions. The method includes implementing the two-dimensional segmentation model on a second plurality of parallel slices based on the seed point to generate a second plurality of segmented regions. The method includes generating a detected region by accumulating the first plurality of segmented regions and the second plurality of segmented regions. The method includes implementing a shape completion model to generate a three-dimensional shape model for the object, and displaying rendering of the object based on the three-dimensional shape model.

Ultrasound imaging system and method for segmenting an object from a volumetric ultrasound dataset

The current disclosure provides systems and methods for improving a visualization of an image volume of a uterus and/or endometrium of a subject acquired using a transvaginal ultrasound system (TVUS). In one example, a method for the TVUS comprises extracting a medial axis of an endometrium of a received two-dimensional (2D) ultrasound image of a uterus of a subject; generating a uterine trace line based on the extracted medial axis; acquiring a three-dimensional (3D) image volume of the uterus based on the uterine trace line; and displaying the 3D image volume on a display device of the TVUS.

Automation of transvaginal ultrasound workflow

Systems/techniques that facilitate anatomy-driven augmentation of medical images are provided. In various embodiments, a system can access a medical image and a ground-truth segmentation mask corresponding to the medical image, wherein the ground-truth segmentation mask can indicate a location of a first anatomical structure depicted in the medical image. In various aspects, the system can create an augmented version of the medical image and an augmented version of the ground-truth segmentation mask, by applying a continuous deformation field to fewer than all pixels or voxels in the medical image and in the ground-truth segmentation mask. In various instances, the continuous deformation field can encompass: pixels or voxels that correspond to the first anatomical structure; and pixels or voxels that correspond to a surrounding periphery of the first anatomical structure.

Anatomy-driven augmentation of medical images

Systems and methods for automatically segmenting and detecting a menstrual cycle phase in ultrasound images of anatomical structures that change over a patient menstrual cycle are provided. The method includes acquiring, by an ultrasound probe of an ultrasound system, an ultrasound image of a region of interest having an anatomical structure that changes over a patient menstrual cycle. The method includes automatically segmenting, by at least one processor of the ultrasound system, an anatomical structure depicted in the ultrasound image. The method includes automatically predicting, by the at least one processor, a menstrual cycle phase based on the segmentation of the anatomical structure. The method includes causing, by the at least one processor, a display system to present at least one rendering of the segmented anatomical structure and the predicted menstrual cycle phase.

Method and system for automatic segmentation and phase prediction in ultrasound images depicting anatomical structures that change over a patient menstrual cycle

Systems/techniques that facilitate self-supervised deblurring are provided. In various embodiments, a system can access an input image generated by an imaging device. In various aspects, the system can train, in a self-supervised manner based on a point spread function of the imaging device, a machine learning model to deblur the input image. More specifically, the system can append to the model one or more non-trainable convolution layers having a blur kernel that is based on the point spread function of the imaging device. In various aspects, the system can feed the input image to the model, the model can generate a first output image based on the input image, the one or more non-trainable convolution layers can generate a second output image by convolving the first output image with the blur kernel, and the system can update parameters of the model based on a difference between the input image and the second output image.

Self-supervised deblurring

A computer-implemented method for correcting artifacts in computed tomography data is provided. The method includes inputting a sinogram into a trained sinogram correction network, wherein the sinogram is missing a pixel value for at least one pixel. The method also includes processing the sinogram via one or more layers of the trained sinogram correction network, wherein processing the sinogram includes deriving complementary information from the sinogram and estimating the pixel value for the at least one pixel based on the complementary information. The method further includes outputting from the trained sinogram correction network a corrected sinogram having the estimated pixel value.

System and method for utilizing a deep learning network to correct for a bad pixel in a computed tomography detector

The present approach relates, in some aspects, to a multi-level and a multi-channel frame work for segmentation using model-based or 'shallow' classification (i.e. learning processes such as linear regression, clustering, support vector machines, and so forth) followed by deep learning. This framework starts with a very low resolution version of the multi-channel data and constructs an shallow classifier with simple features to generate a coarser level tissue mask that in turn is used to crop patches from the high-resolution volume. The cropped volume is then processed using the trained convolution network to perform a deep learning based segmentation within the slices.

Growing community of inventors

Pune, India

Bhushan Dayaram Patil