Ge Precision Healthcare LLC

General Electric Company

Raghu Prasad

Sandeep Lakshmipathy

Jignesh Dholakia

Kavitha Manickam

Govindappa Simhadri

Jayanth Ganapathiraju

Rahul Gupta

Yu Huang

Gireesha Chinthamani Rao

Katelyn Rose Nye

Yanran Xu

Alec Joseph Baenen

Prabhu Rajasekaran

Eric Hart

Adam Pluim

Kiran Panchal

Scott Schubert

Aishwarya Seth

Chinnakotla Krishna Teja Reddy

Ayushi Vishwakarma

Sanket Mali

Harikrishna Rai

Keval Harishabhai Jagatiya

A method for preventing a collision between a first object and a second object using a camera. The method includes capturing images of the first object and the second object using the camera, accessing a database of point clouds, and identify a first point cloud corresponding to the first object and a second point cloud corresponding to the second object within the database of point clouds, where the first point cloud corresponds to the first object being a person. The method further includes calculating a distance between the first object and the second object and comparing the distance to a threshold. The method further includes generating a notification when the distance is below the threshold.

Systems and methods for predicting and preventing collisions

The current disclosure provides methods and systems for rapidly and consistently determining medical image quality metrics following acquisition of a diagnostic medical image. In one embodiment, the current disclosure teaches a method for determining an image quality metric by, acquiring a medical image of an anatomical region, mapping the medical image to a positional attribute of an anatomical feature using a trained deep neural network, determining an image quality metric based on the positional attribute of the anatomical feature, determining if the image quality metric satisfies an image quality criterion, and displaying the medical image, the image quality metric, and a status of the image quality criterion via a display device. In this way, a diagnostic scanning procedure may be expedited by providing technicians with real-time insight into quantitative image quality metrics.

System and methods for medical image quality assessment using deep neural networks

Systems and techniques that facilitate real-time and/or offline de-identification of facial regions from regular and/or occluded color video streams obtained during diagnostic medical procedures are provided. A detection component can generate a bounding box substantially around a person in a frame of a video stream, can generate a heatmap showing key points or anatomical masks of the person based on the bounding box, and can localize a face or facial region of the person based on the key points or anatomical masks. An anonymization component can anonymize pixels in the frame that correspond to the face or facial region. A tracking component can track the face or facial region in a subsequent frame based on a structural similarity index between the frame and the subsequent frame being above a threshold. If the structural similarity index between the frame and the subsequent frame is above the threshold, the tracking component can track the face or facial region in the subsequent frame without having the detection component generate a bounding box or a heatmap in the subsequent frame, and the anonymization component can anonymize pixels in the subsequent frame corresponding to the tracked face or facial region.

Method and system for real-time and offline de-identification of facial regions from regular and occluded color video streams obtained during diagnostic medical procedures

Systems and methods for automated patient anatomy and orientation identification using an artificial intelligence (AI) based deep learning module are provided. The method comprises positioning a subject over a table of a magnetic resonance imaging (MRI) system and wrapping at least one radiofrequency (RF) imaging coil over the subject. The method comprises obtaining a plurality of depth images, color images and infrared images of the subject using a three-dimensional (3D) depth camera and identifying the table boundary of the MRI system using the images obtained by the 3D camera. The method further comprises identifying a location of the subject over the table to determine if the subject is positioned within the table boundary of the MRI system and identifying a plurality of key anatomical points or regions corresponding to a plurality of organs of the subject body. The method further comprises identifying all DICOM orientations of the subject over the table of the MRI system and identifying the coils of the MRI system wrapped around the subject body and determining the orientation of the subject with respect to the coils of the MRI system, hospital gown, and blankets. The method further comprises identifying the anatomical key points occluded by the coils of the MRI system, hospital gown, and blankets to determine accurate positioning of the coils of the MRI system over the subject anatomy for automated landmarking of anatomies and imaging.

Deep learning based methods and systems for automated subject anatomy and orientation identification

Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, determining at least one spine label seed point on a non-functional image volume, automatically labeling the non-functional image volume with a plurality of spine labels based on the at least one spine label seed point, automatically correcting the geometric misalignments and registering the functional image volume, adjusting the plurality of spine labels and propagating the adjusted spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Systems and methods for whole-body spine labeling

Methods and systems are provided for estimating patient structure prior to a scan by a medical imaging system. As one example, a method may include acquiring depth images of a patient positioned on a table of the medical imaging system, correcting the depth images based on histogram data from the depth images, and extracting a three-dimensional structure of the patient based on the corrected depth images.

Systems and methods for patient structure estimation during medical imaging

Methods and systems are provided for whole-body spine labeling. In one embodiment, a method comprises acquiring a non-functional image volume of a spine, acquiring a functional image volume of the spine, automatically labeling the non-functional image volume with spine labels, automatically correcting the geometric misalignments and registering the functional image volume, and propagating the spine labels to the functional image volume. In this way, the anatomical details of non-functional imaging volumes may be leveraged to improve clinical diagnoses based on functional imaging, such as diffusion weighted imaging (DWI).

Systems and methods for deep learning based automated spine registration and label propagation

Growing community of inventors

Bengaluru, India

Raghu Prasad