公开(公告)号：US20230004872A1

公开(公告)日：2023-01-05

申请号：US17365650

申请日：2021-07-01

Applicant: GE PRECISION HEALTHCARE LLC

Inventor： Soumya Ghose ,  Radhika Madhavan ,  Chitresh Bhushan ,  Dattesh Dayanand Shanbhag ,  Deepa Anand ,  Desmond Teck Beng Yeo ,  Thomas Kwok-Fah Foo

IPC: G06N20/20 ,  G06K9/62 ,  G06T7/00

Abstract: A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

公开(公告)号：US20220319006A1

公开(公告)日：2022-10-06

申请号：US17220770

申请日：2021-04-01

Applicant: GE Precision Healthcare LLC

Inventor： Pavan Annangi ,  Rahul Venkataramani ,  Deepa Anand ,  Eigil Samset

IPC: G06T7/00 ,  A61B8/08 ,  G06K9/62 ,  G06K9/03 ,  G06K9/32 ,  G06N3/04 ,  G06N3/08

Abstract: Various methods and systems are provided for bicuspid valve detection with ultrasound imaging. In one embodiment, a method comprises acquiring ultrasound video of a heart over at least one cardiac cycle, identifying frames in the ultrasound video corresponding to at least one cardiac phase, and classifying a cardiac structure in the identified frames as a bicuspid valve or a tricuspid valve. A generative model such as a variational autoencoder trained on ultrasound image frames at the at least one cardiac phase may be used to classify the cardiac structure. In this way, relatively rare occurrences of bicuspid aortic valves may be automatically detected during regular cardiac ultrasound screenings.

公开(公告)号：US20220301287A1

公开(公告)日：2022-09-22

申请号：US17654019

申请日：2022-03-08

Applicant: GE Precision Healthcare LLC

Inventor： Pavan Annangi ,  Deepa Anand

IPC: G06V10/764 ,  G06V10/774 ,  G06T7/00

Abstract: Systems and method for domain adaptation using pseudo-labelling and model certainty quantification for video data are provided. The method includes obtaining a source data and a target data each comprising a plurality of frames for processing by a machine learning module. The method comprises testing the target data to identify if a minimum number of frames exhibit a frame confidence score based on the source data and identifying salient region within the target data and measuring a degree of spatial consistency of the salient region over time. The method comprises identifying class specific attention region within the target data and measuring a confidence score of class specific attention region within the target data and carrying out pseudo-labeling of the target data based on the source data and calculating a certainty metrics value based on the frame confidence score, the degree of spatial consistency of the salient region over time, the confidence score of class specific attention region within the frames of the target data and confidence score of the pseudo-labeling on the target data. The machine learning module is retrained till the certainty metrics value reaches peak and further retraining the machine learning module does not increase the certainty metrics value.

公开(公告)号：US20220301163A1

公开(公告)日：2022-09-22

申请号：US17203196

申请日：2021-03-16

Applicant: GE Precision Healthcare LLC

Inventor： Florintina C. ,  Deepa Anand ,  Dattesh Dayanand Shanbhag ,  Chitresh Bhushan ,  Radhika Madhavan

IPC: G06T7/00 ,  G06N20/00 ,  G06T7/11 ,  G06T3/00

Abstract: A medical imaging system includes at least one medical imaging device providing image data of a subject and a processing system programmed to generate a plurality of training images having simulated medical conditions by blending a pathology region from a plurality of template source images to a plurality of target images. The processing system is further programmed to train a deep learning network model using the plurality of training images and input the image data of the subject to the deep learning network model. The processing system is further programmed to generate a medical image of the subject based on the output of the deep learning network model.