公开(公告)号：US20230141896A1

公开(公告)日：2023-05-11

申请号：US17915362

申请日：2021-03-23

Applicant: University of Florida Research Foundation, Inc.

Inventor： Peng Liu ,  Ruogu Fang

IPC: A61B3/00 ,  A61B3/12 ,  G06V10/82 ,  G06V40/18

CPC classification number: A61B3/0025 ,  A61B3/12 ,  G06V10/82 ,  G06V40/197

Abstract: Embodiments of the present disclosure are directed to training a neural network for ocular cup (OC) or ocular disc (OD) detection. One such method comprises initiating training of a first network to learn detection of OC/OD regions within a labeled source sample from a source domain; sharing training weights of the first network with a second network; initiating training of the second network to learn detection of OC/OD regions within an unlabeled sample from a target domain; transferring average training weights of the second network to a third network; initiating training of the third network to learn detection of OC/OD regions within an unlabeled sample from the target domain; computing a mean square error loss between the third network and the second network for a same target sample; and adjusting training weights of the second network based on the mean square error loss computation.

公开(公告)号：US11069033B2

公开(公告)日：2021-07-20

申请号：US16558779

申请日：2019-09-03

Applicant: University of Florida Research Foundation, Inc.

Inventor： Ruogu Fang ,  Peng Liu

IPC: G06T7/00 ,  G06N3/12 ,  G06F17/15 ,  G06N3/04 ,  G06T5/00

Abstract: Various embodiments for image denoising using a convolutional neural network (CCN) are described. A system may include at least one computing device and program instructions stored in memory and executable in the at least one computing device that, when executed, direct the at least one computing device to implement a genetic algorithm (GA) routine that identifies and optimizes a plurality of hyperparameters for use in denoising an image using the convolutional neural network. An image may be denoised using the convolutional neural network, where the image is denoised using the hyperparameters identified and optimized in the genetic algorithm routine.

公开(公告)号：US20200082507A1

公开(公告)日：2020-03-12

申请号：US16558779

申请日：2019-09-03

Applicant: University of Florida Research Foundation, Inc.

Inventor： Ruogu Fang ,  Peng Liu

IPC: G06T5/00 ,  G06T7/00 ,  G06N3/12 ,  G06N3/04 ,  G06F17/15

Abstract: Various embodiments for image denoising using a convolutional neural network (CCN) are described. A system may include at least one computing device and program instructions stored in memory and executable in the at least one computing device that, when executed, direct the at least one computing device to implement a genetic algorithm (GA) routine that identifies and optimizes a plurality of hyperparameters for use in denoising an image using the convolutional neural network. An image may be denoised using the convolutional neural network, where the image is denoised using the hyperparameters identified and optimized in the genetic algorithm routine.

公开(公告)号：US20230301614A1

公开(公告)日：2023-09-28

申请号：US18007366

申请日：2021-07-29

Applicant: University of Florida Research Foundation, Inc.

Inventor： Ruogu Fang ,  Peng Liu

IPC: A61B6/00 ,  G06T5/00 ,  G06T5/50

CPC classification number: A61B6/5258 ,  A61B6/5235 ,  A61B6/583 ,  G06T5/002 ,  G06T5/50 ,  G06T2207/30004 ,  G06T2207/30168 ,  G06T2207/20081

Abstract: Various examples are provided related to reconstructing images such as, e.g., medical images from low-dose image scans. Adversarial learning such as, e.g., a Cyclic Simulation and Denoising (CSD) framework can be used to address challenges of complicated mixed noise in real low-dose scans. The CSD framework can include a simulator model that can extract low-dose noise and features (e.g., tissue features) from separate image spaces into a unified feature space and a denoiser model that can learn how to remove noise and restore features, simultaneously. Both the simulator model and the denoiser model can regularize each other in a cyclic manner to optimize network learning effectively. The CSD framework in combination with phantom scans can embrace the realistic low-dose noise and features into a unified learning environment to address the challenge of real low-dose image restoration.