公开(公告)号：US20180314943A1

公开(公告)日：2018-11-01

申请号：US15965691

申请日：2018-04-27

Applicant: Jianming Liang ,  Zongwei Zhou ,  Jae Shin

Inventor： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Systems for selecting candidates for labelling and use in training a convolutional neural network (CNN) are provided, the systems comprising: a memory device; and at least one hardware processor configured to: receive a plurality of input candidates, wherein each candidate includes a plurality of identically labelled patches; and for each of the plurality of candidates: determine a plurality of probabilities, each of the plurality of probabilities being a probability that a unique patch of the plurality of identically labelled patches of the candidate corresponds to a label using a pre-trained CNN; identify a subset of candidates of the plurality of input candidates, wherein the subset does not include all of the plurality of candidates, based on the determined probabilities; query an external source to label the subset of candidates to produce labelled candidates; and train the pre-trained CNN using the labelled candidates.

公开(公告)号：US20200380695A1

公开(公告)日：2020-12-03

申请号：US16885579

申请日：2020-05-28

Applicant: Zongwei Zhou ,  Md Mahfuzur Rahman Siddiquee ,  Nima Tajbakhsh ,  Jianming Liang

Inventor： Zongwei Zhou ,  Md Mahfuzur Rahman Siddiquee ,  Nima Tajbakhsh ,  Jianming Liang

IPC: G06T7/143 ,  G06T7/00

Abstract: Methods, systems, and media for segmenting images are provided. In some embodiments, the method comprises: generating an aggregate U-Net comprised of a plurality of U-Nets, wherein each U-Net in the plurality of U-Nets has a different depth, wherein each U-Net is comprised of a plurality of nodes Xi,j, wherein i indicates a down-sampling layer the U-Net, and wherein j indicates a convolution layer of the U-Net; training the aggregate U-Net by: for each training sample in a group of training samples, calculating, for each node in the plurality of nodes Xi,j, a feature map xi,j, wherein xi,j is based on a convolution operation performed on a down-sampling of an output from Xi−1,j when j=0, and wherein xi,j is based on a convolution operation performed on an up-sampling operation of an output from Xi+1,j−1 when j>0; and predicting a segmentation of a test image using the trained aggregate U-Net.

公开(公告)号：US20220262105A1

公开(公告)日：2022-08-18

申请号：US17625313

申请日：2020-07-17

Applicant: Zongwei ZHOU ,  Vatsal SODHA ,  Md, Mahfuzur RAHMAN SIDDIQUEE ,  Ruibin FENG ,  Nima TAJBAKHSH ,  Jianming LIANG ,  Arizona Board of Regents on behalf of Arizona State University

Inventor： Zongwei Zhou ,  Vatsal Sodha ,  Md Mahfuzur Rahman Siddiquee ,  Ruibin Feng ,  Nima Tajbakhsh ,  Jianming Liang

IPC: G06V10/774 ,  G06V10/82 ,  G06V10/98 ,  G06V10/776

Abstract: Described herein are means for generating source models for transfer learning to application specific models used in the processing of medical imaging. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample in the group of training samples includes an image; for each training sample in the group of training samples: identifying an original patch of the image corresponding to the training sample; identifying one or more transformations to be applied to the original patch; generating a transformed patch by applying the one or more transformations to the identified patch; and training an encoder-decoder network using a group of transformed patches corresponding to the group of training samples, wherein the encoder-decoder network is trained to generate an approximation of the original patch from a corresponding transformed patch, and wherein the encoder-decoder network is trained to minimize a loss function that indicates a difference between the generated approximation of the original patch and the original patch. The source models significantly enhance the transfer learning performance for many medical imaging tasks including, but not limited to, disease/organ detection, classification, and segmentation. Other related embodiments are disclosed.

公开(公告)号：US20190332896A1

公开(公告)日：2019-10-31

申请号：US16397990

申请日：2019-04-29

Applicant: Jianming Liang ,  Zongwei Zhou ,  Jae Shin

Inventor： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

IPC: G06K9/62

Abstract: Methods, systems, and media for selecting candidates for annotation for use in training classifiers are provided. In some embodiments, the method comprises: identifying, for a trained Convolutional Neural Network (CNN), a group of candidate training samples, wherein each candidate training sample includes a plurality of patches; for each patch of the plurality of patches, determining a plurality of probabilities, each probability being a probability that the patch corresponds to a label of a plurality of labels; identifying a subset of the patches in the plurality of patches; for each patch in the subset of the patches, calculating a metric that indicates a variance of the probabilities assigned to each patch; selecting a subset of the candidate training samples based on the metric; labeling candidate training samples in the subset of the candidate training samples by querying an external source; and re-training the CNN using the labeled candidate training samples.