Deep Feature Representations for Variable-Sized Regions of Interest in Breast Histopathology

Deep Feature Representations for Variable-Sized Regions of Interest in Breast Histopathology

Objective: Modeling variable-sized regions of interest (ROIs) in whole slide images using deep convolutional networks is a challenging task, as these networks typically require fixed-sized inputs that should contain sufficient structural and contextual information for classification. We propose a de...

Full description

Bibliographic Details
Main Authors: Aksoy, S. (Author), Aygunes, B. (Author), Elmore, J.G (Author), Mercan, C. (Author), Mercan, E. (Author), Shapiro, L.G (Author), Weaver, D.L (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2021
Subjects:
Article
artificial neural network
breast
Breast
breast biopsy
breast cancer
Breast histopathology
Chemical activation
Class prediction
Classification (of information)
classification algorithm
computer simulation
conceptual framework
Contextual information
controlled study
Convolution
Convolutional networks
Convolutional neural networks
deep feature representation
diagnostic imaging
diagnostic test accuracy study
digital pathology
Feature representation
Generic representation
histopathology
human
human tissue
Humans
image analysis
image reconstruction
image segmentation
learning algorithm
machine learning
mathematical model
measurement accuracy
measurement precision
Medical imaging
nerve cell network
Network activations
Neural Networks, Computer
principal component analysis
region of interest classification
Regions of interest
sensitivity and specificity
support vector machine
weakly supervised learning
Whole slide images
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items