Open AccessSparse Data–Driven Learning for Effective and Efficient Biomedical Image Segmentation
Author(s) -
John A. Onofrey,
Lawrence H. Staib,
Xiaojie Huang,
Fan Zhang,
Xenophon Papademetris,
Dimitris N. Metaxas,
Daniel Rueckert,
James S. Duncan
Publication year - 2020
Publication title -
annual review of biomedical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 4.142
H-Index - 133
eISSN - 1545-4274
pISSN - 1523-9829
DOI - 10.1146/annurev-bioeng-060418-052147
Subject(s) - artificial intelligence , segmentation , computer science , image segmentation , exploit , image (mathematics) , machine learning , medical imaging , deep learning , scale space segmentation , pattern recognition (psychology) , selection (genetic algorithm) , computer vision , computer security
Sparsity is a powerful concept to exploit for high-dimensional machine learning and associated representational and computational efficiency. Sparsity is well suited for medical image segmentation. We present a selection of techniques that incorporate sparsity, including strategies based on dictionary learning and deep learning, that are aimed at medical image segmentation and related quantification.