Sparse Data–Driven Learning for Effective and Efficient Biomedical Image Segmentation
John A. Onofrey, Lawrence H. Staib, Xiaojie Huang, Fan Zhang, Xenophon Papademetris, Dimitris Metaxas, Daniel Rueckert, James S. Duncan · Annual Review of Biomedical Engineering · 2020
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.