Pixel-Based Machine Learning in Medical Imaging
Open Access
- 1 January 2012
- journal article
- review article
- Published by Hindawi Limited in International Journal of Biomedical Imaging
- Vol. 2012, 1-18
- https://doi.org/10.1155/2012/792079
Abstract
Machine learning (ML) plays an important role in the medical imaging field, including medical image analysis and computer-aided diagnosis, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical pattern recognition essentially require “learning from examples.” One of the most popular uses of ML is classification of objects such as lesions into certain classes (e.g., abnormal or normal, or lesions or nonlesions) based on input features (e.g., contrast and circularity) obtained from segmented object candidates. Recently, pixel/voxel-based ML (PML) emerged in medical image processing/analysis, which use pixel/voxel values in images directly instead of features calculated from segmented objects as input information; thus, feature calculation or segmentation is not required. Because the PML can avoid errors caused by inaccurate feature calculation and segmentation which often occur for subtle or complex objects, the performance of the PML can potentially be higher for such objects than that of common classifiers (i.e., feature-based MLs). In this paper, PMLs are surveyed to make clear (a) classes of PMLs, (b) similarities and differences within (among) different PMLs and those between PMLs and feature-based MLs, (c) advantages and limitations of PMLs, and (d) their applications in medical imaging.Keywords
Funding Information
- National Cancer Institute (R01CA120549, S10 RR021039, P30 CA14599)
This publication has 93 references indexed in Scilit:
- Fast connected-component labelingPattern Recognition, 2009
- A supervised ‘lesion-enhancement’ filter by use of a massive-training artificial neural network (MTANN) in computer-aided diagnosis (CAD)Physics in Medicine & Biology, 2009
- Employing topographical height map in colonic polyp measurement and false positive reductionPattern Recognition, 2009
- Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonographyMedical Physics, 2008
- Computer-aided diagnosis in medical imaging: Historical review, current status and future potentialComputerized Medical Imaging and Graphics, 2007
- Bilateral analysis based false positive reduction for computer‐aided mass detectionMedical Physics, 2007
- Determining the receptive field of a neural filterJournal of Neural Engineering, 2004
- Neocognitron capable of incremental learningNeural Networks, 2004
- Three-dimensional computer-aided diagnosis scheme for detection of colonic polypsIEEE Transactions on Medical Imaging, 2001
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997