Machine learning for medical images analysis


    loading  Checking for direct PDF access through Ovid

Abstract

HighlightsMachine learning and conventional algorithms are not so different from one another.Hierarchical-structured algorithms are equivalent to decision trees.Decision trees can be optimized automatically from training data and thus achieve higher accuracy.The issue of requiring large amounts of training data is a function of the model/algorithm complexity and not a characteristic of learning-based techniques.Graphical abstractThis article discusses the application of machine learning for the analysis of medical images. Specifically: (i) We show how a special type of learning models can be thought of as automatically optimized, hierarchically-structured, rule-based algorithms, and (ii) We discuss how the issue of collecting large labelled datasets applies to both conventional algorithms as well as machine learning techniques. The size of the training database is a function of model complexity rather than a characteristic of machine learning methods.

    loading  Loading Related Articles