Cross-validation is a statistical method used to estimate the skill of machine learning models. This approach involves randomly dividing the set of observations into k groups, or folds, of approximately equal size. At each round one different fold is treated at turn as a validation set, and the method is trained on the remaining k-1. Finally, the performance are combined (e.g. averaged) over the rounds.
Published in Chapter:
Digital Recognition of Breast Cancer Using TakhisisNet: An Innovative Multi-Head Convolutional Neural Network for Classifying Breast Ultrasonic Images
Loris Nanni (Università di Padova, Italy), Alessandra Lumini (University of Bologna, Italy), and Gianluca Maguolo (University of Padova, Italy)
Copyright: © 2020
|Pages: 19
DOI: 10.4018/978-1-7998-3274-4.ch009
Abstract
In this chapter, the authors evaluate several basic image processing and advanced image pattern recognition techniques for automatically analyzing bioimages, with the aim of designing different ensembles of canonical and deep classifiers for breast lesion classification in ultrasound images. The analysis starts from convolutional neural networks (CNNs) in a square matrix that is used to feed other CNNs. The novel ensemble, named TakhisisNet, is the combination by sum rule of the whole set of the modified CNNs and the original one. Moreover, the performance of the system is further improved by combining it with some handcrafted features. Experimental results obtained on the well-known OASBUD breast cancer dataset (i.e., the open access series of breast ultrasonic data) and on a large set of bioimage classification problems show that TakhisisNet obtains very valuable results and outperforms other approaches previously tested in the same datasets.