Cascaded classifier for large-scale data applied to automatic segmentation of articular cartilage

TY - GEN

T1 - Cascaded classifier for large-scale data applied to automatic segmentation of articular cartilage

AU - Prasoon, Adhish

AU - Igel, Christian

AU - Loog, Marco

AU - Lauze, Francois Bernard

AU - Dam, Erik

AU - Nielsen, Mads

PY - 2012

Y1 - 2012

N2 - Many classification/segmentation tasks in medical imaging are particularly challenging for machine learning algorithms because of the huge amount of training data required to cover biological variability. Learning methods scaling badly in the number of training data points may not be applicable. This may exclude powerful classifiers with good generalization performance such as standard non-linear support vector machines (SVMs). Further, many medical imaging problems have highly imbalanced class populations, because the object to be segmented has only few pixels/voxels compared to the background. This article presents a two-stage classifier for large-scale medical imaging problems. In the first stage, a classifier that is easily trainable on large data sets is employed. The class imbalance is exploited and the classifier is adjusted to correctly detect background with a very high accuracy. Only the comparatively few data points not identified as background are passed to the second stage. Here a powerful classifier with high training time complexity can be employed for making the final decision whether a data point belongs to the object or not. We applied our method to the problem of automatically segmenting tibial articular cartilage from knee MRI scans. We show that by using nearest neighbor (kNN) in the first stage we can reduce the amount of data for training a non-linear SVM in the second stage. The cascaded system achieves better results than the state-of-the-art method relying on a single kNN classifier.

AB - Many classification/segmentation tasks in medical imaging are particularly challenging for machine learning algorithms because of the huge amount of training data required to cover biological variability. Learning methods scaling badly in the number of training data points may not be applicable. This may exclude powerful classifiers with good generalization performance such as standard non-linear support vector machines (SVMs). Further, many medical imaging problems have highly imbalanced class populations, because the object to be segmented has only few pixels/voxels compared to the background. This article presents a two-stage classifier for large-scale medical imaging problems. In the first stage, a classifier that is easily trainable on large data sets is employed. The class imbalance is exploited and the classifier is adjusted to correctly detect background with a very high accuracy. Only the comparatively few data points not identified as background are passed to the second stage. Here a powerful classifier with high training time complexity can be employed for making the final decision whether a data point belongs to the object or not. We applied our method to the problem of automatically segmenting tibial articular cartilage from knee MRI scans. We show that by using nearest neighbor (kNN) in the first stage we can reduce the amount of data for training a non-linear SVM in the second stage. The cascaded system achieves better results than the state-of-the-art method relying on a single kNN classifier.

U2 - 10.1117/12.910809

DO - 10.1117/12.910809

M3 - Article in proceedings

VL - 8314

T3 - SPIE Proceedings

BT - Medical Imaging 2012

A2 - Haynor, David R.

A2 - Ourselin, Sébastien

PB - SPIE - International Society for Optical Engineering

T2 - Medical Imaging 2012: Image Processing

Y2 - 6 February 2012 through 9 February 2012

ER -