Beyond KernelBoost

TL;DR

This paper enhances the KernelBoost classifier with iterative, context-aware mechanisms and new techniques like pooling and clustering, improving biomedical image segmentation accuracy and boundary regularization.

Contribution

It introduces a novel iterative, Auto-Context inspired scheme with KernelBoost, incorporating pooling and clustering to better regularize boundaries and handle small training sets in biomedical imaging.

Findings

Outperforms state-of-the-art methods on medical datasets

Produces high-accuracy, smooth, and noise-reduced segmentations

Effectively captures pixel interactions for boundary regularization

Abstract

In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the lack of large training sets poses a potential problem of overfitting. The aim is to capture the interactions between neighboring image pixels to better regularize the boundaries of segmented regions. As in Auto-Context [Tu et al., PAMI 2009] the segmentation process is iterative and, at each iteration, the segmentation results for the previous iterations are taken into account in conjunction with the image itself. However, unlike in [Tu et al., PAMI 2009], we organize our recursion so that the classifiers can progressively focus on difficult-to-classify locations. This lets us exploit the power of the decision-tree paradigm while avoiding over-fitting. In the context of this architecture, KernelBoost represents a powerful building block due to its ability to learn on the score maps coming from previous iterations. We first introduce two important mechanisms to empower the KernelBoost classifier, namely pooling and the clustering of positive samples based on the appearance of the corresponding ground-truth. These operations significantly contribute to increase the effectiveness of the system on biomedical images, where texture plays a major role in the recognition of the different image components. We then present some other techniques that can be easily integrated in the KernelBoost framework to further improve the accuracy of the final segmentation. We show extensive results on different medical image datasets, including some multi-label tasks, on which our method is shown to outperform state-of-the-art approaches. The resulting segmentations display high accuracy, neat contours, and reduced noise.