Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images

TL;DR

This paper introduces an iterative multi-class learning approach for automatic 3D knee cartilage segmentation in MR images, leveraging spatial and semantic context to improve accuracy and robustness.

Contribution

It proposes a novel iterative discriminative classifier framework that exploits spatial and semantic context for simultaneous multi-cartilage segmentation.

Findings

High segmentation accuracy on OAI dataset

Robustness against challenging cartilage structures

Outperforms existing state-of-the-art methods

Abstract

The automatic segmentation of human knee cartilage from 3D MR images is a useful yet challenging task due to the thin sheet structure of the cartilage with diffuse boundaries and inhomogeneous intensities. In this paper, we present an iterative multi-class learning method to segment the femoral, tibial and patellar cartilage simultaneously, which effectively exploits the spatial contextual constraints between bone and cartilage, and also between different cartilages. First, based on the fact that the cartilage grows in only certain area of the corresponding bone surface, we extract the distance features of not only to the surface of the bone, but more informatively, to the densely registered anatomical landmarks on the bone surface. Second, we introduce a set of iterative discriminative classifiers that at each iteration, probability comparison features are constructed from the class confidence maps derived by previously learned classifiers. These features automatically embed the semantic context information between different cartilages of interest. Validated on a total of 176 volumes from the Osteoarthritis Initiative (OAI) dataset, the proposed approach demonstrates high robustness and accuracy of segmentation in comparison with existing state-of-the-art MR cartilage segmentation methods.