Anatomy Detection and Localization in 3D Medical Images

This chapter discusses the use of regression forests for the automatic detection and simultaneous localization of multiple anatomical regions within Computed Tomography (CT) and Magnetic Resonance (MR) three-dimensional images. Important applications include: organ-specific tracking of radiation dose over time; selective retrieval of patient images from radiological database systems; semantic visual navigation; and the initialization of organ-specific image processing operations. We present a continuous parametrization of the anatomy localization problem, which allows it to be addressed effectively by multivariate random regression forests. A single pass of our probabilistic algorithm enables the direct mapping from voxels to organ location and size, with training focusing on maximizing the confidence of output predictions. As a by-product, our method produces salient anatomical landmarks, i.e. automatically selected “anchor” regions which help localize organs of interest with high confidence. This chapter builds upon the work in [80, 277] and demonstrates the flexibility of forests in dealing with both CT or multi-channel MR images. Quantitative validation is performed on two groundtruth labelled databases: i) a database of 400 highly variable CT scans, and ii) a database of 33 full-body, multi-channel MR scans. In both cases localization errors are shown to be lower and more stable than those from more conventional atlas-based registration approaches. The simplicity of the regressor’s context-rich visual features yield typical run-times of only 4 seconds per volume. This anatomy recognition algorithm is now part of the commercial product Microsoft Amalga Unified Intelligence System.