Fast Multiple Organ Detection and Localization in Whole-Body MR Dixon Sequences

Abstract

Abstract. Automatic localization of multiple anatomical structures in medical images provides important semantic information with potential benefits to diverse clinical applications. Aiming at organ-specific attenuation correction in PET/MR imaging, we propose an efficient approach for estimating location and size of multiple anatomical structures in MR scans. Our contribution is three-fold: (1) we apply supervised regression techniques to the problem of anatomy detection and localization in whole-body MR, (2) we adapt random ferns to produce multidimensional regression output and compare them with random regression forests, and (3) introduce the use of 3D LBP descriptors in multi-channel MR Dixon sequences. The localization accuracy achieved with both fern-and forest-based approaches is evaluated by direct comparison with state of the art atlas-based registration, on ground-truth data from 33 patients. Our results demonstrate improved anatomy localization accuracy with higher efficiency and robustness.

Automatic Detection and Segmentation of Kidneys in 3D CT Images Using Random Forests

“…Regression-based techniques do not require an exhaustive search of parameters. Other regressors such as regression forests and random ferns have also been proposed [13,14].…”

Anatomical Landmark Detection Using Nearest Neighbor Matching and Submodular Optimization

“…In [10], shape regression machine is proposed to learn a boosting regression function to predict the object bounding box from the image appearance bounded in an arbitrarily located box and another regression function to predict the object shape. Pauly et al [3] simultaneously regress out the locations and sizes of multiple organs with confidence scores using a learned Random Forest regressor. To some extent, image registration [11] can be regarded as using the holistic context too.…”

“…Landmarks also provide seed points to initiate image segmentation [1] and registration [2]. In seminar reporting, the detected organ landmarks can help config the optimal intensity window for display [3] and offer the text tooltips for structures in the scan [4].…”

Scale-Adaptive Forest Training via an Efficient Feature Sampling Scheme

“…Recent applications of the forest framework to the medical field include multi-organ segmentation within computed tomography (CT) volumes [3], segmentation of the midbrain in transcranial ultrasound volumes [4], multi-organ localization in magnetic resonance (MR) [5] and CT [6] data, semantic labeling of brain structures in MR scans [7], depth video classification to quantify the progression of multiple sclerosis [8], and localization of anatomical landmarks within hand MR scans [9].…”

“…Our approach builds on the generic Haar-like features [12] which demonstrated lately high performance for a variety of medical objectives and imaging modalities [3][4][5][6][7][8][9]. Instead of sampling Haar-like features uniformly at each node, we sample them sequentially in a fine-to-coarse fashion.…”