Spine detection in CT and MR using iterated marginal space learning

• Published in: Medical image analysis 2013-12, Vol.17 (8), p.1283-1292
• Main Authors: Michael Kelm, B., Wels, Michael, Kevin Zhou, S., Seifert, Sascha, Suehling, Michael, Zheng, Yefeng, Comaniciu, Dorin
• Format: Article
• Language: English
• Subjects: Algorithms; Generative-discriminative detection; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Magnetic Resonance Imaging - methods; Marginal space learning; Pattern Recognition, Automated - methods; Regression Analysis; Reproducibility of Results; Sensitivity and Specificity; Spinal disk segmentation; Spinal Neoplasms - diagnosis; Spine - diagnostic imaging; Spine - pathology; Spine detection; Tomography, X-Ray Computed - methods; Vertebra segmentation
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2012.09.007

[Display omitted] ► We present a learning-based approach that works on CT and MR alike. ► A novel iterative extension of marginal space learning is proposed. ► A novel probabilistic prior on spinal disk position, orientation and scale is used. ► An adaptive segmentation approach, robust towards pathologies and degenerations. ► Competitive detection rates, accuracy and computational speed are achieved. Examinations of the spinal column with both, Magnetic Resonance (MR) imaging and Computed Tomography (CT), often require a precise three-dimensional positioning, angulation and labeling of the spinal disks and the vertebrae. A fully automatic and robust approach is a prerequisite for an automated scan alignment as well as for the segmentation and analysis of spinal disks and vertebral bodies in Computer Aided Diagnosis (CAD) applications. In this article, we present a novel method that combines Marginal Space Learning (MSL), a recently introduced concept for efficient discriminative object detection, with a generative anatomical network that incorporates relative pose information for the detection of multiple objects. It is used to simultaneously detect and label the spinal disks. While a novel iterative version of MSL is used to quickly generate candidate detections comprising position, orientation, and scale of the disks with high sensitivity, the anatomical network selects the most likely candidates using a learned prior on the individual nine dimensional transformation spaces. Finally, we propose an optional case-adaptive segmentation approach that allows to segment the spinal disks and vertebrae in MR and CT respectively. Since the proposed approaches are learning-based, they can be trained for MR or CT alike. Experimental results based on 42 MR and 30 CT volumes show that our system not only achieves superior accuracy but also is among the fastest systems of its kind in the literature. On the MR data set the spinal disks of a whole spine are detected in 11.5s on average with 98.6% sensitivity and 0.073 false positive detections per volume. On the CT data a comparable sensitivity of 98.0% with 0.267 false positives is achieved. Detected disks are localized with an average position error of 2.4mm/3.2mm and angular error of 3.9°/4.5° in MR/CT, which is close to the employed hypothesis resolution of 2.1mm and 3.3°.