Automatic bone detection and soft tissue aware ultrasound–CT registration for computer-aided orthopedic surgery

PurposeThe transfer of preoperative CT data into the tracking system coordinates within an operating room is of high interest for computer-aided orthopedic surgery. In this work, we introduce a solution for intra-operative ultrasound–CT registration of bones.MethodsWe have developed methods for fully automatic real-time bone detection in ultrasound images and global automatic registration to CT. The bone detection algorithm uses a novel bone-specific feature descriptor and was thoroughly evaluated on both in-vivo and ex-vivo data. A global optimization strategy aligns the bone surface, followed by a soft tissue aware intensity-based registration to provide higher local registration accuracy.ResultsWe evaluated the system on femur, tibia and fibula anatomy in a cadaver study with human legs, where magnetically tracked bone markers were implanted to yield ground truth information. An overall median system error of $$3.7$$3.7 mm was achieved on 11 datasets.ConclusionGlobal and fully automatic registration of bones aquired with ultrasound to CT is feasible, with bone detection and tracking operating in real time for immediate feedback to the surgeon.

[1]  Nassir Navab,et al.  Entropy and Laplacian images: Structural representations for multi-modal registration , 2012, Medical Image Anal..

[2]  Antony J. Hodgson,et al.  Towards Real-Time 3D US to CT Bone Image Registration Using Phase and Curvature Feature Based GMM Matching , 2011, MICCAI.

[3]  Nassir Navab,et al.  Ultrasound confidence maps using random walks , 2012, Medical Image Anal..

[4]  Frank Langlotz,et al.  Automated bone contour detection in ultrasound B‐mode images for minimally invasive registration in computer‐assisted surgery—an in vitro evaluation , 2007, The international journal of medical robotics + computer assisted surgery : MRCAS.

[5]  Nassir Navab,et al.  Automatic CT-ultrasound registration for diagnostic imaging and image-guided intervention , 2008, Medical Image Anal..

[6]  David J. Hawkes,et al.  Registration of freehand 3D ultrasound and magnetic resonance liver images , 2004, Medical Image Anal..

[7]  Nassir Navab,et al.  Ultrasound bone detection using patient-specific CT prior , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  David J. Hawkes,et al.  Cadaver Validation of Intensity-Based Ultrasound to CT Registration , 2005, MICCAI.

[9]  Michael Brady,et al.  MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration , 2012, Medical Image Anal..

[10]  M. Ali,et al.  Some Variants of the Controlled Random Search Algorithm for Global Optimization , 2006 .

[11]  Antony J. Hodgson,et al.  3D Ultrasound-CT Registration in Orthopaedic Trauma Using GMM Registration with Optimized Particle Simulation-Based Data Reduction , 2012, MICCAI.

[12]  Russell H. Taylor,et al.  Understanding bone responses in B-mode ultrasound images and automatic bone surface extraction using a Bayesian probabilistic framework , 2004, SPIE Medical Imaging.

[13]  Nicholas Ayache,et al.  Rigid registration of 3-D ultrasound with MR images: a new approach combining intensity and gradient information , 2001, IEEE Transactions on Medical Imaging.

[14]  David J. Hawkes,et al.  Self-calibrating 3D-ultrasound-based bone registration for minimally invasive orthopedic surgery , 2006, IEEE Transactions on Medical Imaging.

[15]  Gabor Fichtinger,et al.  Biomechanically constrained groupwise ultrasound to CT registration of the lumbar spine , 2012, Medical Image Anal..

[16]  Robert Rohling,et al.  Bone Segmentation and Fracture Detection in Ultrasound Using 3D Local Phase Features , 2008, MICCAI.

[17]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Klaus J. Kirchberg,et al.  Robust Face Detection Using the Hausdorff Distance , 2001, AVBPA.