Ultrasound Aided Vertebral Level Localization for Lumbar Surgery.

Localization of the correct vertebral level for surgical entry during lumbar hernia surgery is not straightforward. In this paper, we develop and evaluate a solution using free-hand 2-D ultrasound (US) imaging in the operation room (OR). Our system exploits the difference in spinous process shapes of the vertebrae. The spinous processes are pre-operatively outlined and labeled in a lateral lumbar X-ray of the patient. Then, in the OR the spinous processes are imaged with 2-D sagittal US, and are automatically segmented and registered with the X-ray shapes. After a small number of scanned vertebrae, the system robustly matches the shapes, and propagates the X-ray label to the US images. The main contributions of our work are: we propose a deep convolutional neural network-based bone segmentation algorithm from US imaging that outperforms state of the art methods in both performance and speed. We present a matching strategy that determines the levels of the spinal processes being imaged. And lastly, we evaluate the complete procedure on 19 clinical data sets from two hospitals, and two observers. The final labeling was correct in 92% of the cases, demonstrating the feasibility of US-based surgical entry point detection for spinal surgeries.

Random Forest-Based Bone Segmentation in Ultrasound.

Ultrasound (US) imaging is a safe alternative to radiography for guidance during minimally invasive orthopedic procedures. However, ultrasound is challenging to interpret because of the relatively low signal-to-noise ratio and its inherent speckle pattern that decreases image quality. Here we describe a method for automatic bone segmentation in 2-D ultrasound images using a patch-based random forest classifier and several ultrasound specific features, such as shadowing. We illustrate that existing shadow features are not robust to changes in US acquisition parameters, and propose a novel robust shadow feature. We evaluate the method on several US data sets and report that it favorably compares with existing techniques. We achieve a recall of 0.86 at a precision of 0.82 on a test set of 143 spinal US images.

3D/3D registration of coronary CTA and biplane XA reconstructions for improved image guidance.

PURPOSE: The authors aim to improve image guidance during percutaneous coronary interventions of chronic total occlusions (CTO) by providing information obtained from computed tomography angiography (CTA) to the cardiac interventionist. To this end, the authors investigate a method to register a 3D CTA model to biplane reconstructions. METHODS: The authors developed a method for registering preoperative coronary CTA with intraoperative biplane x-ray angiography (XA) images via 3D models of the coronary arteries. The models are extracted from the CTA and biplane XA images, and are temporally aligned based on CTA reconstruction phase and XA ECG signals. Rigid spatial alignment is achieved with a robust probabilistic point set registration approach using Gaussian mixture models (GMMs). This approach is extended by including orientation in the Gaussian mixtures and by weighting bifurcation points. The method is evaluated on retrospectively acquired coronary CTA datasets of 23 CTO patients for which biplane XA images are available. RESULTS: The Gaussian mixture model approach achieved a median registration accuracy of 1.7 mm. The extended GMM approach including orientation was not significantly different (P>0.1) but did improve robustness with regards to the initialization of the 3D models. CONCLUSIONS: The authors demonstrated that the GMM approach can effectively be applied to register CTA to biplane XA images for the purpose of improving image guidance in percutaneous coronary interventions.

Evaluation of automated statistical shape model based knee kinematics from biplane fluoroscopy.

State-of-the-art fluoroscopic knee kinematic analysis methods require the patient-specific bone shapes segmented from CT or MRI. Substituting the patient-specific bone shapes with personalizable models, such as statistical shape models (SSM), could eliminate the CT/MRI acquisitions, and thereby decrease costs and radiation dose (when eliminating CT). SSM based kinematics, however, have not yet been evaluated on clinically relevant joint motion parameters. Therefore, in this work the applicability of SSMs for computing knee kinematics from biplane fluoroscopic sequences was explored. Kinematic precision with an edge based automated bone tracking method using SSMs was evaluated on 6 cadaveric and 10 in-vivo fluoroscopic sequences. The SSMs of the femur and the tibia-fibula were created using 61 training datasets. Kinematic precision was determined for medial-lateral tibial shift, anterior-posterior tibial drawer, joint distraction-contraction, flexion, tibial rotation and adduction. The relationship between kinematic precision and bone shape accuracy was also investigated. The SSM based kinematics resulted in sub-millimeter (0.48-0.81mm) and approximately 1° (0.69-0.99°) median precision on the cadaveric knees compared to bone-marker-based kinematics. The precision on the in-vivo datasets was comparable to that of the cadaveric sequences when evaluated with a semi-automatic reference method. These results are promising, though further work is necessary to reach the accuracy of CT-based kinematics. We also demonstrated that a better shape reconstruction accuracy does not automatically imply a better kinematic precision. This result suggests that the ability of accurately fitting the edges in the fluoroscopic sequences has a larger role in determining the kinematic precision than that of the overall 3D shape accuracy.

Registration of 3D+t coronary CTA and monoplane 2D+t X-ray angiography.

A method for registering preoperative 3D+t coronary CTA with intraoperative monoplane 2D+t X-ray angiography images is proposed to improve image guidance during minimally invasive coronary interventions. The method uses a patient-specific dynamic coronary model, which is derived from the CTA scan by centerline extraction and motion estimation. The dynamic coronary model is registered with the 2D+t X-ray sequence, considering multiple X-ray time points concurrently, while taking breathing induced motion into account. Evaluation was performed on 26 datasets of 17 patients by comparing projected model centerlines with manually annotated centerlines in the X-ray images. The proposed 3D+t/2D+t registration method performed better than a 3D/2D registration method with respect to the accuracy and especially the robustness of the registration. Registration with a median error of 1.47 mm was achieved.

Regression-based cardiac motion prediction from single-phase CTA.

State of the art cardiac computed tomography (CT) enables the acquisition of imaging data of the heart over the entire cardiac cycle at concurrent high spatial and temporal resolution. However, in clinical practice, acquisition is increasingly limited to 3-D images. Estimating the shape of the cardiac structures throughout the entire cardiac cycle from a 3-D image is therefore useful in applications such as the alignment of preoperative computed tomography angiography (CTA) to intra-operative X-ray images for improved guidance in coronary interventions. We hypothesize that the motion of the heart is partially explained by its shape and therefore investigate the use of three regression methods for motion estimation from single-phase shape information. Quantitative evaluation on 150 4-D CTA images showed a small, but statistically significant, increase in the accuracy of the predicted shape sequences when using any of the regression methods, compared to shape-independent motion prediction by application of the mean motion. The best results were achieved using principal component regression resulting in point-to-point errors of 2.3±0.5 mm, compared to values of 2.7±0.6 mm for shape-independent motion estimation. Finally, we showed that this significant difference withstands small variations in important parameter settings of the landmarking procedure.

Comparison of shape regression methods under landmark position uncertainty.

Despite the growing interest in regression based shape estimation, no study has yet systematically compared different regression methods for shape estimation. We aimed to fill this gap by comparing linear regression methods with a special focus on shapes with landmark position uncertainties. We investigate two scenarios: In the first, the uncertainty of the landmark positions was similar in the training and test dataset, whereas in the second the uncertainty of the training and test data were different. Both scenarios were tested on simulated data and on statistical models of the left ventricle estimating the end-systolic shape from end-diastole with landmark uncertainties derived from the segmentation process, and of the femur estimating the 3D shape from one projection with landmark uncertainties derived from the imaging setup. Results show that in the first scenario linear regression methods tend to perform similar. In the second scenario including estimates of the test shape landmark uncertainty in the regression improved results.

Conditional shape models for cardiac motion estimation.

We propose a conditional statistical shape model to predict patient specific cardiac motion from the 3D end-diastolic CTA scan. The model is built from 4D CTA sequences by combining atlas based segmentation and 4D registration. Cardiac motion estimation is, for example, relevant in the dynamic alignment of pre-operative CTA data with intra-operative X-ray imaging. Due to a trend towards prospective electrocardiogram gating techniques, 4D imaging data, from which motion information could be extracted, is not commonly available. The prediction of motion from shape information is thus relevant for this purpose. Evaluation of the accuracy of the predicted motion was performed using CTA scans of 50 patients, showing an average accuracy of 1.1 mm.