Expectation Conditional Maximization-Based Deformable Shape Registration

This paper addresses the issue of matching statistical and non-rigid shapes, and introduces an Expectation Conditional Maximization-based deformable shape registration (ECM-DSR) algorithm. Similar to previous works, we cast the statistical and non-rigid shape registration problem into a missing data framework and handle the unknown correspondences with Gaussian Mixture Models (GMM). The registration problem is then solved by fitting the GMM centroids to the data. But unlike previous works where equal isotropic covariances are used, our new algorithm uses heteroscedastic covariances whose values are iteratively estimated from the data. A previously introduced virtual observation concept is adopted here to simplify the estimation of the registration parameters. Based on this concept, we derive closed-form solutions to estimate parameters for statistical or non-rigid shape registrations in each iteration. Our experiments conducted on synthesized and real data demonstrate that the ECM-DSR algorithm has various advantages over existing algorithms.

Assessing stool quantities generated by three specific Kato-Katz thick smear templates employed in different settings.

BACKGROUND The Kato-Katz technique is recommended for the diagnosis of helminth infections in epidemiological surveys, drug efficacy studies and monitoring of control interventions. We assessed the comparability of the average amount of faeces generated by three Kato-Katz templates included in test kits from two different providers. METHODS Nine hundred Kato-Katz thick smear preparations were done; 300 per kit. Empty slides, slides plus Kato-Katz template filled with stool and slides plus stool after careful removal of the template were weighed to the nearest 0.1 mg. The average amount of stool that was generated on the slide was calculated for each template, stratified by standard categories of stool consistency (i.e. mushy, soft, sausage-shaped, hard and clumpy). RESULTS The average amount of stool generated on slides was 40.7 mg (95 % confidence interval (CI): 40.0-41.4 mg), 40.3 mg (95 % CI: 39.7-40.9 mg) and 42.8 mg (95 % CI: 42.2-43.3 mg) for the standard Vestergaard Frandsen template, and two different templates from the Chinese Center for Disease Control and Prevention (China CDC), respectively. Mushy stool resulted in considerably lower average weights when the Vestergaard Frandsen (37.0 mg; 95 % CI: 34.9-39.0 mg) or new China CDC templates (37.4 mg; 95 % CI: 35.9-38.9 mg) were used, compared to the old China CDC template (42.2 mg; 95 % CI: 40.7-43.7 mg) and compared to other stool consistency categories. CONCLUSION The average amount of stool generated by three specific Kato-Katz templates was similar (40.3-42.8 mg). Since the multiplication factor is somewhat arbitrary and small changes only have little effect on infection intensity categories, it is suggested that the standard multiplication factor of 24 should be kept for the calculation of eggs per gram of faeces for all investigated templates.

Single fluoroscopic image based 2D/3D reconstruction of a scaled, patient-specific vertebral model

Purpose Accurate three-dimensional (3D) models of lumbar vertebrae can enable image-based 3D kinematic analysis. The common approach to derive 3D models is by direct segmentation of CT or MRI datasets. However, these have the disadvantages that they are expensive, timeconsuming and/or induce high-radiation doses to the patient. In this study, we present a technique to automatically reconstruct a scaled 3D lumbar vertebral model from a single two-dimensional (2D) lateral fluoroscopic image. Methods Our technique is based on a hybrid 2D/3D deformable registration strategy combining a landmark-to-ray registration with a statistical shape model-based 2D/3D reconstruction scheme. Fig. 1 shows different stages of the reconstruction process. Four cadaveric lumbar spine segments (total twelve lumbar vertebrae) were used to validate the technique. To evaluate the reconstruction accuracy, the surface models reconstructed from the lateral fluoroscopic images were compared to the associated ground truth data derived from a 3D CT-scan reconstruction technique. For each case, a surface-based matching was first used to recover the scale and the rigid transformation between the reconstructed surface model Results Our technique could successfully reconstruct 3D surface models of all twelve vertebrae. After recovering the scale and the rigid transformation between the reconstructed surface models and the ground truth models, the average error of the 2D/3D surface model reconstruction over the twelve lumbar vertebrae was found to be 1.0 mm. The errors of reconstructing surface models of all twelve vertebrae are shown in Fig. 2. It was found that the mean errors of the reconstructed surface models in comparison to their associated ground truths after iterative scaled rigid registrations ranged from 0.7 mm to 1.3 mm and the rootmean squared (RMS) errors ranged from 1.0 mm to 1.7 mm. The average mean reconstruction error was found to be 1.0 mm. Conclusion An accurate, scaled 3D reconstruction of the lumbar vertebra can be obtained from a single lateral fluoroscopic image using a statistical shape model based 2D/3D reconstruction technique. Future work will focus on applying the reconstructed model for 3D kinematic analysis of lumbar vertebrae, an extension of our previously-reported imagebased kinematic analysis. The developed method also has potential applications in surgical planning and navigation.