M. de Bruijne

Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge

EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform for fair and meaningful comparison of registration algorithms which are applied to a database of intra patient thoracic CT image pairs. Evaluation of nonrigid registration techniques is a nontrivial task. This is compounded by the fact that researchers typically test only on their own data, which varies widely. For this reason, reliable assessment and comparison of different registration algorithms has been virtually impossible in the past. In this work we present the results of the launch phase of EMPIRE10, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups. All algorithms are applied to the same set of 30 thoracic CT pairs. Algorithm settings and parameters are chosen by researchers expert in the con figuration of their own method and the evaluation is independent, using the same criteria for all participants. All results are published on the EMPIRE10 website (http://empire10.isi.uu.nl). The challenge remains ongoing and open to new participants. Full results from 24 algorithms have been published at the time of writing. This paper details the organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms. The gain in knowledge and future work are discussed.

2D-3D shape reconstruction of the distal femur from stereo X-ray imaging using statistical shape models.

Three-dimensional patient specific bone models are required in a range of medical applications, such as pre-operative surgery planning and improved guidance during surgery, modeling and simulation, and in vivo bone motion tracking. Shape reconstruction from a small number of X-ray images is desired as it lowers both the acquisition costs and the radiation dose compared to CT. We propose a method for pose estimation and shape reconstruction of 3D bone surfaces from two (or more) calibrated X-ray images using a statistical shape model (SSM). User interaction is limited to manual initialization of the mean shape. The proposed method combines a 3D distance based objective function with automatic edge selection on a Canny edge map. Landmark-edge correspondences are weighted based on the orientation difference of the projected silhouette and the corresponding image edge. The method was evaluated by rigid pose estimation of ground truth shapes as well as 3D shape estimation using a SSM of the whole femur, from stereo cadaver X-rays, in vivo biplane fluoroscopy image-pairs, and an in vivo biplane fluoroscopic sequence. Ground truth shapes for all experiments were available in the form of CT segmentations. Rigid registration of the ground truth shape to the biplane fluoroscopy achieved sub-millimeter accuracy (0.68mm) measured as root mean squared (RMS) point-to-surface (P2S) distance. The non-rigid reconstruction from the biplane fluoroscopy using the SSM also showed promising results (1.68mm RMS P2S). A feasibility study on one fluoroscopic time series illustrates the potential of the method for motion and shape estimation from fluoroscopic sequences with minimal user interaction.

Image segmentation by shape particle filtering

Statistical appearance models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but cannot cope with local appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required. We propose a shape inference method that is based on pixel classification, so that local and non-linear intensity variations are dealt with naturally, while a global shape model ensures a consistent segmentation. Optimization by stochastic sampling removes the need for accurate initialization. The method is demonstrated on vertebra segmentation in spine radiographs. Segmentation errors are below 2 mm in 88 out of 91 cases, with an average error of 1.4 mm.

Reirradiation combined with hyperthermia in breast cancer recurrences: overview of experience in Erasmus MC.

For superficial hyperthermia a custom-built multi-applicator multi-amplifier superficial hyperthermia system operating at 433 MHz is utilised. Up to 6 Lucite Cone applicators can be used simultaneously to treat an area of 600 cm2. Temperatures are measured continuously with fibre optic multi-sensor probes. For patients with non-standard clinical problems, hyperthermia treatment planning is used to support decision making with regard to treatment strategy. In 74% of our patients with recurrent breast cancer treated with a reirradiation scheme of 8 fractions of 4 Gy in 4 weeks, combined with 4 or 8 hyperthermia treatments, a complete response is achieved, approximately twice as high as the CR rate following the same reirradation alone. The CR rate in tumours smaller than 30 mm is 80–90%, for larger tumours it is 65%. Hyperthermia appears beneficial for patients with microscopic residual tumour as well. To achieve high CR rates it is important to heat the whole radiotherapy field, and to use an adequate heating technique.

Texture-Based Analysis of COPD: A Data-Driven Approach

This study presents a fully automatic, data-driven approach for texture-based quantitative analysis of chronic obstructive pulmonary disease (COPD) in pulmonary computed tomography (CT) images. The approach uses supervised learning where the class labels are, in contrast to previous work, based on measured lung function instead of on manually annotated regions of interest (ROIs). A quantitative measure of COPD is obtained by fusing COPD probabilities computed in ROIs within the lung fields where the individual ROI probabilities are computed using a k nearest neighbor (kNN ) classifier. The distance between two ROIs in the kNN classifier is computed as the textural dissimilarity between the ROIs, where the ROI texture is described by histograms of filter responses from a multi-scale, rotation invariant Gaussian filter bank. The method was trained on 400 images from a lung cancer screening trial and subsequently applied to classify 200 independent images from the same screening trial. The texture-based measure was significantly better at discriminating between subjects with and without COPD than were the two most common quantitative measures of COPD in the literature, which are based on density. The proposed measure achieved an area under the receiver operating characteristic curve (AUC) of 0.713 whereas the best performing density measure achieved an AUC of 0.598. Further, the proposed measure is as reproducible as the density measures, and there were indications that it correlates better with lung function and is less influenced by inspiration level.

Development of a guideline for the water bolus temperature in superficial hyperthermia

Purpose: The research presented in this work investigates the influence of the water bolus temperature on temperature distributions in tissue during superficial hyperthermia treatments using Lucite cone applicators. The goal of the research was to develop a guideline for the selection of the water bolus temperature based on 3-D electromagnetic and thermal modelling. Methods: A 3-D model was set up to simulate an abstraction of the treatment. In the model a convection coefficient for the water bolus to skin surface was employed. In order to simulate the heat balance as realistically as possible, convection coefficients were measured for different water boluses and ranged from 70–152 W (m2 K)−1. The model was evaluated by simulating three clinical treatments and comparing the outcome of the model to the clinical measurements. Results: The model was found to predict the temperature distribution well on a global view; root mean square errors between 0.66–1.5°C were found for the three treatments. For some temperature probes a deviation of 1.5–2.0°C between measured and predicted temperature was found. These large deviations can be explained by local variations in cooling by blood vessels, tissue inhomogeneity, a varying convection coefficient of the water bolus and of course the complexity of the anatomy. Conclusions: The model was used to set up guidelines for the water bolus temperature selection in clinical practice for the target depths and applicator arrays used in the Rotterdam Erasmus Medical Center.

Automated Brain Structure Segmentation Based on Atlas Registration and Appearance Models

Accurate automated brain structure segmentation methods facilitate the analysis of large-scale neuroimaging studies. This work describes a novel method for brain structure segmentation in magnetic resonance images that combines information about a structures location and appearance. The spatial model is implemented by registering multiple atlas images to the target image and creating a spatial probability map. The structures appearance is modeled by a classifier based on Gaussian scale-space features. These components are combined with a regularization term in a Bayesian framework that is globally optimized using graph cuts. The incorporation of the appearance model enables the method to segment structures with complex intensity distributions and increases its robustness against errors in the spatial model. The method is tested in cross-validation experiments on two datasets acquired with different magnetic resonance sequences, in which the hippocampus and cerebellum were segmented by an expert. Furthermore, the method is compared to two other segmentation techniques that were applied to the same data. Results show that the atlas- and appearance-based method produces accurate results with mean Dice similarity indices of 0.95 for the cerebellum, and 0.87 for the hippocampus. This was comparable to or better than the other methods, whereas the proposed technique is more widely applicable and robust.

Effects of waterbolus size, shape and configuration on the SAR distribution pattern of the Lucite cone applicator

The effects of waterbolus dimensions and configuration on the effective field size (EFS) of the Lucite cone applicator (LCA) for superficial hyperthermia are presented. The goal of the research is to develop guidelines which mark out a sub-set of optimal LCA-waterbolus set-ups. The effects of variations in (i) waterbolus thickness, (ii) waterbolus area, (iii) waterbolus length/width ratio and (iv) eccentric placement of the applicator have been investigated in an FDTD model study. The prominent effects are verified with IR thermography measurements. An optimal EFS value of 80 cm2 is found for waterbolus area of 200–400 cm2. A small (10 × 10 cm2) waterbolus area restricts the EFS to 25% of the optimal value. The sensitivity to sub-optimal waterbolus area and length/width ratio increases with waterbolus height. Eccentric placement of the LCA near the waterbolus edge reduces the EFS to up to 50% of the optimal value. The IR measurements confirm the model findings. Based on the results, the following guidelines for the clinical application of the LCA have been defined: the waterbolus (i) should extend the LCA aperture at least 2.5 cm, especially at the Lucite windows, and (ii) the height should not exceed 2 cm.

Robust Shape Regression for Supervised Vessel Segmentation and its Application to Coronary Segmentation in CTA

This paper presents a vessel segmentation method which learns the geometry and appearance of vessels in medical images from annotated data and uses this knowledge to segment vessels in unseen images. Vessels are segmented in a coarse-to-fine fashion. First, the vessel boundaries are estimated with multivariate linear regression using image intensities sampled in a region of interest around an initialization curve. Subsequently, the position of the vessel boundary is refined with a robust nonlinear regression technique using intensity profiles sampled across the boundary of the rough segmentation and using information about plausible cross-sectional vessel shapes. The method was evaluated by quantitatively comparing segmentation results to manual annotations of 229 coronary arteries. On average the difference between the automatically obtained segmentations and manual contours was smaller than the inter-observer variability, which is an indicator that the method outperforms manual annotation. The method was also evaluated by using it for centerline refinement on 24 publicly available datasets of the Rotterdam Coronary Artery Evaluation Framework. Centerlines are extracted with an existing method and refined with the proposed method. This combination is currently ranked second out of 10 evaluated interactive centerline extraction methods. An additional qualitative expert evaluation in which 250 automatic segmentations were compared to manual segmentations showed that the automatically obtained contours were rated on average better than manual contours.

Benefits of superficial hyperthermia treatment planning: Five case studies

Purpose: To demonstrate the benefits of treatment planning in superficial hyperthermia. Materials and methods: Five patient cases are presented, in which treatment planning was applied to troubleshoot treatment-limiting hotspots, to select the optimum applicator type and orientation, to assess the risk associated with metallic implants, to assess the feasibility of heating a deeper seated tumour, and to analyse the effective SAR coverage resulting from arrays of multiple incoherent applicators. FDTD simulation tools were used to investigate treatment options, either based on segmented or simplified anatomies. Results: The background, approach and model implementation are presented per case. SAR cross-sections, profiles and isosurfaces are visualized to predict the effective SAR coverage of the target and the location of the maximum power absorption. In addition, the followed treatment strategy and the implications for the clinical treatment are given: for example, higher temperatures, relief of treatment limiting hot-spots or increased power input. Conclusions: Treatment planning in superficial hyperthermia can be applied to improve clinical routine. Its application supports the selection of the optimum technique in non-standard cases, leading to direct benefits for the patient. In addition, treatment planning has shown to be an excellent tool for education and training for hyperthermia technicians and physicians.