Timo Kohlberger

Automatic multi-organ segmentation using learning-based segmentation and level set optimization

We present a novel generic segmentation system for the fully automatic multi-organ segmentation from CT medical images. Thereby we combine the advantages of learning-based approaches on point cloud-based shape representation, such a speed, robustness, point correspondences, with those of PDE-optimization-based level set approaches, such as high accuracy and the straightforward prevention of segment overlaps. In a benchmark on 10-100 annotated datasets for the liver, the lungs, and the kidneys we show that the proposed system yields segmentation accuracies of 1.17-2.89 mm average surface errors. Thereby the level set segmentation (which is initialized by the learning-based segmentations) contributes with an 20%-40% increase in accuracy.

4D shape priors for a level set segmentation of the left myocardium in SPECT sequences

We develop a 4D (3D plus time) statistical shape model for implicit level set based shape representations. To this end, we represent hand segmented training sequences of the left ventricle by respective 4-dimensional embedding functions and approximate these by a principal component analysis. In contrast to recent 4D models on explicit shape representations, the implicit shape model developed in this work does not require the computation of point correspondences which is known to be quite challenging, especially in higher dimensions. Experimental results on the segmentation of SPECT sequences of the left myocardium confirm that the 4D shape model outperforms respective 3D models, because it takes into account a statistical model of the temporal shape evolution.

Evaluating segmentation error without ground truth

The automatic delineation of the boundaries of organs and other anatomical structures is a key component of many medical image processing systems. In this paper we present a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overlap error and Dice coefficient of an arbitrary organ segmentation without knowing the ground truth delineation. We show the regressor to be much stronger a predictor of these error metrics than the responses of probabilistic boosting classifiers trained on the segmentation boundary. The presented approach not only allows us to build reliable confidence measures and fidelity checks, but also to rank several segmentation hypotheses against each other during online usage of the segmentation algorithm in clinical practice.

Multi-stage learning for robust lung segmentation in challenging CT volumes

Simple algorithms for segmenting healthy lung parenchyma in CT are unable to deal with high density tissue common in pulmonary diseases. To overcome this problem, we propose a multi-stage learning-based approach that combines anatomical information to predict an initialization of a statistical shape model of the lungs. The initialization first detects the carina of the trachea, and uses this to detect a set of automatically selected stable landmarks on regions near the lung (e.g., ribs, spine). These landmarks are used to align the shape model, which is then refined through boundary detection to obtain fine-grained segmentation. Robustness is obtained through hierarchical use of discriminative classifiers that are trained on a range of manually annotated data of diseased and healthy lungs. We demonstrate fast detection (35s per volume on average) and segmentation of 2 mm accuracy on challenging data.

Organ Segmentation with Level Sets Using Local Shape and Appearance Priors

Organ segmentation is a challenging problem on which recent progress has been made by incorporation of local image statistics that model the heterogeneity of structures outside of an organ of interest. However, most of these methods rely on landmark based segmentation, which has certain drawbacks. We propose to perform organ segmentation with a novel level set algorithm that incorporates local statistics via a highly efficient point tracking mechanism. Specifically, we compile statistics on these tracked points to allow for a local intensity profile outside of the contour and to allow for a local surface area penalty, which allows us to capture fine detail where it is expected. The local intensity and curvature models are learned through landmarks automatically embedded on the surface of the training shapes. We use Parzen windows to model the internal organ intensities as one distribution since this is sufficient for most organs. In addition, since the method is based on level sets, we are able to naturally take advantage of recent work on global shape regularization. We show state-of-the-art results on the challenging problems of liver and kidney segmentation.

Precise segmentation of multiple organs in CT volumes using learning-based approach and information theory

In this paper, we present a novel method by incorporating information theory into the learning-based approach for automatic and accurate pelvic organ segmentation (including the prostate, bladder and rectum). We target 3D CT volumes that are generated using different scanning protocols (e.g., contrast and non-contrast, with and without implant in the prostate, various resolution and position), and the volumes come from largely diverse sources (e.g., diseased in different organs). Three key ingredients are combined to solve this challenging segmentation problem. First, marginal space learning (MSL) is applied to efficiently and effectively localize the multiple organs in the largely diverse CT volumes. Second, learning techniques, steerable features, are applied for robust boundary detection. This enables handling of highly heterogeneous texture pattern. Third, a novel information theoretic scheme is incorporated into the boundary inference process. The incorporation of the Jensen-Shannon divergence further drives the mesh to the best fit of the image, thus improves the segmentation performance. The proposed approach is tested on a challenging dataset containing 188 volumes from diverse sources. Our approach not only produces excellent segmentation accuracy, but also runs about eighty times faster than previous state-of-the-art solutions. The proposed method can be applied to CT images to provide visual guidance to physicians during the computer-aided diagnosis, treatment planning and image-guided radiotherapy to treat cancers in pelvic region.

Automatic Segmentation of Unknown Objects, with Application to Baggage Security

Computed tomography (CT) is used widely to image patients for medical diagnosis and to scan baggage for threatening materials. Automated reading of these images can be used to reduce the costs of a human operator, extract quantitative information from the images or support the judgements of a human operator. Object quantification requires an image segmentation to make measurements about object size, material composition and morphology. Medical applications mostly require the segmentation of prespecified objects, such as specific organs or lesions, which allows the use of customized algorithms that take advantage of training data to provide orientation and anatomical context of the segmentation targets. In contrast, baggage screening requires the segmentation algorithm to provide segmentation of an unspecified number of objects with enormous variability in size, shape, appearance and spatial context. Furthermore, security systems demand 3D segmentation algorithms that can quickly and reliably detect threats. To address this problem, we present a segmentation algorithm for 3D CT images that makes no assumptions on the number of objects in the image or on the composition of these objects. The algorithm features a new Automatic QUality Measure (AQUA) model that measures the segmentation confidence for any single object (from any segmentation method) and uses this confidence measure to both control splitting and to optimize the segmentation parameters at runtime for each dataset. The algorithm is tested on 27 bags that were packed with a large variety of different objects.

Luggage visualization and virtual unpacking

We present a system for luggage visualization where any object is clearly distinguishable from its neighbors. It supports virtual unpacking by visually moving any object away from its original pose. To achieve these, we first apply a volume segmentation guided by a confidence measure that recursively splits connected regions until semantically meaningful objects are obtained, and a label volume whose voxels specifying the object IDs is generated. The original luggage dataset and the label volume are visualized by volume rendering. Through an automatic coloring algorithm, any pair of objects whose projections are adjacent in an image are assigned distinct hues that are modulated onto a transfer function to both reduce rendering cost as well as to improve the smoothness across object boundaries. We have designed a layered framework to efficiently render a scene mixed with packed luggage, animated unpacking objects, and already unpacked objects put aside for further inspection. The system uses GPU to quickly select unpackable objects that are not blocked by others to make the unpacking plausible.

Advanced level set segmentation of the right atrium in MR

Atrial fibrillation is a common heart arrhythmia, and can be effectively treated with ablation. Ablation planning requires 3D models of the patients left atrium (LA) and/or right atrium (RA), therefore an automatic segmentation procedure to retrieve these models is desirable. In this study, we investigate the use of advanced level set segmentation approaches to automatically segment RA in magnetic resonance angiographic (MRA) volume images. Low contrast to noise ratio makes the boundary between the RA and the nearby structures nearly indistinguishable. Therefore, pure data driven segmentation approaches such as watershed and ChanVese methods are bound to fail. Incorporating training shapes through PCA modeling to constrain the segmentation is one popular solution, and is also used in our segmentation framework. The shape parameters from PCA are optimized with a global histogram based energy model. However, since the shape parameters span a much smaller space, it can not capture fine details of the shape. Therefore, we employ a second refinement step after the shape based segmentation stage, which follows closely the recent work of localized appearance model based techniques. The local appearance model is established through a robust point tracking mechanism and is learned through landmarks embedded on the surface of training shapes. The key contribution of our work is the combination of a statistical shape prior and a localized appearance prior for level set segmentation of the right atrium from MRA. We test this two step segmentation framework on porcine RA to verify the algorithm.

Soft level set coupling for LV segmentation in gated perfusion SPECT

We present a new segmentation approach for the myocardium in gated and non-gated perfusion SPECT images. To this end, we represent the epi- and endocardium by separate signed distance functions and couple them by a soft constraint to give explicit control over the wall thickness. By an explicit modeling of the basal plane, the volume of the blood pool as well as the myocardium are determinable. Furthermore, prior shape information is incorporated by applying a kernel density estimation on a number of expert segmentations in a low-dimensional PCA subspace. Thereby, information along the time axis is fully taken into account by employing 4-dimensional embedding functions.