Heiko Seim

Automatic segmentation of the pelvic bones from CT data based on a statistical shape model

We present an algorithm for automatic segmentation of the human pelvic bones from CT datasets that is based on the application of a statistical shape model. The proposed method is divided into three steps: 1) The averaged shape of the pelvis model is initially placed within the CT data using the Generalized Hough Transform, 2) the statistical shape model is then adapted to the image data by a transformation and variation of its shape modes, and 3) a final free-form deformation step based on optimal graph searching is applied to overcome the restrictive character of the statistical shape representation. We thoroughly evaluated the method on 50 manually segmented CT datasets by performing a leave-one-out study. The Generalized Hough Transform proved to be a reliable method for an automatic initial placement of the shape model within the CT data. Compared to the manual gold standard segmentations, our automatic segmentation approach produced an average surface distance of 1.2 ± 0.3mm after the adaptation of the statistical shape model, which could be reduced to 0.7±0.3mm using a final free-form deformation step. Together with an average segmentation time of less than 5 minutes, the results of our study indicate that our method meets the requirements of clinical routine.

3D reconstruction of the human rib cage from 2D projection images using a statistical shape model

PurposeThis paper describes an approach for the three-dimensional (3D) shape and pose reconstruction of the human rib cage from few segmented two-dimensional (2D) projection images. Our work is aimed at supporting temporal subtraction techniques of subsequently acquired radiographs by establishing a method for the assessment of pose differences in sequences of chest radiographs of the same patient.MethodsThe reconstruction method is based on a 3D statistical shape model (SSM) of the rib cage, which is adapted to binary 2D projection images of an individual rib cage. To drive the adaptation we minimize a distance measure that quantifies the dissimilarities between 2D projections of the 3D SSM and the projection images of the individual rib cage. We propose different silhouette-based distance measures and evaluate their suitability for the adaptation of the SSM to the projection images.ResultsAn evaluation was performed on 29 sets of biplanar binary images (posterior–anterior and lateral). Depending on the chosen distance measure, our experiments on the combined reconstruction of shape and pose of the rib cages yield reconstruction errors from 2.2 to 4.7mm average mean 3D surface distance. Given a geometry of an individual rib cage, the rotational errors for the pose reconstruction range from 0.1° to 0.9°.ConclusionsThe results show that our method is suitable for the estimation of pose differences of the human rib cage in binary projection images. Thus, it is able to provide crucial 3D information for registration during the generation of 2D subtraction images.

Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data

The exact localization of the mandibular nerve with respect to the bone is important for applications in dental implantology and maxillofacial surgery. Cone beam computed tomography (CBCT), often also called digital volume tomography (DVT), is increasingly utilized in maxillofacial or dental imaging. Compared to conventional CT, however, soft tissue discrimination is worse due to a reduced dose. Thus, small structures like the alveolar nerves are even harder recognizable within the image data. We show that it is nonetheless possible to accurately reconstruct the 3D bone surface and the course of the nerve in a fully automatic fashion, with a method that is based on a combined statistical shape model of the nerve and the bone and a Dijkstra-based optimization procedure. Our method has been validated on 106 clinical datasets: the average reconstruction error for the bone is 0.5 +/- 0.1 mm, and the nerve can be detected with an average error of 1.0 +/- 0.6 mm.

An Articulated Statistical Shape Model of the Human Knee

In this work we present an articulated statistical shape model (ASSM) of the human knee. The model incorporates statistical shape variation plus explicit degrees of freedom that model physiological joint motion. We also present a strategy for segmentation of the knee joint from medical image data. We show the potential of the model via an evaluation on a set of 40 clinical MRI datasets with manual expert segmentations available.

Segmentation of Bony Structures with Ligament Attachment Sites

This work presents an approach towards reconstructing ligament and tendon attachment sites from 3D medical image data. We apply statistical shape models with an additional free form step to reconstruct the anatomical shape of the distal femur from CT data. After the shape fitting process the locations of ligament attachment sites, which are incorporated in the geometric model, are extracted and their positions optimized via an image based approach. To show the potential of our method we manually extracted the surface of 11 distal femora and their corresponding ligament attachment sites in clinical CT data and compared them to the results of our method.

Automatic extraction of anatomical landmarks from medical image data: An evaluation of different methods

This work presents three different methods for automatic detection of anatomical landmarks in CT data, namely for the left and right anterior superior iliac spines and the pubic symphysis. The methods exhibit different degrees of generality in terms of portability to other anatomical landmarks and require a different amount of training data. The first method is problem-specific and is based on the convex hull of the pelvis. Method two is a more generic approach based on a statistical shape model including the landmarks of interest for every training shape. With our third method we present the most generic approach, where only a small set of training landmarks is required. Those landmarks are transferred to the patient specific geometry based on Mean Value Coordinates (MVCs). The methods work on surfaces of the pelvis that need to be extracted beforehand. We perform this geometry reconstruction with our previously introduced fully automatic segmentation framework for the pelvic bones. With a focus on the accuracy of our novel MVC-based approach, we evaluate and compare our methods on 100 clinical CT datasets, for which gold standard landmarks were defined manually by multiple observers.