This paper describes a framework for establishing a reference airway tree segmentation, which was used to quantitatively evaluate 15 different airway tree extraction algorithms in a standardized manner. Because of the sheer difficulty involved in manually constructing a complete reference standard from scratch, we propose to construct the reference using results from all algorithms that are to be evaluated. We start by subdividing each segmented airway tree into its individual branch segments. Each branch segment is then visually scored by trained observers to determine whether or not it is a correctly segmented part of the airway tree. Finally, the reference airway trees are constructed by taking the union of all correctly extracted branch segments. Fifteen airway tree extraction algorithms from different research groups are evaluated on a diverse set of 20 chest computed tomography (CT) scans of subjects ranging from healthy volunteers to patients with severe pathologies, scanned at different sites, with different CT scanner brands, models, and scanning protocols. Three performance measures covering different aspects of segmentation quality were computed for all participating algorithms. Results from the evaluation showed that no single algorithm could extract more than an average of 74% of the total length of all branches in the reference standard, indicating substantial differences between the algorithms. A fusion scheme that obtained superior results is presented, demonstrating that there is complementary information provided by the different algorithms and there is still room for further improvements in airway segmentation algorithms.

/pdf/extraction-of-airways-from-ct-exact-09-3csyoa7gg4.pdf

Extraction of Airways From CT (EXACT'09)

Visualization in Medicine is the first book on visualization and its application to problems in medical diagnosis, education, and treatment. The book describes the algorithms, the applications and their validation (how reliable are the results?), and the clinical evaluation of the applications (are the techniques useful?). It discusses visualization techniques from research literature as well as the compromises required to solve practical clinical problems. 

The book covers image acquisition, image analysis, and interaction techniques designed to explore and analyze the data. The final chapter shows how visualization is used for planning liver surgery, one of the most demanding surgical disciplines. The book is based on several years of the authors' teaching and research experience. Both authors have initiated and lead a variety of interdisciplinary projects involving computer scientists and medical doctors, primarily radiologists and surgeons.

* A core field of visualization and graphics missing a dedicated book until now
* Written by pioneers in the field and illustrated in full color
* Covers theory as well as practice

Visualization in Medicine: Theory, Algorithms, and Applications

Adaptive border marching algorithm: Automatic lung segmentation on chest CT images

Anatomy teaching is undergoing significant changes due to time constraints, limited availability of cadavers and technological developments in the areas of three-dimensional modelling and computer-assisted learning. This paper gives an overview of methods used to teach anatomy to undergraduate medical students and discusses the educational advantages and disadvantages of using three-dimensional computer models. A 'work in progress' account is then given of a project to develop two Web3D resources to enhance undergraduate tuition of the nervous system. Our approach is to support existing curricula using advanced modelling tools and a variety of delivery mechanisms. The first resource is a three-dimensional model of the adult brachial plexus: a network of nerves extending from the neck down to the shoulder, arm, hand, and fingers. This will be incorporated into existing didactic classroom teaching under the supervision of an anatomy teacher. The second resource is a piece of online courseware which will teach the embryological development of the brachial plexus. The delivery method will be the WebSET framework, a collaborative environment that allows a teacher to manipulate 3D models over the Web in real time whilst providing explanation and help to students. In this way the courseware can be used for both self-directed study and 'virtual anatomy demonstrations' within an online peer group.

Using multimedia and Web3D to enhance anatomy teaching

Although direct volume rendering is established as a powerful tool for the visualization of volumetric data, efficient and reliable feature detection is still an open topic. Usually, a tradeoff between fast but imprecise classification schemes and accurate but time-consuming segmentation techniques has to be made. Furthermore, the issue of uncertainty introduced with the feature detection process is completely neglected by the majority of existing approaches.In this paper we propose a guided probabilistic volume segmentation approach that focuses on the minimization of uncertainty. In an iterative process, our system continuously assesses uncertainty of a random walker-based segmentation in order to detect regions with high ambiguity, to which the user's attention is directed to support the correction of potential misclassifications. This reduces the risk of critical segmentation errors and ensures that information about the segmentation's reliability is conveyed to the user in a dependable way. In order to improve the efficiency of the segmentation process, our technique does not only take into account the volume data to be segmented, but also enables the user to incorporate classification information. An interactive workflow has been achieved by implementing the presented system on the GPU using the OpenCL API. Our results obtained for several medical data sets of different modalities, including brain MRI and abdominal CT, demonstrate the reliability and efficiency of our approach.

/pdf/uncertainty-aware-guided-volume-segmentation-3ejlfbqp3f.pdf

Uncertainty-Aware Guided Volume Segmentation

Segmentation of the tracheo-bronchial tree of the lungs is notoriously difficult. This is due to the fact that the small size of some of the anatomical structures is subject to partial volume effects. Furthermore, the limited intensity contrast between the participating materials (air, blood, and tissue) increases the segmentation of difficulties. In this paper, we propose a hybrid segmentation method which is based on a pipeline of three segmentation stages to extract the lower airways down to the seventh generation of the bronchi. User interaction is limited to the specification of a seed point inside the easily detectable trachea at the upper end of the lower airways. Similarly, the complementary vascular tree of the lungs can be segmented. Furthermore, we modified our virtual endoscopy system to visualize the vascular and airway system of the lungs along with other features, such as lung tumors.

Hybrid segmentation and exploration of the human lungs

In the visualization of 3D medical data, the appropriateness of the achieved result is highly dependent on the application. Therefore, an intuitive interaction with the user is of utter importance in order to determine the particular aim of the visualization. In this paper, we present a novel approach for the visualization of 3D medical data with volume rendering combined with AR-based user interaction. The utilization of augmented reality (AR), with the assistance of a set of simple tools, allows the direct manipulation in 3D of the rendered data. The proposed method takes into account regions of interest defined by the user and employs this information to automatically generate an adequate transfer function. Machine learning techniques are utilized for the automatic creation of transfer functions, which are to be used during the classification stage of the rendering pipeline. The validity of the proposed approach for medical applications is illustrated.

/pdf/augmented-reality-interaction-for-semiautomatic-volume-rjwok9s5yu.pdf

Augmented reality interaction for semiautomatic volume classification

The demand for higher quality in the graphical representation of 3D scenes is continuously increasing. Subdivision of triangular meshes is one of the most employed techniques for improving the quality of these rendered images. The high communication requirements between the CPU and the graphics system associated with this kind of method can be considerably reduced if the subdivision task is carried out in hardware, within a new unit placed at the entry of the standard graphics pipeline. In this paper we present a comparative analysis of two possible implementations of this hardware unit, corresponding to two different alternatives for applying loop subdivision to triangle meshes: subdivision based on forward differencing and on meshing scheme. In the first case, the amount of information sent to the graphics pipeline grows linearly with the level of subdivision; whereas, with the meshing scheme the communication requirements are lower and independent of the subdivision level.

A. del Rio

Papers

Hybrid segmentation and exploration of the human lungs

Augmented reality interaction for semiautomatic volume classification

Hardware implementation of the subdivision loop algorithm

Bilddatengestützte navigation und optische endoskopie zur minimai invasiven kraniomaxillofazialen chirurgie