This paper reviews ultrasound segmentation methods, in a broad sense, focusing on techniques developed for medical B-mode ultrasound images. First, we present a review of articles by clinical application to highlight the approaches that have been investigated and degree of validation that has been done in different clinical domains. Then, we present a classification of methodology in terms of use of prior information. We conclude by selecting ten papers which have presented original ideas that have demonstrated particular clinical usefulness or potential specific to the ultrasound segmentation problem

/pdf/ultrasound-image-segmentation-a-survey-55ssqpzk7q.pdf

Ultrasound image segmentation: a survey

Commercially available software for cardiovascular image analysis often has limited functionality and frequently lacks the careful validation that is required for clinical studies. We have already implemented a cardiovascular image analysis software package and released it as freeware for the research community. However, it was distributed as a stand-alone application and other researchers could not extend it by writing their own custom image analysis algorithms. We believe that the work required to make a clinically applicable prototype can be reduced by making the software extensible, so that researchers can develop their own modules or improvements. Such an initiative might then serve as a bridge between image analysis research and cardiovascular research. The aim of this article is therefore to present the design and validation of a cardiovascular image analysis software package (Segment) and to announce its release in a source code format. Segment can be used for image analysis in magnetic resonance imaging (MRI), computed tomography (CT), single photon emission computed tomography (SPECT) and positron emission tomography (PET). Some of its main features include loading of DICOM images from all major scanner vendors, simultaneous display of multiple image stacks and plane intersections, automated segmentation of the left ventricle, quantification of MRI flow, tools for manual and general object segmentation, quantitative regional wall motion analysis, myocardial viability analysis and image fusion tools. Here we present an overview of the validation results and validation procedures for the functionality of the software. We describe a technique to ensure continued accuracy and validity of the software by implementing and using a test script that tests the functionality of the software and validates the output. The software has been made freely available for research purposes in a source code format on the project home page http://segment.heiberg.se
 . Segment is a well-validated comprehensive software package for cardiovascular image analysis. It is freely available for research purposes provided that relevant original research publications related to the software are cited.

/pdf/design-and-validation-of-segment-freely-available-software-40iwqqksv9.pdf

Design and validation of Segment--freely available software for cardiovascular image analysis.

We propose an automatic four-chamber heart segmentation system for the quantitative functional analysis of the heart from cardiac computed tomography (CT) volumes. Two topics are discussed: heart modeling and automatic model fitting to an unseen volume. Heart modeling is a nontrivial task since the heart is a complex nonrigid organ. The model must be anatomically accurate, allow manual editing, and provide sufficient information to guide automatic detection and segmentation. Unlike previous work, we explicitly represent important landmarks (such as the valves and the ventricular septum cusps) among the control points of the model. The control points can be detected reliably to guide the automatic model fitting process. Using this model, we develop an efficient and robust approach for automatic heart chamber segmentation in 3D CT volumes. We formulate the segmentation as a two-step learning problem: anatomical structure localization and boundary delineation. In both steps, we exploit the recent advances in learning discriminative models. A novel algorithm, marginal space learning (MSL), is introduced to solve the 9-D similarity transformation search problem for localizing the heart chambers. After determining the pose of the heart chambers, we estimate the 3D shape through learning-based boundary delineation. The proposed method has been extensively tested on the largest dataset (with 323 volumes from 137 patients) ever reported in the literature. To the best of our knowledge, our system is the fastest with a speed of 4.0 s per volume (on a dual-core 3.2-GHz processor) for the automatic segmentation of all four chambers.

Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features

The Medical Imaging Interaction Toolkit

Object tracking is a key enabling technology in the context of computer-assisted medical interventions. Allowing the continuous localization of medical instruments and patient anatomy, it is a prerequisite for providing instrument guidance to subsurface anatomical structures. The only widely used technique that enables real-time tracking of small objects without line-of-sight restrictions is electromagnetic (EM) tracking. While EM tracking has been the subject of many research efforts, clinical applications have been slow to emerge. The aim of this review paper is therefore to provide insight into the future potential and limitations of EM tracking for medical use. We describe the basic working principles of EM tracking systems, list the main sources of error, and summarize the published studies on tracking accuracy, precision and robustness along with the corresponding validation protocols proposed. State-of-the-art approaches to error compensation are also reviewed in depth. Finally, an overview of the clinical applications addressed with EM tracking is given. Throughout the paper, we report not only on scientific progress, but also provide a review on commercial systems. Given the continuous debate on the applicability of EM tracking in medicine, this paper provides a timely overview of the state-of-the-art in the field.

/pdf/electromagnetic-tracking-in-medicine-a-review-of-technology-4tkbhbr4he.pdf

Electromagnetic tracking in medicine--a review of technology, validation, and applications.

The aim of the Medical Imaging Interaction Toolkit (MITK) is to facilitate the creation of clinically usable
image-based software. Clinically usable software for image-guided procedures and image analysis require a high
degree of interaction to verify and, if necessary, correct results from (semi-)automatic algorithms. MITK is
a class library basing on and extending the Insight Toolkit (ITK) and the Visualization Toolkit (VTK). ITK
provides leading-edge registration and segmentation algorithms and forms the algorithmic basis. VTK has
powerful visualization capabilities, but only low-level support for interaction (like picking methods, rotation,
movement and scaling of objects). MITK adds support for high level interactions with data like, for example, the
interactive construction and modification of data objects. This includes concepts for interactions with multiple
states as well as undo-capabilities. Furthermore, VTK is designed to create one kind of view on the data
(either one 2D visualization or a 3D visualization). MITK facilitates the realization of multiple, different views
on the same data (like multiple, multiplanar reconstructions and a 3D rendering). Hierarchically structured
combinations of any number and type of data objects (image, surface, vessels, etc.) are possible. MITK can
handle 3D+t data, which are required for several important medical applications, whereas VTK alone supports
only 2D and 3D data. The benefit of MITK is that it supplements those features to ITK and VTK that are
required for convenient to use, interactive and by that clinically usable image-based software, and that are
outside the scope of both. MITK will be made open-source (http://www.mitk.org).

/pdf/the-medical-imaging-interaction-toolkit-mitk-a-toolkit-6d4qg10wcp.pdf

The medical imaging interaction toolkit (MITK): a toolkit facilitating the creation of interactive software by extending VTK and ITK

In the last few years, 3D ultrasound probes have became readily available. New fields of image-guided surgery applications are opened by attaching small electromagnetic position sensors to 3D ultrasound probes. However, nothing is known about the distortions caused by 3D ultrasound probes regarding electromagnetic sensors. Several trials were performed to investigate error-proneness of state-of-the-art electromagnetic tracking systems when used in combination with 3D ultrasound probes. It was found that 3D ultrasound probes do distort electromagnetic sensors more than 2D probes do. When attaching electromagnetic sensors to 3D probes, maximum errors of 5 mm up to 119 mm occur. The distortion strongly depends on the electromagnetic technology as well on the probe technology used. Thus, for 3D ultrasound-guided applications using electromagnetic tracking technology, the interference of ultrasound probes and electromagnetic sensors have to be checked carefully. (E-mail: mark.hastenteufel@gmx.de )

Effect of 3D ultrasound probes on the accuracy of electromagnetic tracking systems.

Echocardiography (cardiac ultrasound) is today the predominant technique for quantitative assessment of cardiac function and valvular heart lesions. Segmentation of cardiac structures is required to determine many important diagnostic parameters. As the heart is a moving organ, reliable information can be obtained only from three-dimensional (3-D) data over time (3-D + time = 4-D). Due to their size, the resulting four-dimensional (4-D) data sets are not reasonably accessible to simple manual segmentation methods. Automatic segmentation often yields unsatisfactory results in a clinical environment, especially for ultrasonic images. We describe a semiautomated segmentation algorithm (ROPES) that is able to greatly reduce the time necessary for user interaction and its application to extract various parameters from 4-D echocardiographic data. After searching for candidate contour points, which have to fulfill a multiscale edge criterion, the candidates are connected by minimizing a cost function to line segments that then are connected to form a closed contour. The contour is automatically checked for plausibility. If necessary, two correction methods that can also be used interactively are applied (fitting of other line segments into the contour and searching for additional candidates with a relaxed criterion). The method is validated using in vivo transesophageal echocardiographic data sets.

ROPES: a semiautomated segmentation method for accelerated analysis of three-dimensional echocardiographic data

This contribution presents a novel method for image-guided navigation in oncological liver surgery. It enables the perpetuation of the registration for deeply located intrahepatic structures during the resection. For this purpose, navigation aids localizable by an electro-magnetic tracking system are anchored within the liver. Position and orientation data gained from the navigation aids are used to parameterize a real-time deformation model. This approach enables for the first time the real-time monitoring of target structures also in the depth of the intraoperatively deformed liver. The dynamic behavior of the deformation model has been evaluated with a silicon phantom. First experiments have been carried out with pig livers ex vivo.

Mark Hastenteufel

Papers

The Medical Imaging Interaction Toolkit

The medical imaging interaction toolkit (MITK): a toolkit facilitating the creation of interactive software by extending VTK and ITK

Effect of 3D ultrasound probes on the accuracy of electromagnetic tracking systems.

ROPES: a semiautomated segmentation method for accelerated analysis of three-dimensional echocardiographic data

Navigation aids and real-time deformation modeling for open liver surgery