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

Abstract

Background: 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.

Results: 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.

Conclusions: 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.

Figure 1

Overview of the main building blocks of Segment and transaction analysis. Red arrows indicate communication that is initiated from a user interface. Green arrows indicate call of calculation sub-routines. Blue arrows indicate requests for graphical update or call of low-level user input and output routines.

Figure 2

Annotated screen shot of the main user interface of Segment. The circles indicate functional units in the user interface. Example images from one patient have been loaded and displayed in different viewing panels. The yellow box around one image panel indicates the current image stack.

Figure 3

Correlation plot where timer and beaker flow measurements are plotted versus velocity encoded MR flow quantification.

Figure 4

Difference in total net flow comparing automated and manual vessel delineation. Bias ± 2 SD is indicated in the plot.

Figure 5

Example of vessel flow profile visualisation over time in the human aorta of a healthy volunteer. The first time frame is at the top left and time is increasing along each row. Top right vessel is peak systolic time frame. Note the relative skewedness of the flow in the healthy volunteer.

Figure 6

Illustration of sampling error for small regions of interest. Horizontal axis represents true area and vertical axis represents area based on counting pixels included in the ROI. The error depends on the pixel resolution. Open circles denote a pixel resolution of 1 mm, diamonds indicate a pixel resolution up-sampled to 0.5 mm, and plus signs indicate a pixel resolution up-sampled to 0.25 mm.