To read the full-text of this research, you can request a copy directly from the authors.
In this article we present an extension to the Live-Wire segmentation approach. An automatic preprocessing is done before the interactive segmentation and thus provides an additional level of abstraction. The amount of the interactively processed data is reduced and additional problem specific knowledge is included. We achieve a data reduction of a factor of >6 for a typical MRT image of the human brain.
This paper presents a user-steered segmentation algorithm based on the livewire paradigm. Livewire is an image-feature driven
method that finds the optimal path between user-selected image locations, thus reducing the need to manually define the complete
boundary. We introduce an image feature based on local phase, which describes local edge symmetry independent of absolute
gray value. Because phase is amplitude invariant, the measurements are robust with respect to smooth variations, such as bias
field inhomogeneities present in all MR images. In order to enable validation of our segmentation method, we have created
a system that continuously records user interaction and automatically generates a database containing the number of user interactions,
such as mouse events, and time stamps from various editing modules. We have conducted validation trials of the system and
obtained expert opinions regarding its functionality.
Segmenting medical structures is mandatory in any computer assisted surgery system. This major field must be addressed in
order to build realistic and accurate 3D models of patient individual anatomical structures.Magnetic Resonance Imaging (MRI)
is becoming part of daily routine in clinical work. Whereas scanning speed and slice numbers increase each year, segmenting
such data is still a challenging problem. Moreover, the segmentation stage remains time limiting in pre-operative planning
and intra-operative guidance. Indeed, interactive tools, like live wire or intensity-based thresholding, requires a pre or
post-filtering to homogenize areas. Common medical filters, such as median or morphology-based, are actually non adapted for
MR noise removal. Their main side effect is to remove boundaries when applied on Gaussian corrupted data. Next, numerous steps
spend efforts in reconstructing lost information and current approaches are therefore non interactive.
In the past, we have presented three user-steered image segmentation
paradigms: live wire, live lane, and the 3D extension of the live-wire
method. In this paper, we introduce an ultra-fast live-wire method,
referred to as live-wire-on-the-fly, for further reducing user's time
compared to live wire. For both approaches, given a slice and a 2D
boundary of interest in this slice, we translate the problem of finding
the best boundary segment between any two points specified by the user
on this boundary to the problem of finding the minimum-cost path between
two vertices in a weighted and directed graph. The entire 2D boundary is
identified as a set of consecutive boundary segments, each specified and
detected in this fashion. A drawback in live wire is that the speed for
optimal path computation depends on image size, compromising the overall
segmentation efficiency. In this work, we solve this problem by
exploiting some properties of graph theory to avoid unnecessary
minimum-cost path computation during segmentation. Based on 164
segmentation experiments from an actual medical application, we
demonstrate that live-wire- on-the-fly is about 1.5 to 33 times faster
than live wire for actual segmentation, although the pure computational
part alone is found to be over a hundred times faster.
We present here a new algorithm for segmentation of intensity
images which is robust, rapid, and free of tuning parameters. The
method, however, requires the input of a number of seeds, either
individual pixels or regions, which will control the formation of
regions into which the image will be segmented. In this correspondence,
we present the algorithm, discuss briefly its properties, and suggest
two ways in which it can be employed, namely, by using manual seed
selection or by automated procedures
E N Mortensen
Mortensen E N, Barrett W A: Interactive Segmentation with Intelligent Scissors. Graphical Models and Image Processing, no. 60, pp. 349-384, 1998.
Interactive Segmentation and Visualization of Volume Data Sets. Late Breaking Hot Topics, Visualization pp
Kühne G, Poliwoda C, Hesser J, Männer R: Interactive Segmentation and Visualization
of Volume Data Sets. Late Breaking Hot Topics, Visualization pp. 9-12, 1997.