Intensity Based Automatic Segmentation

Early approaches for automatic segmentation fundamentally use the assumption that radiological images are basically "self-contained," i.e., they contain most of the information which is necessary for the identification of anatomical objects. In some limited applications such techniques can be very successful, as the automatic segmentation of dual-echo MR images [1]. This example will be used here as an illustration as it addresses most aspects of intensity-based medical image segmentation. The method uses two spatially perfectly matched echos of a spin-echo MR acquisition as illustrated by Figs. 14.1(a) and 14.1(c).

Figure 14.1: Spin-echo MR image pair (an early echo is shown on the left, a late echo on the right). In the middle the two-dimensional intensity distribution (i.e., the frequency of the occurrence of intensities I and I2 in the left and right images) is given.

Figure 14.1: Spin-echo MR image pair (an early echo is shown on the left, a late echo on the right). In the middle the two-dimensional intensity distribution (i.e., the frequency of the occurrence of intensities I and I2 in the left and right images) is given.

Figure 14.2: Segmentation of the dual-echo MR image using training. The left image shows user-defined training regions for the different tissue classes. The corresponding tessellation of the feature space (spanned by the joint intensity distribution) is shown in the middle, resulting in the segmentation on the right.

Figure 14.2: Segmentation of the dual-echo MR image using training. The left image shows user-defined training regions for the different tissue classes. The corresponding tessellation of the feature space (spanned by the joint intensity distribution) is shown in the middle, resulting in the segmentation on the right.

The applied procedure can be regarded as a generalized thresholding, aiming at the identification of areas in a feature space, i.e. in the two-dimensional intensity distribution (Fig. 14.1(b)), which uniquely characterize the different tissue classes (as gray or white matter of the brain). These areas are usually determined during a training phase, where the user identifies examples for each tissue class (e.g. in the form of regions of interest as illustrated in Fig. 14.2(a)). Standard pattern recognition procedures (e.g., as k-nearest neighbor classification) [2] can be used to derive a corresponding tessellation of the feature space (Fig. 14.2(b)) leading to the classification of the entire image (Fig. 14.2(c)).

The success of the segmentation basically depends on the assumption that tissue classes can perfectly be separated in the feature space provided by the measurements. Beside physiologically induced overlaps between features of different tissue classes, limitations of the acquisition process can seriously compromise the efficiency of the method.

The most important sources of error are the presence of noise, the spatial inhomogeneity of the signal intensity generated by the tissue, and the limited spatial resolution of the images leading to partial volume effects.

The presence of voxels containing several tissue classes can be smoothly incorporated into the classification framework by extending the original scheme by mixed tissue classes [3,4]. As classical methods of noise reduction are based on linear low-pass filtering, they necessarily blur the boundary between different tissues, leading to artificially created partial volume effects. Nonlinear techniques based on anisotropic diffusion processes [5], which selectively stop the smoothing process at spatial positions with large intensity gradients, have been established during the past decade as effective tools for noise reduction, while preserving anatomical structures at tissue boundaries.

Several techniques have been developed for the correction of the spatial intensity bias resulting, for example, from the inhomogeneity of the RF field during MR image acquisition. One possibility considered is the implementation of bias-field correction as a preprocessing step, using generic assumptions about the expected distortions [6,7]. As an alternative, expectation maximization has been proposed as an iterative framework to perform classification and bias correction simultaneously [8].

One important limitation of the above intensity-based classification framework is that it handles pixels in the image completely independently. This means that the result of the segmentation is invariant to the actual positions of the voxels in the image. This assumption is of course highly nonrealistic as intensities of nearby voxels are usually strongly correlated. This correlation between single pixels can explicitely be described by spatial interaction models. Spatial correlation between the single pixels can be introduced using more or less complex interaction models as, for example, Markov random fields [9,10] and integrated into the classification framework. As an alternative, postprocessing techniques can be used to correct for erroneous classification. One popular technique is based on mathematical morphology [11], which allows the identification and correction of wrongly classified pixels based on morphological criteria, like the presence of very small, isolated tissue clusters [3]. The latter process is illustrated by the identification of the brain mask on a neuroradiological MR slice Fig. 14.3.

0 0

Post a comment