Stage One: Building the Intra-Cranial Mask

  The first step in the system presented here is to isolate the intra-cranial region from the rest of the image. During pre-processing, extra and intra-cranial pixels were distinguished primarily by separating the clusters from the initial FCM segmentation into two groups: Group 2 for brain tissue clusters, and Group 1 for the remaining extra-cranial clusters. Occasionally, enhancing tumor pixels can be placed into one or more Group 1 clusters with high T1-weighted centroids. In most cases, these pixels can be reclaimed through a series of morphological operations (described below). As shown in Figures 3(b) and (c), however, the tumor loss may be too severe to recover morphologically without distorting the intra-cranial mask.

  

Figure 4: (a) Initial segmented image; (b) a quadrangle overlaid on (a); (c) classes that passed quadrangle test.

Group 1 clusters with significant ``Lost Tumor'' can be located, however. During pre-processing, Group 1 and 2 clusters were separated based on the observation that extra-cranial tissues surround the brain and are not found within the brain itself. A ``quadrangle'' was developed by Li in [21,36] to roughly approximate the intra-cranial region. Group 1 and 2 clusters were then discriminated by counting the number of pixels a cluster had within the quadrangle. Clusters consisting of extra-cranial tissues will have very few pixels inside this estimated brain, while clusters of intra-cranial tissues will have a significant number. An example is shown in Figure 4.

A Group 1 cluster is considered to have ``Lost Tumor'' here if more than 1% of its pixels were contained in the approximated intra-cranial region. The value of 1% is used to maximize the recovery of lost tumor pixels because extra-cranial clusters with no lost tumor will have very few pixels within the quadrangle, if any at all. Pixels belonging to Lost Tumor clusters (Figure 3(b)) are merged with pixels from all Group 2 clusters (Figure 3(c)) and set to foreground (a non-zero value), with all other pixels in the image set to background (value=0). This produces a new intra-cranial mask similar to the one shown in Figure 3(d).

Since a Lost Tumor cluster is primarily extra-cranial, its inclusion in the intra-cranial mask introduces areas of extra-cranial tissues, such as the eyes and skin/fat/muscle. To remove these unwanted extra-cranial regions (and recover smaller areas of lost tumor, mentioned above), a series of morphological operations [37] are applied, which use window sizes that are the smallest possible (to minimize mask distortion) while still producing the desired result.

Small regions of extra-cranial pixels are removed and separation of the brain from meningial tissues is enhanced by applying a $5\times5$ closing operation to the background. Then the brain is extracted by applying an eight-wise connected components operation [37] and keeping only the largest foreground component (the intra-cranial mask). Finally, ``gaps'' along the periphery of the intra-cranial mask are filled by first applying a $15\times15$ closing, then a $3\times3$ erosion operation. An example of the final intra-cranial mask can be seen in Figure 3(e).