Removing Non-Tumor Regions

 

Once any extra-cranial regions have been removed, the knowledge base is applied to discriminate between regions with and without tumor based on statistical information about the region. A region mean, standard deviation, and skewness in $\langle T1\rangle$, $\langle PD \rangle$, and $\langle T2 \rangle$ feature space respectively are used as features. The concept exploited is that trends and characteristics described at a pixel level in Table 2 and Section 3.3 are also applicable on a region level. By sorting regions in feature space based upon their mean values, rules based on their relative order can be created:

1.

Large regions that contain tumor will likely contain a significant number of pixels that are of highest intensity in T1 and PD space, while regions without tumor likely contain a significant number of pixels of lowest intensity in T1 and PD space.

2.

The means of regions with similar tissue types neighbor one another in feature space.

3.

The intra-cranial region with the highest mean T1 value and a ``high'' PD and T2 value, is considered ``First Tumor,'' against which all other regions are compared.

4.

Other regions that contain tumor are likely to fall within 1 to 1.5 standard deviations (depending on region size) of First Tumor in T1 and PD space.

While most glioblastoma-multiforme tumor cases have only one tumorous spatially compact region that has the highest mean T1 value, in some cases, the tumor has grown such that it has branched into both hemispheres of the brain, causing the tumor to appear disjoint in some slices, or it has fragmented as a result of treatment. Also, different tumor regions do not enhance equally. Thus, cases can range from a single well-enhancing tumor to a fragmented tumor with different levels of enhancement. In comparison, the makeup of non-tumor regions is generally more consistent than in tumorous regions. Therefore, the knowledge base is designed to facilitate removal of non-tumor regions because their composition can be more reliably modeled and detected.

  

Figure 11: Using Pixel Counts to Remove Non-Tumorous Regions. Given a refined tumor segmentation after Stage Three (a), spatial regions with a significant number of pixels highest in T1 space (b) or PD space (c) are likely to contain tumor. Regions with pixels lowest in T1 space (d) are unlikely to contain significant tumor. Ground truth is shown in (e).

Regions that comply with the first heuristic listed above are the easiest to locate and their statistics can be used to examine the remaining regions. To apply the first heuristic, three new image masks are created. The first image mask takes the refined tumor segmentation image and keeps only 20% of the highest T1 value pixels (i.e., if there were 100 pixels in the refined tumor image, the 20 pixels with the highest T1 values are kept). The second mask keeps the highest 20% in PD space, while the third mask keeps the 30% lowest in T1 space. Each region is isolated and intersected with each of the 3 masks created. The number of pixels of the region in a particular mask is recorded and compared with the rules listed in Table 3. An example is shown in Figure 11.

  

Region Size Pixels in intersections with the 3 masks Action

$$\leq 5$$ Any Bottom T1 Pixels AND Remove

Less than 2 Top T1 Pixels Non-Tumor

$$\ge 500 Region Size \times 0.06$$ Label As Tumor

$$\ge 5$$ No Top T1 Pixels AND Remove

$$Region Size \times 0.005$$

$$Region Size \times 0.01$$

Regions that do not activate any of the rules in Table 3 remain unlabeled and are analyzed using the last two heuristics.

According to the third heuristic, given a region that has been positively labeled tumor as a point of reference, a search can be made in feature space for neighboring tumor regions. Normally, the region with the highest T1 mean value can be selected as this point of reference (called ``First Tumor''). To guard against the possibility that an extra-cranial region (usually meningial tissues at the inter-hemispheric fissure) has been selected instead, the selected region is verified via the heuristic that a tumor region will not only have a very high T1 mean value, but will also occupy the highest half of all regions in sorted PD and T2 mean space. For example, if there were 10 regions total, the region being tested must be one of the 5 highest mean values in both PD and T2 space. If the candidate region passes, it is confirmed as First Tumor. Otherwise, it is discarded and the region with the next highest T1 mean value is selected for testing as First Tumor.

Once First Tumor has been confirmed, the search for neighboring tumor regions can begin. Although tumorous regions can have between-slice variance, the third and fourth heuristics hold for the purpose of separating tumor from non-tumor regions within a given slice. Furthermore, the standard deviations in T1 and PD space of a known tumor region were found to be a useful and flexible distance measure.

  

Region Size If Region's Mean Values are: Action

$$\le 10$$ More than 1 SD away in T1 space OR Remove

$$\ge Largest/4$$ More than 1 SD away in PD space.

$$\geq 10$$ More than 1.5 SD away in T1 space AND Remove

$$\leq Largest/4$$ More than 1.5 SD away in PD space. 3c(b) Labeling Rules Based on Region Statistics

$$\ge 100 T1\_Skewness \le 0.75$$ Remove

$$PD\_Skewness \le 0.75$$

$$T2\_Skewness \le 0.75$$

Table 4(a) lists the two rules that used the standard deviation to remove non-tumor regions, based on the size (number of pixels) of the region being tested. The rule in Table 4(b) serves as a tie-breaker for some regions that were not labeled before. The term Largest is used to indicate the largest known tumor region. In most cases there was only a single tumor region, so the ``first tumor'' region was also the Largest region. In cases where tumor was fragmented, however, a larger tumorous region will provide a more robust mean and standard deviation for the distance measure. Therefore, the system would find Largest by searching for the largest region that was within one standard deviation in both T1 and PD space to the First Tumor region.

After the rules in Table 4 are applied, all regions that were not removed are labeled as tumor, and the segmentation process terminates.