Slices of Interest for the Study

  The system described here can process any transaxial slice [29,30] (intersecting the long axis of the human body) starting from an initial slice 7 to 8 cm from the top of the brain and upward. This range of slices provides a good starting point in tumor segmentation, due to the relatively good signal uniformity within the MR coil used [23]. Each brain slice consists of three feature images: T1-weighted (T1), proton density weighted (PD), and T2-weighted (T2) [3] .

  

Figure 1: Slices of Interest: (a) raw data from a normal slice (T1-weighted, PD and T2-weighted images from left to right) (b) after segmentation (c) raw data from an abnormal slice (T1-weighted, PD and T2-weighted images from left to right) (d) after segmentation. White=white matter; Black=gray matter; Dark Gray=CSF; Light Gray=Pathology in (b) and (d).

An example of a normal slice after segmentation is shown in Figures 1(a) and (b). Figures 1(c) and (d) show an abnormal slice through the ventricles, though pathology may exist within any given slice. The labeled normal intra-cranial tissues of interest are: CSF (dark gray) and the parenchymal tissues, white matter (white) and gray matter (black). In the abnormal slice, pathology (light gray) occupies an area that would otherwise belong to normal tissues. In the approach described here, only part of the pathology (gadolinium-enhanced tumor) is identified and labeled.

 
 

1||c| 5c||# Slices Extracted from Volume

Pat Baseline Repeat 1 Repeat 2 Repeat 3 Repeat 4

2 8 9(9) 9 - -

4 6 7 7(2) - -

5 6(6) - - - -

1 9 10 10 9 8

3 9 9 - - -

6 3 - - - -

7 1 - - - -

A total of 120 slices containing radiologist diagnosed glioblastoma-multiforme tumor were available for processing. Table 1 lists the distribution of these slices across sixteen volumes of seven patients who received varying levels of treatment, including surgery, radiation therapy, and chemo-therapy prior to initial acquisition and between subsequent acquisitions. Using a criteria of tumor size (per slice) and level of gadolinium enhancement to capture the required characteristics of all data sets acquired with this protocol, a training subset of seventeen slices was created. The heuristics discussed in Section 3 were extracted from the training subset through the process of ``knowledge engineering.'' Knowledge engineering is not automated, but human directed. Heuristics are expressed in general terms, such as ``higher end of the T1 spectrum'' (which does not specify an actual T1 value). This provides knowledge that is more robust across slices, without regard to a slice's particular thickness, scanning protocol, or signal intensity, as was the case in [23]. In contrast, multi-spectral efforts such as [32] tune imaging parameters, which may limit their application to slices with the same parameters. The generality of the system will be discussed in Section 5.