Representative Line Ditectio Algorithm with Fuzzy Inference
and Its Application to Segmentation of CT Knee Images
Makoto Shibata, Syoji Kobashi, Katsuya Kondo, Yutaka Hata,
Seturo Imawaki*, and Makoto Ishikawa*
Ishikawa Hospital
Proc. of 9th Int. Conf. on Neural Information Processing, CD-ROM, (2002)
We propose a new algorithm called representative line detection algorithm
embedded physician knowledge with fuzzy if-then rules. The algorithm is
to detect the representative line of the region of interest (ROI). The
representative line can show the rough location and shape. We first
consider the representative line which consisted of some nodes. These
nodes are then automatically detected by tracking most suitable direction
from the starting node. To evaluate this algorithm, it applies to segmentation
of the meniscus from CT knee images. The experimental results of six normal
subjects showed that the representative line detection algorithm could express
center line of the meniscus, and could lead to detect successful segmentation
of the menisci for the all.