Using k-means clustering to classify microscopic colon images
This study reports on the performance of k-means clustering technique in classifying microscopic images of colonic tissue. Prior to the applications of the k-means clustering algorithm, the images were classified by a human expert according to 3 categories: normal, adenomatous polyp, and adenocarcin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | text |
| Published: |
Animo Repository
2008
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/6041 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Summary: | This study reports on the performance of k-means clustering technique in classifying microscopic images of colonic tissue. Prior to the applications of the k-means clustering algorithm, the images were classified by a human expert according to 3 categories: normal, adenomatous polyp, and adenocarcinoma or cancerous. The images were selected in order to produce 25 images for each category, totaling 75 images in all. The image properties used were texture quantities derived from grey-level co-occurrence matrices (GLCM). Results showed classification accuracies of 69%, 62%, and 40% for the adenomatous polyp, normal, and cancerous cases, respectively. |
|---|