Features for Measuring the Congestive Extent of Internal Hemorrhoids in Endoscopic Images

Abe, K., Takagi, H., Minami, M. and Tian, H.

This paper presents a computer-aided diagnosis for internal hemorrhoids based on the congestive extent in endoscopic images. This system could be effective for young or even general practitioners as a second opinion because diagnosis of hemorrhoids needs much experience. Since the images are not always clear depending on situation of scenes, a pre-processing is conducted to the images to enhance saturation and contrast of congestive regions and blood vessels. Next, from characteristics of internal hemorrhoids, the proposed method measures degree of the congestion in the images and extracts the congestive region and features on the congestive extent. Experimental results of discriminations using the proposed abnormalities between normal and abnormal cases for 204 images including 108 abnormal cases have shown that the abnormalities are well effective to diagnose the congestion in internal hemorrhoids.

Cite as: Abe, K., Takagi, H., Minami, M. and Tian, H. (2013). Features for Measuring the Congestive Extent of Internal Hemorrhoids in Endoscopic Images. In Proc. Data Mining and Analytics 2013 (AusDM'13) Canberra, Australia. CRPIT, 146. Christen, P., Kennedy, P., Liu, L., Ong, K.L., Stranieri, A. and Zhao, Y. Eds., ACS. 17-24

(from crpit.com) (local if available)