Data Management And Analysis Of Colposcopic Image

The 2008 Nobel Prize in physiology caught the world's eyes onto the research in uterine cervical cancer. Uterine cervical cancer has been the second most common cancer in women worldwide, according to the 2007's report from NCI. Optical colposcopy is the primary method used to detect uterine cervical cancer or Cervical Intraepithelial Neoplasia.Due to the insufficiency of China in colposcopy image collection , a novel image database is developed and it will be the basis of a computer-aided-diagnosis system for colposcopy. Teaching, preservation of prime data, medical research, etc. would also benefit from the setting-up of the image database.Secondly, in order to get more effective biopsies, four alternative processing methods are proposed to segment effective region from original images, detect and analyze the features of acetowhite regions and mark candidate acetowhite regions within digital uterine cervix images automatically.33 color features are extracted for the image analysis after processing the original images in the above methods. Support vector machine classifier is applied -- classifying accuracy is 78.1%, sensitivity is 81.1% and specificity is 75%. The result shows a considerable increase by around 15% on the accuracy which proves the validity of the feature extraction and the classifying scheme.