Modelling Aceto-White Response Functions of Precancerous Cervical Lesions. |
|
The aim of this project is to investigate the temporal patterns intrinsic in colposcopic images that are related to precursor lesions of cervical cancer. Colposcopy test is the second most used technique to diagnose cervical cancer disease. Many approaches have been proposed to automatically characterize cervical lesion from colposcopic images, most of them use color, texture, shading or optical features of tissue. More recently, some researchers have suggested to use the temporal patterns intrinsic to the color changes. However the phenomenon has not been fully understood and a lot of research has to be carried out to find how the visual information (used by the medical expert) can be automatically extracted from the colposcopic images in order to help them to perform a more accurate diagnosis. In the present project, we are interested in applying Artificial Intelligence Techniques, such as Computer Vision, Machine Learning and Data Mining, to analyze the temporal patterns intrinsic to colposcopic image sequences, so that it is possible to identify cervical regions that are suggestive of colposcopic abnormalities. |