Mucosal Lesion Analysis of HD digital Chromocolonoscopy using Wavelets

According to the American Cancer Society colon cancer ist the third most common type of cancer in males and fourth in females in western countries. Therefore screening programs have been established worldwide in order to detect lesions with a malignant potential or early cancer. The current goldstandard for the detection of lesions in the colon is flexible video-endoscopy. The colonoscope allows a physician or surgeon to examine the colon and the distal part of the ileum and to take tissue samples. Modern colonoscopes are using high resolution CCD and storage of pictures and video sequences can be done using additional hardware. Therefore, analysis of images or video sequences with the assistance of computers is possible in principle. This allows computer assisted detection and classification of lesions. Recently, high definition (HD and HD+) endoscopy has been introduced into the market and is becoming quickly the de-facto standard in medical centers. Major manufacturers are offering corresponding technology, e.g. Olympus EVIS EXARA II or Pentax HiLINE HD+, and this technology is being adopted quickly in colonoscopy. The combination of digital chromoendoscopy and HD-endoscopy leads to characteristic mucosal surface patterns which can be interpreted by an experienced examiner. However, result accuracy is limited by about 90\% - 95\% and also inter-examiner variability has been reporteted recently and require to improve the results for clinical deployment in e.g. screening programs. Consequently, this project proposal aims at developing techniques for a computer assisted clinical assessment employing and comparing different types of wavelet-based techniques for an automated classification of visual data aquired by a HD colonoscope using digital virtual chromoendoscopy (Pentax i-Scan) corresponding to different types of lesions. Besides establishing a database of HD texture patches with available ground truth with respect to histopathologic ground truth, a collection of preprocessing, wavelet-based feaure extraction and classification algorithms will be developed to result in a prototype decision support system, which will be assessed in a clinical study.

According to the American Cancer Society colon cancer is the third most common type of cancer in males and fourth in females in western countries. Therefore screening programs have been established worldwide in order to detect lesions with a malignant potential or early cancer. The current goldstandard for the detection of lesions in the colon is flexible video-endoscopy. The colonoscope allows a physician or surgeon to examine the colon and the distal part of the ileum and to take tissue samples. Modern colonoscopes are using high resolution CCD and storage of pictures and video sequences can be done using additional hardware. Therefore, analysis of images or video sequences with the assistance of computers is possible in principle. This allows computer assisted detection and classification of lesions.Recently, high definition (HD and HD+) endoscopy has been introduced into the market and is becoming quickly the de-facto standard in medical centers. Major manufacturers are offering corresponding technology, e.g. Olympus EVIS EXARA II or Pentax HiLINE HD+, and this technology is being adopted quickly in colonoscopy. The combination of digital chromoendoscopy and HD-endoscopy leads to characteristic mucosal surface patterns which can be interpreted by an experienced examiner. However, result accuracy is limited by about 90\% - 95\% and also inter-examiner variability has been reported recently and requires to improve the results for clinical deployment in e.g. screening programs.Consequently, this project has developed techniques for a computer assisted clinical assessment of colonic polys employing and comparing different types of wavelet-based and other techniques for an automated classification of visual data acquired by a HD colonoscope using digital virtual chromoendoscopy (Pentax i-Scan) corresponding to different types of lesions. Besides establishing a database of HD texture patches with available histopathologic ground truth, a collection of preprocessing, (wavelet-based) feature extraction and classification algorithms have been developed to result in a prototype polyp dignity assessment decision support system.