Quantitative analysis and development of a computer-aided system for identification of regular pit patterns of colorectal lesions

• Published in: Gastrointestinal endoscopy Vol. 72; no. 5; pp. 1047 - 1051
• Main Authors: Takemura, Yoshito, MD, Yoshida, Shigeto, MD, Tanaka, Shinji, MD, Onji, Keiichi, MD, Oka, Shiro, MD, Tamaki, Toru, PhD, Kaneda, Kazufumi, PhD, Yoshihara, Masaharu, MD, Chayama, Kazuaki, MD
• Format: Journal Article
• Language: English
• Published: Maryland heights, MO Mosby, Inc 01.11.2010; Elsevier
• Subjects: Biological and medical sciences; Cohort Studies; Colorectal Neoplasms - diagnosis; Digestive system. Abdomen; Endoscopy; Endoscopy, Gastrointestinal; Gastroenterology and Hepatology; Gastroenterology. Liver. Pancreas. Abdomen; Humans; Image Interpretation, Computer-Assisted; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Predictive Value of Tests; Reproducibility of Results; Retrospective Studies; Software Design; Software Validation; Identification; Colon; Lesion; Computer aid; Rectum; Quantitative analysis
• ISSN: 0016-5107; 1097-6779
• DOI: 10.1016/j.gie.2010.07.037

Background Because pit pattern classification of colorectal lesions is clinically useful in determining treatment options for colorectal tumors but requires extensive training, we developed a computerized system to automatically quantify and thus classify pit patterns depicted on magnifying endoscopy images. Objective To evaluate the utility and limitations of our automated pit pattern classification system. Design Retrospective study. Setting Department of endoscopy at a university hospital. Main Outcome Measurements Performance of our automated computer-based system for classification of pit patterns on magnifying endoscopic images in comparison to classification by diagnosis of the 134 regular pit pattern images by an endoscopist. Results For type I and II pit patterns, the results of discriminant analysis were in complete agreement with the endoscopic diagnoses. Type III l was diagnosed in 29 of 30 cases (96.7%) and type IV was diagnosed in 1 case. Twenty-nine of 30 cases (96.7%) were diagnosed as type IV pit pattern. The overall accuracy of our computerized recognition system was 132 of 134 (98.5%). Conclusions Our system is best characterized as semiautomated but is a step toward the development of a fully automated system to assist in the diagnosis of colorectal lesions based on classification of pit patterns.