Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy (with video)

Takemura, Yoshito; Yoshida, Shigeto; Tanaka, Shinji; Kawase, Rie; Onji, Keiichi; Oka, Shiro; Tamaki, Toru; Raytchev, Bisser; Kaneda, Kazufumi; Yoshihara, Masaharu; Chayama, Kazuaki

doi:10.1016/j.gie.2011.08.051

« Previous Next »Gastrointestinal Endoscopy
Volume 75, Issue 1 , Pages 179-185, January 2012

Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy (with video)

Yoshito Takemura, MD
- Department of Medicine and Molecular Science, Hiroshima University, Hiroshima, Japan
Shigeto Yoshida, MD
- Graduate School of Biochemical Science, Department of Endoscopy, Hiroshima University, Hiroshima, Japan
- Reprint requests: Shigeto Yoshida, MD, Department of Endoscopy, Hiroshima University Hospital, 1-2-3 Kasumi, Minami-ku, Hiroshima 734-8551, Japan
Shinji Tanaka, MD
- Graduate School of Biochemical Science, Department of Endoscopy, Hiroshima University, Hiroshima, Japan
Rie Kawase, MD
- Department of Medicine and Molecular Science, Hiroshima University, Hiroshima, Japan
Keiichi Onji, MD
- Department of Medicine and Molecular Science, Hiroshima University, Hiroshima, Japan
Shiro Oka, MD
- Graduate School of Biochemical Science, Department of Endoscopy, Hiroshima University, Hiroshima, Japan
Toru Tamaki, PhD
- Department of Information Engineering, Hiroshima University, Hiroshima, Japan
Bisser Raytchev, PhD
- Department of Information Engineering, Hiroshima University, Hiroshima, Japan
Kazufumi Kaneda, PhD
- Department of Information Engineering, Hiroshima University, Hiroshima, Japan
Masaharu Yoshihara, MD
- Graduate School of Engineering, Department of Health Service Center, Hiroshima University, Hiroshima, Japan
Kazuaki Chayama, MD
- Department of Medicine and Molecular Science, Hiroshima University, Hiroshima, Japan

Received 1 June 2011; accepted 25 August 2011.

Background

Narrow-band imaging (NBI) classification of colorectal lesions is clinically useful in determining treatment options for colorectal tumors. There is a learning curve, however. Accurate NBI-based diagnosis requires training and experience. In addition, objective diagnosis is necessary. Thus, we developed a computerized system to automatically classify NBI magnifying colonoscopic images.

Objective

To evaluate the utility and limitations of our automated NBI classification system.

Design

Retrospective study.

Setting

Department of endoscopy, university hospital.

Main outcome measurements

Performance of our computer-based system for classification of NBI magnifying colonoscopy images in comparison to classification by two experienced endoscopists and to histologic findings.

Results

For the 371 colorectal lesions depicted on validation images, the computer-aided classification system yielded a detection accuracy of 97.8% (363/371); sensitivity and specificity of types B-C3 lesions for a diagnosis of neoplastic lesion were 97.8% (317/324) and 97.9% (46/47), respectively. Diagnostic concordance between the computer-aided classification system and the two experienced endoscopists was 98.7% (366/371), with no significant difference between methods.