Optical classification of neoplastic colorectal polyps - a computer-assisted approach (the COACH study).

BACKGROUND AND AIMS: Clinical data suggest that the quality of optical diagnoses of colorectal polyps differs markedly among endoscopists. The aim of this study was to develop a computer program that was able to differentiate neoplastic from non-neoplastic polyps using unmagnified endoscopic pictures. METHODS: During colonoscopy procedures polyp photographies were performed using the unmagnified high-definition white light and narrow band image mode. All detected polyps (n = 275) were resected and sent to pathology. Histopathological diagnoses served as the ground truth. Machine learning was used in order to generate a computer-assisted optical biopsy (CAOB) approach. In the test phase pictures were presented to CAOB in order to obtain optical diagnoses. Altogether 788 pictures were available (602 for training the machine learning algorithm and 186 for CAOB testing). All test pictures were also presented to two experts in optical polyp characterization. The primary endpoint of the study was the accuracy of CAOB diagnoses in the test phase. RESULTS: A total of 100 polyps (of these 52% neoplastic) were used in the CAOB test phase. The mean size of test polyps was 4 mm. Accuracy of the CAOB approach was 78.0%. Sensitivity and negative predictive value were 92.3% and 88.2%, respectively. Accuracy obtained by two expert endoscopists was 84.0% and 77.0%. Regarding accuracy of optical diagnoses CAOB predictions did not differ significantly compared to experts (p = .307 and p = 1.000, respectively). CONCLUSIONS: CAOB showed good accuracy on the basis of unmagnified endoscopic pictures. Performance of CAOB predictions did not differ significantly from experts' decisions. The concept of computer assistance for colorectal polyp characterization needs to evolve towards a real-time application prior of being used in a broader set-up.

Longer observation time increases adenoma detection in the proximal colon - a prospective study.

BACKGROUND AND STUDY AIMS: Longer observation times are associated with increased adenoma detection rates (ADR) in the entire colon. However, adenomas in the proximal colon are at risk of being missed during colonoscopy. The aim of this study was to investigate the impact of observation time on detection of adenomatous polyps in the proximal colon. PATIENTS AND METHODS: This was a prospective study at a university hospital in Germany. Colonoscopies were conducted using magnetic endoscope imaging (MEI) in order to determine the exact position of the scope. Exact observation times spent for the detection of polyps in the proximal and distal colon segments were assessed. The primary outcome was adenoma detection in the proximal colon. ROC curves were generated in order to test the correlation between observation time and adenoma detection. Logistic regression analysis was used to check for interfering factors. RESULTS: A total 480 procedures with 538 polyps were available for analysis. The overall adenoma detection rate was 38.5 %. ADR in the proximal colon was 28.0 %. There was a significant association between observation time in the proximal colon and the detection of proximal adenomas ( P  < 0.001). The impact of the time factor on ADR was stronger in the proximal compared to the distal colon ( P  = 0.030). A net period of 4 min 7 sec was found to be the minimum time span for sufficient adenoma detection in the proximal colon. CONCLUSION: Observation time is significant in terms of adenoma detection in the proximal colon. The impact of observation time on ADR is stronger in the proximal compared to the distal colon. In the proximal colon a minimum time span of 4 minutes should be spent in order to ensure adequate adenoma detection.