FIRST IN VIVO COMPUTER-AIDED DIAGNOSIS OF COLORECTAL POLYPS USING WHITE LIGHT ENDOSCOPY

Aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy and to compare its performance with endoscopists.

Methods ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded and only white light endoscopy was used. The in vivo ATENEA’s prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA’s output. Histology was the gold standard.

Results 90 polyps (median size: 5 mm, range: 2-25) were included of which 69 (76.6%) were adenomas. ATENEA correctly predicted the histology in 63/69 (91.3%, 95% CI: 85.4%-97.1%) adenomas and 12/21 (57.1%, 95% CI: 46.9%-67.3%) non-adenomas whilst endoscopists in 52/69 (75.3%, 95% CI: 66.4%-84.2%) and 20/21 (95.2%, 95% CI: 90.8%-99.6%), respectively. The global accuracy was 83.3% (95% CI: 75.6%-91%) and 80% (95% CI: 71.7%-88.2%) for ATENEA and endoscopists, respectively.

Conclusions ATENEA can accurately be used for in vivo characterization of colorectal polyps enabling the endoscopist to make direct decisions. ATENEA showed a similar global accuracy compared to endoscopists despite an unsatisfactory performance for non-adenomatous lesions.

Publication History

Article published online:
14 April 2022