Video Comment on Kenichi Takeda et al.

Kenichi Takeda et al. Accuracy of diagnosing invasive colorectal cancer using computer-aided endocytoscopy

In this ex vivo pilot study the authors developed a computer algorithm to automatically detect invasive cancer in colorectal lesions using endocytoscopy. The algorithm was created from randomly selected images using machine learning. When applied to 200 images, the algorithm reached a positive predictive value of 99 % and a negative predictive value of 90 %.