Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia

Abstract

Background Artificial Intelligence (AI) may reduce miss rate of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe), and cost of pathology by improving optical diagnosis (CADx). Methods To train a combined CADe and CADx (CAD-EYE,Fujifilm,Japan) based on deep learning, a multicenter library of >200,000 images from 1,572 polyps was used, while testing was performed on two independent image sets (CADe: 446 with polyps and 234 without; CADx: 267) from 234 polyps that was also evaluated by 6 endoscopists (3 experts, 3 non-experts). Results CADe showed a sensitivity, specificity and accuracy of 92.9%, 90.6% and 91.7%, respectively. Experts showed slightly higher accuracy and specificity and a similar sensitivity, while non-experts+CADe showed comparable sensitivity, but lower specificity and accuracy. CADx system showed a sensitivity, specificity and accuracy of 85%, 79.4% and 83.6% for polyp characterization, respectively. Experts comparable performances, while non-experts using CADx showed comparable accuracy, but lower specificity. Conclusions The high accuracy shown by CADe and CADx systems is similar to expert endoscopists, prompting its implementation in clinical practice. When using CAD, non-expert endoscopists achieve similar performances to those of expert endoscopists, with suboptimal specificity.

Clinical Applications of Linked Color Imaging and Blue Laser/Light Imaging in the Screening, Diagnosis, and Treatment of Superficial Colorectal Tumors

“…In terms of the assessments of the performance of the CAD systems, the experimental phase is complete and clinical trials have progressed rapidly. The CAD-EYE system from FUJIFILM was recently launched commercially and has been approved in Europe 25 and Japan. This system was developed to detect colorectal polyps (CADe system) and characterize the detected polyps (CADx system) (Fig.…”

Artificial Intelligence in Endoscopy

“…Still, studies analyzing the effect of CAD systems do not have the same quality including a randomized prospective design as the ones examining the effect of CADe systems [30]. Additionally, vendors are grading their devices up by adding CADx to the already existing CADe modes [31]. Thus, examiners will start using CADx in practice and gather experience.…”

Artificial Intelligence and Deep Learning for Upper Gastrointestinal Neoplasia

“…24 By extracting data on 122 endoscopists, we estimated an 18% miss rate for upper GI neoplasia detection. 24 In detail, such a miss rate was statistically significantly lower for Eastern vs Western endoscopists (13% [95% CI, [11][12][13][14][15][16] vs 25% [95% CI, 22-28]), and for expert vs nonexpert endoscopists (15% [95% CI, [13][14][15][16][17] vs 29% [95% CI, [25][26][27][28][29][30][31][32][33]). 24 What Is Artificial Intelligence for Upper Gastrointestinal Neoplasia?…”

“…Fifth, the use of advanced imaging in the training set should be considered. Although DL algorithms are extremely robust to exogenous factors, such as blue light or magnified endoscopy, 28 it seems more appropriate to apply any AI system with the same light that has been used in training. However, there is emerging evidence showing comparable performances of AI systems across different imaging modalities.…”