Artificial intelligence for characterization of diminutive colorectal polyps:A feasibility study comparing two computer-aided diagnosis systems

BACKGROUND Artificial intelligence(AI)has potential in the optical diagnosis of colorectal polyps.AIM To evaluate the feasibility of the real-time use of the computer-aided diagnosis system(CADx)AI for ColoRectal Polyps(AI4CRP)for the optical diagnosis of diminutive colorectal polyps and to compare the performance with CAD EYE^(TM)(Fujifilm,Tokyo,Japan).CADx influence on the optical diagnosis of an expert endoscopist was also investigated.METHODS AI4CRP was developed in-house and CAD EYE was proprietary software provided by Fujifilm.Both CADxsystems exploit convolutional neural networks.Colorectal polyps were characterized as benign or premalignant and histopathology was used as gold standard.AI4CRP provided an objective assessment of its characterization by presenting a calibrated confidence characterization value(range 0.0-1.0).A predefined cut-off value of 0.6 was set with values<0.6 indicating benign and values≥0.6 indicating premalignant colorectal polyps.Low confidence characterizations were defined as values 40%around the cut-off value of 0.6(<0.36 and>0.76).Self-critical AI4CRP’s diagnostic performances excluded low confidence characterizations.RESULTS AI4CRP use was feasible and performed on 30 patients with 51 colorectal polyps.Self-critical AI4CRP,excluding 14 low confidence characterizations[27.5%(14/51)],had a diagnostic accuracy of 89.2%,sensitivity of 89.7%,and specificity of 87.5%,which was higher compared to AI4CRP.CAD EYE had a 83.7%diagnostic accuracy,74.2%sensitivity,and 100.0%specificity.Diagnostic performances of the endoscopist alone(before AI)increased nonsignificantly after reviewing the CADx characterizations of both AI4CRP and CAD EYE(AI-assisted endoscopist).Diagnostic performances of the AI-assisted endoscopist were higher compared to both CADx-systems,except for specificity for which CAD EYE performed best.CONCLUSION Real-time use of AI4CRP was feasible.Objective confidence values provided by a CADx is novel and self-critical AI4CRP showed higher diagnostic performances compared to AI4CRP.

Removal of diminutive colorectal polyps: A prospective randomized clinical trial between cold snare polypectomy and hot forceps biopsy

AIMTo compare the efficacy and safety of cold snare polypectomy (CSP) and hot forceps biopsy (HFB) for diminutive colorectal polyps.METHODSThis prospective, randomized single-center clinical trial included consecutive patients &#x02265; 20 years of age with diminutive colorectal polyps 3-5 mm from December 2014 to October 2015. The primary outcome measures were en-bloc resection (endoscopic evaluation) and complete resection rates (pathological evaluation). The secondary outcome measures were the immediate bleeding or immediate perforation rate after polypectomy, delayed bleeding or delayed perforation rate after polypectomy, use of clipping for bleeding or perforation, and polyp retrieval rate. Prophylactic clipping after polyp removal wasn&#x02019;t routinely performed.RESULTSTwo hundred eight patients were randomized into the CSP (102), HFB (106) and 283 polyps were evaluated (CSP: 148, HFB: 135). The en-bloc resection rate was significantly higher with CSP than with HFB [99.3% (147/148) vs 80.0% (108/135), P &#x0003c; 0.0001]. The complete resection rate was significantly higher with CSP than with HFB [80.4% (119/148) vs 47.4% (64/135), P &#x0003c; 0.0001]. The immediate bleeding rate was similar between the groups [8.6% (13/148) vs 8.1% (11/135), P = 1.000], and endoscopic hemostasis with hemoclips was successful in all cases. No cases of perforation or delayed bleeding occurred. The rate of severe tissue injury to the pathological specimen was higher HFB than CSP [52.6% (71/135) vs 1.3% (2/148), P &#x0003c; 0.0001]. Polyp retrieval failure was encountered CSP (7), HFB (2).CONCLUSIONCSP is more effective than HFB for resecting diminutive polyps. Further long-term follow-up study is required.