Using artificial intelligence in colonoscopy's adenoma detection: An invention to help clinicians (Part 2)

This is an automatically translated article.

Posted by Master, Doctor Mai Vien Phuong - Gastrointestinal Endoscopy - Department of Examination & Internal Medicine - Vinmec Central Park International General Hospital
Computer-aided disease (CAD) detection and diagnosis, thanks to the newly developed innovations of artificial intelligence, will help increase the detection rate of adenomas and thus contribute to a reduction in the incidence of cancer. , improves the effectiveness of colonoscopy in screening for important outcomes such as colorectal cancer-related mortality.

1. AI can help detect Polyps

The adenoma detection rate (ADR) was defined as the proportion of patients with at least one colorectal adenoma detected on initial colonoscopy, among all patients examined by a colonoscopy. check. The standard for ADR was generally 25% (30% in men, 20% in women) and it was reported that a 1% increase in ADR was associated with a 3% reduction in CRC incidence over the time period. A recent systematic review with Meta-Analysis reported that approximately 25% of colorectal cancers are missed on endoscopic examination, resulting in an unacceptable change in the primary quality index ADR, among endoscopists.
The rationale for the workflow, the support of the AI ​​CADe system is the attributes “Learning and Memorizing”. The CADe system was fed with data obtained from video recordings of colonoscopies post-modified by specialists. Among them, for example, a convolutional neural network (GI -nius, Medtronic) was installed and validated (99.7% sensitivity, 0.9% false-positive frame-trigger noise) using video library of 2684 histologically validated lesions, in a high quality clinical trial this CAD system collects input from standard endoscopic processor digital frames and outputs coordinates intensity of the signal box only if the instance of the target lesion is recognized in the image. Real-time assessment is made possible by the fact that this input-output process, which results in the CADe signal on the endoscopic display, is not a matter of time for the endoscopic surgeon, because it present instantaneously (1.52 ± 0.08 μs ie, 1.52 microseconds)

2. Evaluation studies

The average video recording of a 30-minute colonoscopy is taken at about 50000 frames, corresponding to 25-30 frames per second, and a colon polyp can be recognized even in several frames, explaining how failure of polyp recognition can occur, regardless of the modality of endoscopy.
In this way, this innovative new technology can provide much needed help in reducing the incidence of CRC and related mortality. In fact, the CADe system was recently introduced in the real-time endoscopic setting to correct the incidence of colonic lesions. The results reported by different multicenter and multicenter randomized clinical trials (RCTs) appear to be growing strongly: the overall ADRs of these studies were significantly higher when supported. by CADe systems as presented in Table 1: Repici et al performed in 2019 a multicenter study in which 700 consecutive patients aged 40 to 80 years were randomized 1:1 in CADe group and control group. ADR was significantly higher in the CADe group 54.8% vs 40.4%. They also reported Adenoma Per Colonoscopy, which was still higher in the CADe group (1.05 ± 1.55 vs 0.7 ± 1.19). Wang et al in 2019 performed an open trial in which 1058 consecutive patients were prospectively randomized to undergo diagnostic colonoscopy with (n=522) or without (n=536) ) the support of real-time automatic polyp detection system. Thanks to AI support, ADR increased from 20% to 29%. Wang et al in 2020 performed a double-blind single-center RCT that enrolled 1010 patients randomized in the CAD support arm (n=508) and control group (n=502), which reported higher ADRs. in the CAD support arm: 34.1% vs 28%. Gong et al in 2020 performed and RCT in which 704 patients were randomly assigned to either the ENDOANGEL CADe system (n=355) or unassisted colonoscopy (control) (n=349). ADR was significantly higher in the CADe group: 16.7% vs 8.2%. Liu et al enrolled 1026 patients in one RCT and randomized them to a Control (n=518) and an adjunctive CADe (n=508), also in this case, the reported ADR was high. significantly more on group supported CADe: 39.2% vs 24%. This type of AI could also help standardize colonoscopy regardless of operator and colonoscopy setting by removing subjective biases.
Table 1: The overall adenoma detection rates of these studies were significantly higher when supported by computer-aided detection systems.
Abbreviation: WL: White Light; RCT: Randomized clinical trial; CADe: Computer aided detection; ADR: Detection rate of adenomas.

3. Conclusion

Artificial Intelligence (AI) is an emerging technology whose application is rapidly increasing in many medical fields. Several applications of AI in gastroenterology are showing promising results, especially in the treatment of gastrointestinal cancers. Among these, techniques that can increase ADR will play an important role in reducing the incidence of CRC and its associated mortality from undetected or misclassified space cancers. Moreover, it is also expected to significantly reduce costs. In addition, the support of the machine will help reduce the examination time and thus optimize the endoscopic schedule.
Furthermore, the indication for colon polypectomy, supported by good sensitivity and specificity, will lead to a reduction in the direct cost of unnecessary polyps. Furthermore, higher diagnostic accuracy in identifying precancerous and cancerous lesions will lead to a reduction in the secondary costs of prevented cancers.
Despite promising results, AI techniques to detect and identify colorectal lesions still need to be studied further in the near future. In particular, since most of the results come from trials conducted in highly specialized centres, presenting a limitation on the generalizability of the results, they must also be validated in clinical practice.

Finally, the integration of AI in a fundamentally human medical environment must be considered: AI was not conceived, nor now, never, to replace the endoscopist, on the contrary, it seems as an extremely useful tool to be used from the endoscopist himself who, with his abilities and skills, is the only one who can process and interpret all the AI ​​information to make decisions on patient management.
Currently, gastrointestinal cancer screening is a scientific and effective measure for early detection of gastrointestinal cancer (esophageal cancer, stomach cancer, colon cancer) and giving a treatment plan. best treatment. Currently, Vinmec International General Hospital has a package of screening and early detection of cancers of the gastrointestinal tract (esophagus - stomach - colon) combined with clinical and paraclinical examination to bring the most accurate results. maybe.
When screening for gastrointestinal cancer at Vinmec, you will receive:
Gastrointestinal specialty examination with an oncologist (by appointment). Gastroscopy and colonoscopy with an NBI endoscope under anesthesia. Complete peripheral blood cytology (by laser counter). Automated prothrombin time test. Automated thrombin time test. Activated Partial Thromboplastin Time (APTT) test using an automated machine. General abdominal ultrasound

Please dial HOTLINE for more information or register for an appointment HERE. Download MyVinmec app to make appointments faster and to manage your bookings easily.

References
Emanuele Sinagra, Matteo Badalamenti, et al., Use of artificial intelligence in improving adenoma detection rate during colonoscopy: Might both endoscopists and pathologists be further helped. World J Gastroenterol. Oct 21, 2020; 26(39): 5911-5918 Torre LA, Bray F, Siegel RL, Ferlay J, Lortet-Tieulent J, Jemal A. Global cancer statistics, 2012. CA Cancer J Clin. 2015;65:87-108. [PubMed] [DOI] Maida M, Morreale G, Sinagra E, Ianiro G, Margherita V, Cirrone Cipolla A, Camilleri S. Quality measures improving endoscopic screening of colorectal cancer: a review of the literature. Expert Rev Anticancer Ther. 2019;19:223-235. [PubMed] [DOI]