Artificial Intelligence Identifying Polyps in Real-world Colonoscopy

Mean Number of Polyps Per Colonoscopy for Colonoscopists and Colonoscopists + ADS Clinical Trial

Official title:

Validating the Performance of Artificial Intelligence in Identifying Polyps in Real-world Colonoscopy

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT03761771
• Other study ID #: AI-1
• Status: Completed
• Start date: November 1, 2018
• Est. completion date: December 10, 2018

Study information

• Verified date: December 2018
• Source: Changhai Hospital
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Recently, artificial intelligence (AI) assisted image recognition has made remarkable breakthroughs in various medical fields with the developing of deep learning and conventional neural networks (CNNs). However, all current AI assisted-diagnosis systems (ADSs) were established and validated on endoscopic images or selected videos, while its actual assisted-diagnosis performance in real-world colonoscopy is up to now unknown. Therefore, we validated the performance of an ADS in real-world colonoscopy, which is based on deep learning algorithm and CNNs, trained and tested in multicenter datasets of 20 endoscopy centers.

Description:

The ADS were established in changhai digestive endoscopy center to assess its efficacy in clinical practice. The ADS automatically initiated once the ileocecal valve was pictured by the colonoscopist or the colonoscopist recorded any image of colon during the insertion. When colonoscopists withdrew the colonoscopies and inspect the colons, the video streaming of colonoscopies was real-time switched to the ADS, which made it feasible to identify and classify lesions in real time. Colonoscopists were invited to respond if they doubted potential polyps in the screen, and the ADS also made a voice when identifying potential polyps, followed by repeatedly inspecting to confirm the existence of lesions. The voice of ADS could be real-time heard by colonoscopists, while the screen of ADS was placed right behind colonoscopists, where polyps identified by ADS could be seen after the colonoscopists' turning but not simultaneously. The lesion detection by ADS or colonoscopists were determined as follow: A. polyps only identified by ADS, which was considered to be missed by colonoscopists: polyps were reported by the ADS and the colonoscopists did not know the location of polyps without reminder of the ADS until the polyps disappeared from the view; B. polyps first identified by ADS: polyps were first reported by the ADS and the colonoscopists also later knew the location of polyps by themselves; C. polyps simultaneously identified by the ADS and colonoscopists: the time of reporting polyps was closely synchronal (within 1 second); D. polyps first reported by colonoscopists: polyps were first reported by the colonoscopists and the ADS also later identified the location of polyps before the colonoscopists unfolded and pictured the polyps; E. polyps only reported by colonoscopists, which was considered to be missed by the ADS: polyps were reported by the colonoscopists and the ADS did not identify the location of polyps until colonoscopists unfolded and pictured the polyps. Besides, the false-positives of real-world ADS were also reported with potential causes analyzed by colonoscopists.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 209
• Est. completion date: December 10, 2018
• Est. primary completion date: December 10, 2018
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years to 75 Years

Eligibility

Inclusion Criteria:

• patients receiving screening colonoscopy

• patients receiving surveillance colonoscopy

• patients receiving diagnostic colonoscopy

Exclusion Criteria:

• patients with declined consent

• patients with poor bowel preparation

• patients with failed cecal intubation

• patients with colonic resection

• patients with inflammatory bowel diseases

• patients with polyposis

Related Conditions & MeSH terms

• Mean Number of Polyps Per Colonoscopy for Colonoscopists and Colonoscopists + ADS
• Polyps
• Sensitivity of the ADS in Identifying Polyps in Real-world Colonoscopy

Intervention

Device:
• colonoscopy withdrawal with the ADS monitoring
During the testing of trained ADS, when the system doubts colonic lesions from the input data of the test images, a rectangular frame was displayed in the endoscopic image to surround the lesion. If the system confirmed it as the colonic lesions, a sound of reminder will be played and the types of lesions (non-adenomatous polyps, adenomatous polyps and colorectal cancers) will be classified by the system. We adopted several standards to define the identification and classification of colonic lesions: 1) when the system identified and confirmed any lesion in the images of no polyps or cancers, the results were judged to be false-positive. 2) when the system both confirmed and correctly localized the lesions in images (IoU > 0.3), the results were judged to be true-positive. 3) when the system did not confirm or correctly localize the lesions, the results were judged as false-negative. 4) when system confirmed no lesions in the normal images, the results were judged to be true-negative.

Locations

Country	Name	City	State
China	Changhai Hospital	Shanghai
China	Changhai Hospital, Second Military Medical University	Shanghai

Sponsors (1)

Lead Sponsor	Collaborator
Zhaoshen Li

Country where clinical trial is conducted

China, 

References & Publications (4)

Byrne MF, Chapados N, Soudan F, Oertel C, Linares Pérez M, Kelly R, Iqbal N, Chandelier F, Rex DK. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut. 2017 Oct 24. pii: gutjnl-2017-314547. doi: 10.1136/gutjnl-2017-314547. [Epub ahead of print] — View Citation

Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F, Karnes W, Baldi P. Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. Gastroenterology. 2018 Oct;155(4):1069-1078.e8. doi: 10.1053/j.gastro.2018.06.03 — View Citation

Wang Z, Meng Q, Wang S, Li Z, Bai Y, Wang D. Deep learning-based endoscopic image recognition for detection of early gastric cancer: a Chinese perspective. Gastrointest Endosc. 2018 Jul;88(1):198-199. doi: 10.1016/j.gie.2018.01.029. — View Citation

Wang Z, Zhao S, Bai Y. Artificial Intelligence as a Third Eye in Lesion Detection by Endoscopy. Clin Gastroenterol Hepatol. 2018 Sep;16(9):1537. doi: 10.1016/j.cgh.2018.04.032. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	sensitivity of the ADS in identifying polyps	Polyps that were only reported by colonoscopists were considered to be missed by the ADS (polyps were reported by the colonoscopists and the ADS did not identify the location of polyps until colonoscopists unfolded and pictured the polyps.)	1 hour
Secondary	false positves of the ADS per colonoscopy withdrawal	when the system identified and confirmed any lesion in the images with no polyps or cancers appearing, the results were judged to be false-positive.	1 hour