MY-CJ-01 raised first-pass polyp detection in Tencent's trial

China's CMDE found that first-pass polyp detection was superior in group B of Tencent's randomized MY-CJ-01 trial. The polyp miss rate was 23.39%, against 44.67% in group A.

  • Not rated an organization

    The gain was measured in the maker's pre-market trial, and the report gives no outcome of care and does not say how each group used the software.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Group A of the same randomized trial (the report does not say how each group used the software). Measured.

Without the system
Polyp miss rate 44.67% (95%CI:39.07%~50.42%) in group A
With it
Polyp miss rate 23.39% (95%CI:18.92%~28.54%) in group B
The system’s part
The randomized trial compared two groups of patients to test the software for superiority, so it isolates the software's part. The report does not say how each group used the software. Group B is presumed to have used it in the first examination because CMDE found its result superior. The trial was the maker's own.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
MY-CJ-01 (结肠息肉电子内窥镜图像辅助检测软件)
Made by
Tencent Healthcare (Shenzhen) Co., Ltd. (腾讯医疗健康（深圳）有限公司)
Used by
Tencent Healthcare (Shenzhen) (prospective randomized trial with 296 patients at two centers)
Where
Two trial centers that the report does not name, for a registration in China
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Monitoring Processes, Materials, or Surroundings
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Center for Medical Device Evaluation (CMDE), National Medical Products Administration, China. 医疗器械产品注册技术审评报告：结肠息肉电子内窥镜图像辅助检测软件 (technical review report for the registration of colon polyp electronic endoscope image detection-aid software), acceptance no. CQZ2200455, applicant 腾讯医疗健康（深圳）有限公司. 18 May 2023. Section 三、临床评价概述 (clinical evaluation), pp. 6-7.

    A 组息肉漏检率为 44.67% (95%CI:39.07%~50.42%)，B 组息肉漏检率为23.39% (95%CI:18.92%~28.54%)
    根据申请人提供的申报资料，经综合评价，在目前认知水平上，认为该产品的上市为适用人群带来的受益大于风险。

  2. Regulatory document, by authors with no tie to the system. Context or contrary evidence.

    National Medical Products Administration (NMPA), China. Computer-aided Detection Software for Electronic Endoscope for Colon Polyps Approved for Marketing. NMPA English website, 1 June 2023.

    Recently, the innovative product computer-aided detection software for electronic endoscope for colon polyps of Tencent Healthcare (Shenzhen) Co., Ltd. is approved by China NMPA.

Details

AI system

Reported configuration

Release V2 (full version V2.0.0_build001)

Workflow

The software took the video stream from the endoscope's image processor and marked suspected polyps with a deep learning algorithm on a separate video client. Patients at two centers were randomized to two groups in a prospective superiority trial.

Follow-up

Conditions for replication

Patients are adults having colonoscopy in a medical institution. The endoscope is a specified model used in white light mode. Endoscopists judge polyps from the images and the patient's condition and do not decide on the marks alone.

Entry details

Sector

Healthcare.

Purpose

Tencent Healthcare (Shenzhen) built MY-CJ-01 to mark suspected polyps in real time in the video of adult colonoscopies for endoscopists.

29 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). MY-CJ-01 raised first-pass polyp detection in Tencent's trial (AIBD-1068). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1068.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions