CCAA.91360 cut the time to read cervical cytology slides

In the maker's trial that China's CMDE reviewed, pathologists took a mean 64.12 seconds per cervical cytology slide with CCAA.91360, against 333.49 seconds reading digital slides alone.

  • Not rated an organization

    Pathologists read slides faster in the maker's pre-market trial, where microscope reading was the reference, so no time saved in routine work is measured.

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

Digital reading of the same slides without the software. Measured.

Without the system
Mean diagnosis time 333.49 seconds
With it
Mean diagnosis time 64.12 seconds
The system’s part
Pathologists read the same slides digitally with and without the software, so the time saved is attributed to the software. The trial was the maker's own, and microscope reading was the reference.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
CCAA.91360 (宫颈细胞学数字病理图像计算机辅助分析软件)
Made by
91360 Medical Technology (Nanjing) Co., Ltd. (玖壹叁陆零医学科技南京有限公司)
Used by
91360 Medical Technology (Nanjing) (registration trial at the First Affiliated Hospital of Nanjing Medical University and the Affiliated Drum Tower Hospital of Nanjing University Medical School)
Where
Nanjing, Jiangsu, China
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Analyzing Data or Information
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：宫颈细胞学数字病理图像计算机辅助分析软件 (technical review report for the registration of cervical cytology digital pathology image computer-aided analysis software), acceptance no. CQZ2101339, applicant 玖壹叁陆零医学科技南京有限公司. 3 March 2023. Section 三、临床评价概述 (clinical evaluation), pp. 7-8.

    两者的均数差值为-269.37（95CI：-382.05，-156.69） ，小于方案规定的优效界值，因此认为本软件辅助数字阅片的诊断时间效率优于单独数字阅片。
    经综合评价，在目前认知水平上，认为该产品上市带来的受益大于风险，综合剩余风险可接受。

Details

AI system

Reported configuration

Release V2

Workflow

Slides prepared by the membrane-based liquid-based thin-layer method were scanned on a specified slide scanner. The software segmented cell nuclei with a deep convolutional neural network, classified the cells and marked suspected abnormal ones for the pathologist.

Follow-up

Conditions for replication

Pathologists review the whole digital image and not only the marked cells. The prompts are not the sole basis for a diagnosis, and the software is not used for cervical cancer screening. Patients who had radiotherapy or surgery removing the whole cervix are excluded.

Entry details

Sector

Healthcare.

Purpose

91360 Medical Technology (Nanjing) built CCAA.91360 to mark suspected abnormal cells in scanned cervical cytology slides and give cytopathologists a diagnostic prompt.

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). CCAA.91360 cut the time to read cervical cytology slides (AIBD-1070). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1070.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions