uAI-CT_CerebralPerfusion agreed with a marketed tool on stroke scans

In the maker's trial that China's CMDE reviewed, uAI-CT_CerebralPerfusion measured infarct core and penumbra volumes with ICCs of 0.96 and 0.83 against an already-marketed product.

  • Not rated an organization

    The volumes were measured on stored images in the maker's pre-market trial, and no patient's care depended on them.

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

An already-marketed cerebral ischemia image assessment software of the same kind on the same cases, with a target ICC of 0.75 for the lower 95% confidence bound. Measured.

Without the system
Target ICC of 0.75
With it
ICC 0.96 (95%CI: 0.95, 0.97) for the infarct core and 0.83 (95%CI: 0.79, 0.86) for the penumbra
The system’s part
Not isolated. The trial measured the software's volumes against those of an already-marketed product of the same kind. It did not compare doctors' assessments with and without the software. The trial was the maker's own. The report says that the product uses deep learning for segmentation and measurement.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
uAI-CT_CerebralPerfusion (脑缺血CT灌注图像辅助评估软件)
Made by
Shanghai United Imaging Intelligence Co., Ltd. (上海联影智能医疗科技有限公司)
Used by
Shanghai United Imaging Intelligence (retrospective registration trial with 446 cases at six institutions)
Where
Six trial institutions that the report does not name, for a registration in China
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Identifying Objects, Actions, and Events
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：脑缺血CT灌注图像辅助评估软件 (technical review report for the registration of cerebral ischemia CT perfusion image assessment-aid software), acceptance no. CQZ2401663, applicant 上海联影智能医疗科技有限公司. 26 June 2025. Section 三、临床评价概述 (clinical evaluation).

    主要评价指标软件评估梗死区体积 ICC一致性系数为 0.96 (95%CI: 0.95, 0.97)
    经综合评价，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 1.1 (full version 1.1-0-0-56)

Workflow

The software segmented brain CT perfusion images with deep learning and measured the volumes of the infarct core and the penumbra. Its volumes were compared with those of an already-marketed product on the same 446 cases.

Follow-up

Conditions for replication

Patients are adults with ischemic stroke who have brain CT perfusion images. Trained doctors use the volumes and do not base a clinical decision on the software alone.

Entry details

Sector

Healthcare.

Purpose

Shanghai United Imaging Intelligence built uAI-CT_CerebralPerfusion to help trained doctors assess infarct core and penumbra volumes on brain CT perfusion images of adults with ischemic stroke.

30 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, 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). uAI-CT_CerebralPerfusion agreed with a marketed tool on stroke scans (AIBD-1093). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1093.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions