AIneurysm helped doctors find more brain aneurysms on MR scans

In the maker's trial that China's CMDE reviewed, AIneurysm raised doctors' lesion-level sensitivity for brain aneurysms on MR angiograms by 0.0698.

  • Not rated an organization

    Doctors read stored images in the maker's pre-market trial, and no patient's care depended on 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

The same doctors reading the same MR angiograms without the software, with an expert panel's marks as the reference. Measured.

The system’s part
In a fully crossed design, every doctor read every case with and without the software, so the gain in sensitivity is attributed to the software. The trial was the maker's own. The report says that the aneurysm detection module uses deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
AIneurysm (颅内动脉瘤磁共振图像辅助检测软件)
Made by
Fuying (Shanghai) Medical Technology Co., Ltd. (复影（上海）医疗科技有限公司). The Paper reports that a Fudan University team led by Professor Geng Daoying developed the software.
Used by
Fuying (Shanghai) Medical Technology (retrospective reader trial on 486 cases from three centers)
Where
Three trial centers 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
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：颅内动脉瘤磁共振图像辅助检测软件 (technical review report for the registration of intracranial aneurysm detection-aid software for magnetic resonance images), acceptance no. CQZ2301701, applicant 复影（上海）医疗科技有限公司. 13 August 2024. Section 三、临床评价概述 (clinical evaluation).

    病灶水平下 AI 辅助阅片与单独阅片对动脉瘤检出灵敏度差值的 95%置信区间下限大于优效界值
    综上，该产品上市带来的受益大于风险，综合剩余风险可接受。

  2. News report, by authors with no tie to the system. Context or contrary evidence.

    The Paper (澎湃新闻), republished by ifeng.com (凤凰网科技). 高校主导、临床医生牵头，这款软件获批三类医疗器械注册证 (Led by a university and clinicians, this software wins a Class III medical device registration certificate). 6 September 2024. The figures are the development team's statements to the reporter.

    颅内动脉瘤磁共振造影图像辅助检测软件提升动脉瘤检出率10%，诊断效能由82%提高到94%，每例阅片时间缩短60%

Details

AI system

Reported configuration

Release 1 (full version 1.0.0.20240116)

Workflow

The software extracted the intracranial arteries from MR angiograms and marked suspected saccular aneurysms with deep learning. Doctors could edit the marks and produce a text report.

Follow-up

Conditions for replication

Images are brain MR angiograms, and aneurysms are 3 mm or larger. Trained doctors read the images and do not base a clinical decision on the software alone.

Entry details

Sector

Healthcare.

Purpose

Fuying (Shanghai) Medical Technology built AIneurysm to help trained doctors detect intracranial saccular aneurysms of 3 mm or more on brain MR angiography images.

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). AIneurysm helped doctors find more brain aneurysms on MR scans (AIBD-1061). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1061.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions