Yizhun-DBU helped less senior sonographers find breast lesions

In the maker's trial that China's CMDE reviewed, six less senior readers detected breast lesions with an AFROC-AUC of 0.8785 using Yizhun-DBU, against 0.6500 alone.

  • Not rated an organization

    Readers were scored against senior readers' judgment in the maker's pre-market trial, and the report does not say that the marks guided any patient's care.

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 six readers reading the same cases without the software, with three senior readers as the reference. Measured.

Without the system
AFROC-AUC 0.6500(0.6268, 0.6733)
With it
AFROC-AUC 0.8785 (0.8471, 0.9100)
The system’s part
The same six readers read every case with and without the software, so the gain is attributed to the software. The trial was the maker's own. The reference standard was three senior readers, and the report mentions no pathology.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Yizhun-DBU (乳腺超声影像辅助检测软件)
Made by
Beijing Yizhun Medical Technology Co., Ltd. (北京医准医疗科技有限公司)
Used by
Beijing Yizhun Medical Technology (prospective reader trial with 176 subjects at three sites)
Where
Three trial sites 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, 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：乳腺超声影像辅助检测软件 (technical review report for the registration of breast ultrasound image detection-aid software), acceptance no. CQZ2400392, applicant 北京医准医疗科技有限公司. 25 February 2025. Section 三、临床评价概述 (clinical evaluation).

    试验组的 AFROC-AUC 为 0.8785 (0.8471, 0.9100)，对照组的AFROC-AUC 为 0.6500(0.6268, 0.6733)
    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。

Details

AI system

Reported configuration

Release 4

Workflow

A video capture card fed the scanner's output to the software, which marked suspected masses in real time. Six mid- and junior-level readers read each case with and without the marks.

Follow-up

Conditions for replication

Patients are adult women without prior breast removal, ablation, radiotherapy, chemotherapy or implants. Images come from the specified ultrasound devices and probes. Sonographers judge each case from the images and the patient's condition and do not decide on the marks alone.

Entry details

Sector

Healthcare.

Purpose

Beijing Yizhun Medical Technology built Yizhun-DBU to mark suspected breast masses over 5 mm in real time in the video of breast ultrasound examinations of adult women.

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). Yizhun-DBU helped less senior sonographers find breast lesions (AIBD-0961). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-0961.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions