An AI-Assisted Agentic System for Ultrasound Scanning and Diagnosis of Ovarian Lesions

New Strategy of Knowledge-Enhanced Large Model for Ultrasound Scanning and Diagnosis of Ovarian Masses

Investigators developed an interactive agentic system designed to guide newly qualified sonographers in ovarian lesion scanning and improve their scanning quality and diagnostic performance toward expert-level standards. Our agentic system is capable of capturing key features including the max-diameter plane of ovarian lesions from dynamic ultrasound videos, translating these findings into standardized International Ovarian Tumor Analysis (IOTA) descriptors, and providing multi-turn guidance for subsequent scanning, and ultimately generating an AI-assisted diagnostic assessment based on embedded expert knowledge.

In this multicenter study, participants are asked to undergo gynecological ultrasonography performed by sonographers with less than 3 years of experience with or without AI assistance. Our researchers will compare the performance of operators working with AI against that of operators working without AI, as well as against the performance of expert sonographers, to see whether AI assistance enhances the proficiency of less experienced operators and help them approach the scanning quality and diagnostic accuracy of expert sonographers in real-world clinical scenarios.

Study Overview

• Status: Not yet recruiting
• Conditions: Adnexal Mass; Ovarian Mass
• Intervention / Treatment: Other: non-AI assisted and then AI assisted; Other: AI assisted and then non-AI assisted

Detailed Description

This multicenter, prospective study will be conducted at tertiary cancer centers and primary healthcare institutions across China. Participants will be recruited from gynecological ultrasound clinics of each site.

Each participant will undergo gynecological ultrasonography under both AI-assisted and unassisted conditions according to their group allocation. Following completion of the study examinations, expert sonographers with more than 10 years of experience, blinded to the scanning and diagnostic results of the junior sonographers, will independently perform a repeat gynecological ultrasound examination of each participant. Based solely on their independent examination, they will issue the final clinical report for each participant. The expert assessments will serve as one reference standard for evaluating scanning completeness, feature interpretation accuracy and diagnostic agreement. Histopathological findings, when available, or clinical follow-up for conservatively managed lesions will serve as the reference standard for evaluating diagnostic accuracy.

• Study Type: Observational
• Enrollment (Estimated): 250

Contacts and Locations

• Study Contact: Name: Jiale Qin, Prof., Professor; Phone Number: +86 0571-89998869; Email: qinjiale@zju.edu.cn
• Study Contact Backup: Name: Ruixia Dai, Ph.D. student; Email: 12418399@zju.edu.cn

Study Locations

• China
  • Zhejiang
    • Hangzhou, Zhejiang, China, 310006
      • Women's Hospital School Of Medicine Zhejiang University
      • Contact: Jiale Qin, Prof., Professor; Phone Number: +86 0571-89998869; Email: qinjiale@zju.edu.cn
      • Contact: Ruixia Dai, Ph.D. student; Email: 12418399@zju.edu.cn
    • Shaoxing, Zhejiang, China, 311800
      • Shaoxing Maternity and Child Health Care Hospital
      • Contact: Hua Yuan, Chief physician in ultrasound; Phone Number: +86 0575-88211352; Email: yh0464@163.com
      • Contact: Xuezhen Lou, Attending physician; Email: 505571621@qq.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Participants, with suspected ovarian masses identified clinically or by previous imaging examination, will be consecutively recruited from gynecological ultrasound clinics of tertiary cancer centers and primary healthcare institutions across China.

Description

Inclusion Criteria:

• Female aged 18-75 years
• With suspected ovarian masses identified clinically or by previous imaging examination
• Eligible for and able to undergo transvaginal or transabdominal ultrasonography
• Agree to provide written informed consent before enrollment

Exclusion Criteria:

• No ovarian mass identified on ultrasound examination
• Previous bilateral oophorectomy
• Previous surgery or chemotherapy for ovarian cancer
• Previous treatment for other malignant tumors
• Presence of any psychiatric or psychological disorders that may prevent completion of the study procedures or follow-up
• Concurrent participation in other clinical trials that may interfere with the outcomes of this study

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Arm A: experimental sequence of non-AI exertion followed by AI-assisted exertion; The goal is to test the within-operator effect associated with AI assistance by comparing the performance of the same junior sonographer before and after AI guidance, and to compare the performance of both AI-assisted and unaided junior sonographers with that of the standalone AI model.	Other: non-AI assisted and then AI assisted; Participants first undergo ultrasound scanning and diagnosis by a junior sonographer without AI assistance, followed by ultrasound scanning by the same sonographer with AI assistance.
Arm B: experimental sequence of AI-assisted exertion followed by non-AI exertion; The goal is to test the clinical utility of AI with minimized potential carry-over effects and recall bias caused by repeated examinations on the same patient, by comparing the performance of one junior sonographer with AI-assisted, with that of independent unaided junior sonographers, and by comparing the performance of both AI-assisted junior sonographers and another unaided ones with that of the standalone AI model.	Other: AI assisted and then non-AI assisted; Participants first undergo ultrasound scanning and diagnosis by a junior sonographer with AI assistance, followed by ultrasound scanning by another junior sonographer without AI assistance. The two junior sonographers are blinded to each other's scanning and assessment results.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Completeness of ultrasound feature acquisition	The completeness of ultrasound feature acquisition will be assessed with reference to national authoritative quality-control standards. After each examination, all stored ultrasound images and videos will be labeled according to their intended purpose. A feature will be considered adequately acquired when at least one stored image or video provides sufficient visual evidence for assessment of that feature. The proportion of required features successfully acquired will be calculated. The proportion of redundant stored images will also be recorded as an additional indicator of acquisition quality.	Up to 7 days from completion of the study
Accuracy of interpretation of individual ultrasound features	The accuracy of interpretation of ultrasound features will be assessed by comparing the assessments made by junior sonographers under AI-assisted and unassisted conditions with the findings independently acquired and interpreted by expert sonographers during a separate repeat ultrasound examination. The accuracy rate for each feature will be calculated.	Up to 7 days from completion of the study
Agreement between junior and expert sonographers in ultrasound diagnosis	Agreement between junior and expert sonographers will be assessed for the final diagnosis of ovarian lesions. The assessments made by junior sonographers under AI-assisted and unassisted conditions will be compared with the corresponding diagnoses independently obtained by expert sonographers during a separate repeat ultrasound examination, which will then be quantified using appropriate agreement statistics.	Up to 7 days from completion of the study
Diagnostic accuracy of ovarian tumors	Diagnostic accuracy will be assessed against histopathological diagnosis as the golden reference standard. This outcome will be evaluated only in participants who undergo surgical treatment and have definitive histopathological findings based on paraffin-embedded surgical specimens.	Within 3 months after the ultrasonography examination
Diagnostic performance of ovarian tumors	Area under curve will be assessed against histopathological diagnosis as the golden reference standard. This outcome will be evaluated only in participants who undergo surgical treatment and have definitive histopathological findings based on paraffin-embedded surgical specimens.	Within 3 months after the ultrasonography examination
Diagnostic performance of ovarian tumors	Diagnostic sensitivity and specificity will be assessed against histopathological diagnosis as the golden reference standard. This outcome will be evaluated only in participants who undergo surgical treatment and have definitive histopathological findings based on paraffin-embedded surgical specimens.	Within 3 months after the ultrasonography examination
Diagnostic performance of ovarian tumors	Diagnostic F1-score will be assessed against histopathological diagnosis as the golden reference standard. This outcome will be evaluated only in participants who undergo surgical treatment and have definitive histopathological findings based on paraffin-embedded surgical specimens.	Within 3 months after the ultrasonography examination

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Confidence in ultrasound feature acquisition and diagnosis	Sonographers' confidence in the completeness and adequacy of feature acquisition and in their final diagnostic assessment will be evaluated using a predefined rating scale as follows: 5 = very confident, 4 = confident, 3 = uncertain, 2 = less confident, and 1 = not confident at al.	Up to 7 days from completion of the study

Collaborators and Investigators

• Sponsor: Women's Hospital School Of Medicine Zhejiang University
• Collaborators: Shaoxing Maternity and Child Health Care Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): August 19, 2026
• Primary Completion (Estimated): March 31, 2027
• Study Completion (Estimated): March 31, 2027

Study Registration Dates

• First Submitted: August 17, 2026
• First Submitted That Met QC Criteria: September 2, 2026
• First Posted (Actual): September 3, 2026

Study Record Updates

• Last Update Posted (Actual): September 3, 2026
• Last Update Submitted That Met QC Criteria: September 2, 2026
• Last Verified: September 1, 2026

More Information

Terms related to this study

• Other Study ID Numbers: IRB-20250490-R

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No