New Strategy of Knowledge-Enhanced Large Model for Ultrasound Scanning and Diagnosis of Ovarian Masses
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.
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.
Inclusion Criteria:
Exclusion Criteria:
qinjiale@zju.edu.cn+86 0571-89998869
12418399@zju.edu.cn
yh0464@163.com+86 0575-88211352
505571621@qq.com