95% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Oncol.
Sec. Gynecological Oncology
Volume 15 - 2025 | doi: 10.3389/fonc.2025.1549803
This article is part of the Research Topic Deep Learning for Medical Imaging Applications View all 14 articles
Artificial Intelligence for Instance Segmentation of MRI: Advancing Efficiency and Safety in Laparoscopic Myomectomy of Broad Ligament Fibroids
Provisionally accepted- 1 Department of Obstetrics and Gynecology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
- 2 college of software, Beijing University, Beijing, Haiti
- 3 Department of MRI, Beijing Shijitan Hospital, Beijing, China
In this research endeavor, we harnessed AI instance segmentation of magnetic resonance images to assist laparoscopic myomectomy procedures. We assembled a cohort comprising 120 patients diagnosed with broad ligament fibroid, which underwent magnetic resonance imaging (MRI) examinations. Subsequently, half of the participants were randomly designated to undergo AI instance segmentation procedures. Our AI system has demonstrated exceptional ability to elucidate the precise spatial localization of broad ligament fibroids. The results of our study showcased the adoption of AI render the reduction of operation time(140.00(115.75-160.75)min vs . 118.00(112.25-125.00)min, p<0.001), proportion of people whose surgery lasted more than or equal to 150 minutes(27[45.00] vs. 4[6.67],p<0.001), blood loss(85.00(50.00-100.00)ml vs. 50.00(50.00-100.00)ml, p=0.01), and the facilitation of the first flatus within 24 hours after surgery(15[25.00%] vs . 29[48.33%], p=0.01) in procedures assisted by AI. Our multidisciplinary team, rooted in deep learning technology, developed a comprehensive suite of algorithms，addressing fibroids segmentation tasks. Consequently, our findings substantiate the potential of AI-driven interventions within the field of gynecological surgery.
Keywords: Wenpei Bai: Supervision, Writing -review & editing. Haixia Pan: Software, Writing -review & editing. Bin Li: Methodology, Writing -review & editing. Feiran Liu: Writing -original draft, Writing -review & editing. Minghuang Chen: Methodology, Writing -review & editing artificial intelligence -AI, uterine myoma, Instance segmentation
Received: 22 Dec 2024; Accepted: 18 Mar 2025.
Copyright: © 2025 Liu, Chen, Pan, Li and Bai. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Feiran Liu, Department of Obstetrics and Gynecology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.