A Deep Learning-Based Automatic Recognition Model for Polycystic Ovary Ultrasound Images

IF 3.8 4区医学 Q2 MEDICINE, GENERAL & INTERNAL

Balkan Medical Journal Pub Date : 2025-09-01 Epub Date: 2025-08-11 DOI:10.4274/balkanmedj.galenos.2025.2025-5-114

Baihua Zhao, Lieming Wen, Yunxia Huang, Yaqian Fu, Shan Zhou, Jieyu Liu, Minghui Liu, Yingjia Li

{"title":"A Deep Learning-Based Automatic Recognition Model for Polycystic Ovary Ultrasound Images","authors":"Baihua Zhao, Lieming Wen, Yunxia Huang, Yaqian Fu, Shan Zhou, Jieyu Liu, Minghui Liu, Yingjia Li","doi":"10.4274/balkanmedj.galenos.2025.2025-5-114","DOIUrl":null,"url":null,"abstract":"Background: Polycystic ovary syndrome (PCOS) has a significant impact on endocrine metabolism, reproductive function, and mental health in women of reproductive age. The accuracy of ultrasound in identifying polycystic ovarian morphology remains variable.Aims: To develop a deep learning model capable of rapidly and accurately identifying PCOS using ovarian ultrasound images.Study design: Prospective diagnostic accuracy study.Methods: This prospective study included data from 1,751 women with suspected PCOS with clinical and ultrasound information collected and archived. Patients from center 1 were randomly divided into a training set and an internal validation set in a 7:3 ratio, while patients from center 2 served as the external validation set. Using the YOLOv11 deep learning framework, an automated recognition model for ovarian ultrasound images in PCOS cases was constructed, and its diagnostic performance was evaluated.Results: Ultrasound images from 933 patients (781 from center 1 and 152 from center 2) were analyzed. The mean average precision of the YOLOv11 model in detecting the target ovary was 95.7%, 97.6%, and 97.8% for the training, internal validation, and external validation sets, respectively. For diagnostic classification, the model achieved an F1 score of 95.0% in the training set and 96.9% in both validation sets. The area under the curve values were 0.953, 0.973, and 0.967 for the training, internal validation, and external validation sets respectively. The model also demonstrated significantly faster evaluation of a single ovary compared to clinicians (doctor, 5.0 seconds; model, 0.1 seconds; p < 0.01).Conclusion: The YOLOv11-based automatic recognition model for PCOS ovarian ultrasound images exhibits strong target detection and diagnostic performance. This approach can streamline the follicle counting process in conventional ultrasound and enhance the efficiency and generalizability of ultrasound-based PCOS assessment.","PeriodicalId":8690,"journal":{"name":"Balkan Medical Journal","volume":" ","pages":"419-428"},"PeriodicalIF":3.8000,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12402960/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Balkan Medical Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4274/balkanmedj.galenos.2025.2025-5-114","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/11 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Polycystic ovary syndrome (PCOS) has a significant impact on endocrine metabolism, reproductive function, and mental health in women of reproductive age. The accuracy of ultrasound in identifying polycystic ovarian morphology remains variable.

Aims: To develop a deep learning model capable of rapidly and accurately identifying PCOS using ovarian ultrasound images.

Study design: Prospective diagnostic accuracy study.

Methods: This prospective study included data from 1,751 women with suspected PCOS with clinical and ultrasound information collected and archived. Patients from center 1 were randomly divided into a training set and an internal validation set in a 7:3 ratio, while patients from center 2 served as the external validation set. Using the YOLOv11 deep learning framework, an automated recognition model for ovarian ultrasound images in PCOS cases was constructed, and its diagnostic performance was evaluated.

Results: Ultrasound images from 933 patients (781 from center 1 and 152 from center 2) were analyzed. The mean average precision of the YOLOv11 model in detecting the target ovary was 95.7%, 97.6%, and 97.8% for the training, internal validation, and external validation sets, respectively. For diagnostic classification, the model achieved an F1 score of 95.0% in the training set and 96.9% in both validation sets. The area under the curve values were 0.953, 0.973, and 0.967 for the training, internal validation, and external validation sets respectively. The model also demonstrated significantly faster evaluation of a single ovary compared to clinicians (doctor, 5.0 seconds; model, 0.1 seconds; p < 0.01).

Conclusion: The YOLOv11-based automatic recognition model for PCOS ovarian ultrasound images exhibits strong target detection and diagnostic performance. This approach can streamline the follicle counting process in conventional ultrasound and enhance the efficiency and generalizability of ultrasound-based PCOS assessment.

Abstract Image

查看原文本刊更多论文

基于深度学习的多囊卵巢超声图像自动识别模型。

背景：多囊卵巢综合征（PCOS）对育龄妇女的内分泌代谢、生殖功能和心理健康有显著影响。超声仍然是多囊卵巢综合征的重要诊断工具，特别是在伴有多囊卵巢的少经血或排卵功能障碍以及多囊卵巢相关的高雄激素症的个体中。然而，超声识别多囊卵巢形态的准确性仍然是可变的。目的：建立一种基于卵巢超声图像快速准确识别PCOS的深度学习模型。研究设计：前瞻性诊断准确性研究。方法：本前瞻性研究纳入了中南大学两家附属医院1751例疑似多囊卵巢综合征的妇女，收集临床和超声信息并存档。中心1的患者按7:3的比例随机分为训练集和内部验证集，中心2的患者作为外部验证集。利用YOLOv11深度学习框架，构建PCOS病例卵巢超声图像的自动识别模型，并对其诊断性能进行评价。结果：对933例患者的超声图像进行分析，其中1中心781例，2中心152例。在训练集、内部验证集和外部验证集上，YOLOv11模型检测目标卵巢的平均精度分别为95.7%、97.6%和97.8%。对于诊断分类，该模型在训练集中的F1得分为95.0%，在两个验证集中的F1得分为96.9%。训练集、内部验证集和外部验证集的曲线下面积分别为0.953、0.973和0.967。与临床医生相比，该模型对单个卵巢的评估也明显更快(医生，5.0秒；模型，0.1秒；P < 0.01)。结论：基于yolov11的PCOS卵巢超声图像自动识别模型具有较强的目标检测和诊断能力。该方法简化了常规超声的卵泡计数过程，提高了超声诊断PCOS的效率和通用性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Balkan Medical Journal MEDICINE, GENERAL & INTERNAL-

CiteScore

4.10

自引率

6.70%

发文量

审稿时长

6-12 weeks

期刊介绍： The Balkan Medical Journal (Balkan Med J) is a peer-reviewed open-access international journal that publishes interesting clinical and experimental research conducted in all fields of medicine, interesting case reports and clinical images, invited reviews, editorials, letters, comments and letters to the Editor including reports on publication and research ethics. The journal is the official scientific publication of the Trakya University Faculty of Medicine, Edirne, Turkey and is printed six times a year, in January, March, May, July, September and November. The language of the journal is English. The journal is based on independent and unbiased double-blinded peer-reviewed principles. Only unpublished papers that are not under review for publication elsewhere can be submitted. Balkan Medical Journal does not accept multiple submission and duplicate submission even though the previous one was published in a different language. The authors are responsible for the scientific content of the material to be published. The Balkan Medical Journal reserves the right to request any research materials on which the paper is based. The Balkan Medical Journal encourages and enables academicians, researchers, specialists and primary care physicians of Balkan countries to publish their valuable research in all branches of medicine. The primary aim of the journal is to publish original articles with high scientific and ethical quality and serve as a good example of medical publications in the Balkans as well as in the World.