A Study on Automatic O-RADS Classification of Sonograms of Ovarian Adnexal Lesions Based on Deep Convolutional Neural Networks

IF 2.4 3区医学 Q2 ACOUSTICS

Ultrasound in Medicine and Biology Pub Date : 2025-02-01 DOI:10.1016/j.ultrasmedbio.2024.11.009

Tao Liu, Kuo Miao, Gaoqiang Tan, Hanqi Bu, Xiaohui Shao, Siming Wang, Xiaoqiu Dong

{"title":"A Study on Automatic O-RADS Classification of Sonograms of Ovarian Adnexal Lesions Based on Deep Convolutional Neural Networks","authors":"Tao Liu, Kuo Miao, Gaoqiang Tan, Hanqi Bu, Xiaohui Shao, Siming Wang, Xiaoqiu Dong","doi":"10.1016/j.ultrasmedbio.2024.11.009","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>This study explored a new method for automatic O-RADS classification of sonograms based on a deep convolutional neural network (DCNN).</div></div><div><h3>Methods</h3><div>A development dataset (DD) of 2,455 2D grayscale sonograms of 870 ovarian adnexal lesions and an intertemporal validation dataset (IVD) of 426 sonograms of 280 lesions were collected and classified according to O-RADS v2022 (categories 2–5) by three senior sonographers. Classification results verified by a two-tailed z-test to be consistent with the O-RADS v2022 malignancy rate indicated the diagnostic performance was comparable to that of a previous study and were used for training; otherwise, the classification was repeated by two different sonographers. The DD was used to develop three DCNN models (ResNet34, DenseNet121, and ConvNeXt-Tiny) that employed transfer learning techniques. Model performance was assessed for accuracy, precision, and F1 score, among others. The optimal model was selected and validated over time using the IVD and to analyze whether the efficiency of O-RADS classification was improved with the assistance of this model for three sonographers with different years of experience.</div></div><div><h3>Results</h3><div>The proportion of malignant tumors in the DD and IVD in each O-RADS-defined risk category was verified using a two-tailed z-test. Malignant lesions (O-RADS categories 4 and 5) were diagnosed in the DD and IVD with sensitivities of 0.949 and 0.962 and specificities of 0.892 and 0.842, respectively. ResNet34, DenseNet121, and ConvNeXt-Tiny had overall accuracies of 0.737, 0.752, and 0.878, respectively, for sonogram prediction in the DD. The ConvNeXt-Tiny model's accuracy for sonogram prediction in the IVD was 0.859, with no significant difference between test sets. The modeling aid significantly reduced O-RADS classification time for three sonographers (Cohen's d = 5.75).</div></div><div><h3>Conclusion</h3><div>ConvNeXt-Tiny showed robust and stable performance in classifying O-RADS 2–5, improving sonologists' classification efficacy.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 387-395"},"PeriodicalIF":2.4000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ultrasound in Medicine and Biology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0301562924004307","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

This study explored a new method for automatic O-RADS classification of sonograms based on a deep convolutional neural network (DCNN).

Methods

A development dataset (DD) of 2,455 2D grayscale sonograms of 870 ovarian adnexal lesions and an intertemporal validation dataset (IVD) of 426 sonograms of 280 lesions were collected and classified according to O-RADS v2022 (categories 2–5) by three senior sonographers. Classification results verified by a two-tailed z-test to be consistent with the O-RADS v2022 malignancy rate indicated the diagnostic performance was comparable to that of a previous study and were used for training; otherwise, the classification was repeated by two different sonographers. The DD was used to develop three DCNN models (ResNet34, DenseNet121, and ConvNeXt-Tiny) that employed transfer learning techniques. Model performance was assessed for accuracy, precision, and F1 score, among others. The optimal model was selected and validated over time using the IVD and to analyze whether the efficiency of O-RADS classification was improved with the assistance of this model for three sonographers with different years of experience.

Results

The proportion of malignant tumors in the DD and IVD in each O-RADS-defined risk category was verified using a two-tailed z-test. Malignant lesions (O-RADS categories 4 and 5) were diagnosed in the DD and IVD with sensitivities of 0.949 and 0.962 and specificities of 0.892 and 0.842, respectively. ResNet34, DenseNet121, and ConvNeXt-Tiny had overall accuracies of 0.737, 0.752, and 0.878, respectively, for sonogram prediction in the DD. The ConvNeXt-Tiny model's accuracy for sonogram prediction in the IVD was 0.859, with no significant difference between test sets. The modeling aid significantly reduced O-RADS classification time for three sonographers (Cohen's d = 5.75).

Conclusion

ConvNeXt-Tiny showed robust and stable performance in classifying O-RADS 2–5, improving sonologists' classification efficacy.

查看原文本刊更多论文

基于深度卷积神经网络的卵巢附件病变声像图 O-RADS 自动分类研究

目的本研究探索了一种基于深度卷积神经网络（DCNN）的声像图 O-RADS 自动分类新方法：方法：由三位资深超声技师根据 O-RADS v2022（2-5 类）收集并分类了包含 870 例卵巢附件病变的 2,455 张二维灰度声像图的开发数据集（DD）和包含 280 例病变的 426 张声像图的时际验证数据集（IVD）。分类结果经双尾z检验验证与O-RADS v2022恶性率一致，表明诊断性能与之前的一项研究相当，并用于训练；否则，由两名不同的超声技师重复进行分类。DD 被用于开发采用迁移学习技术的三个 DCNN 模型（ResNet34、DenseNet121 和 ConvNeXt-Tiny）。对模型性能进行了准确度、精确度和 F1 分数等方面的评估。选择了最佳模型，并使用 IVD 进行了长期验证，以分析在该模型的帮助下，三位具有不同年限经验的超声技师的 O-RADS 分类效率是否有所提高：采用双尾z检验验证了DD和IVD中恶性肿瘤在每个O-RADS定义的风险类别中所占的比例。在 DD 和 IVD 诊断出恶性病变（O-RADS 类别 4 和 5）的敏感性分别为 0.949 和 0.962，特异性分别为 0.892 和 0.842。ResNet34、DenseNet121 和 ConvNeXt-Tiny 对 DD 声像图预测的总体准确度分别为 0.737、0.752 和 0.878。ConvNeXt-Tiny 模型对 IVD 声像图预测的准确率为 0.859，不同测试集之间没有显著差异。建模辅助工具大大缩短了三位超声技师的 O-RADS 分类时间（Cohen's d = 5.75）：结论：ConvNeXt-Tiny 在 O-RADS 2-5 级分类中表现出强大而稳定的性能，提高了超声技师的分类效率。

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

Ultrasound in Medicine and Biology 医学-核医学

CiteScore

6.20

自引率

6.90%

发文量

325

审稿时长

70 days

期刊介绍： Ultrasound in Medicine and Biology is the official journal of the World Federation for Ultrasound in Medicine and Biology. The journal publishes original contributions that demonstrate a novel application of an existing ultrasound technology in clinical diagnostic, interventional and therapeutic applications, new and improved clinical techniques, the physics, engineering and technology of ultrasound in medicine and biology, and the interactions between ultrasound and biological systems, including bioeffects. Papers that simply utilize standard diagnostic ultrasound as a measuring tool will be considered out of scope. Extended critical reviews of subjects of contemporary interest in the field are also published, in addition to occasional editorial articles, clinical and technical notes, book reviews, letters to the editor and a calendar of forthcoming meetings. It is the aim of the journal fully to meet the information and publication requirements of the clinicians, scientists, engineers and other professionals who constitute the biomedical ultrasonic community.