结合超声成像和分子检测的多模态深度学习模型对不确定甲状腺结节的风险分层。

IF 6.7 1区 医学 Q1 ENDOCRINOLOGY & METABOLISM
Thyroid Pub Date : 2025-05-01 Epub Date: 2025-04-21 DOI:10.1089/thy.2024.0584
Shreeram Athreya, Andrew Melehy, Sujit Silas Armstrong Suthahar, Vedrana Ivezić, Ashwath Radhachandran, Vivek R Sant, Chace Moleta, Henry Zheng, Maitraya Patel, Rinat Masamed, Masha Livhits, Michael Yeh, Corey W Arnold, William Speier
{"title":"结合超声成像和分子检测的多模态深度学习模型对不确定甲状腺结节的风险分层。","authors":"Shreeram Athreya, Andrew Melehy, Sujit Silas Armstrong Suthahar, Vedrana Ivezić, Ashwath Radhachandran, Vivek R Sant, Chace Moleta, Henry Zheng, Maitraya Patel, Rinat Masamed, Masha Livhits, Michael Yeh, Corey W Arnold, William Speier","doi":"10.1089/thy.2024.0584","DOIUrl":null,"url":null,"abstract":"<p><p><b><i>Objective:</i></b> Indeterminate cytology (Bethesda III and IV) represents 15-30% of biopsied thyroid nodules and require additional diagnostic testing. Molecular testing (MT) is a commonly used diagnostic tool that evaluatesmalignancy risk through next generation sequencing of fine needle aspiration (FNA) samples. While MT achieves high sensitivity (97-100%) in ruling out malignancy, its specificity and positive predictive value (PPV) remain relatively low. This study proposes a multimodal deep learning model that integrates ultrasound (US) imaging with MT to improve risk stratification by enhancing PPV while maintaining high sensitivity. Combining these modalities leverages complementary information from both molecular and imaging data, addressing limitations in current approaches and offering a robust framework for evaluating indeterminate nodules. <b><i>Methods:</i></b> We retrospectively analyzed 333 patients with indeterminate thyroid nodules (259 benign, 74 malignant) at UCLA Medical Center between 2016 and 2022. We evaluated four configurations: whole frame US images, 256 × 256 patches, 128 × 128 patches, and an ensemble model combining the first three configurations. The clinical baseline consisted of Bethesda cytology and MT results. Models were assessed using five fold cross validation stratified by surgical outcomes. <b><i>Results:</i></b> The clinical baseline (Bethesda + MT) achieved an AUROC of 0.728 [0.68, 0.78] with sensitivity of 0.946 [0.88, 1.00], specificity of 0.664 [0.60, 0.73], and PPV of 0.448 [0.41, 0.48]. The proposed ensemble model demonstrated improved performance, achieving an AUROC of 0.831 [0.77, 0.89] with a sensitivity of 0.946 [0.88, 1.00], specificity of 0.703 [0.66, 0.75], and PPV of 0.477 [0.46, 0.50]. These improvements were statistically significant (<i>p</i> = 0.0008). <b><i>Conclusion:</i></b> Our multimodal model enhances MT performance by providing statistically significant improvements in PPV and specificity while maintaining high sensitivity. Our framework could be leveraged to reduce the number of benign thyroid resections in patients with indeterminate nodules. However, this study is limited by its single center dataset, lack of external validation, and the use of binarized MT outputs rather than granular malignancy risk probabilities. Future work should validate these findings across diverse populations and larger external datasets for more comprehensive risk stratification.</p>","PeriodicalId":23016,"journal":{"name":"Thyroid","volume":" ","pages":"590-594"},"PeriodicalIF":6.7000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Combining Ultrasound Imaging and Molecular Testing in a Multimodal Deep Learning Model for Risk Stratification of Indeterminate Thyroid Nodules.\",\"authors\":\"Shreeram Athreya, Andrew Melehy, Sujit Silas Armstrong Suthahar, Vedrana Ivezić, Ashwath Radhachandran, Vivek R Sant, Chace Moleta, Henry Zheng, Maitraya Patel, Rinat Masamed, Masha Livhits, Michael Yeh, Corey W Arnold, William Speier\",\"doi\":\"10.1089/thy.2024.0584\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b><i>Objective:</i></b> Indeterminate cytology (Bethesda III and IV) represents 15-30% of biopsied thyroid nodules and require additional diagnostic testing. Molecular testing (MT) is a commonly used diagnostic tool that evaluatesmalignancy risk through next generation sequencing of fine needle aspiration (FNA) samples. While MT achieves high sensitivity (97-100%) in ruling out malignancy, its specificity and positive predictive value (PPV) remain relatively low. This study proposes a multimodal deep learning model that integrates ultrasound (US) imaging with MT to improve risk stratification by enhancing PPV while maintaining high sensitivity. Combining these modalities leverages complementary information from both molecular and imaging data, addressing limitations in current approaches and offering a robust framework for evaluating indeterminate nodules. <b><i>Methods:</i></b> We retrospectively analyzed 333 patients with indeterminate thyroid nodules (259 benign, 74 malignant) at UCLA Medical Center between 2016 and 2022. We evaluated four configurations: whole frame US images, 256 × 256 patches, 128 × 128 patches, and an ensemble model combining the first three configurations. The clinical baseline consisted of Bethesda cytology and MT results. Models were assessed using five fold cross validation stratified by surgical outcomes. <b><i>Results:</i></b> The clinical baseline (Bethesda + MT) achieved an AUROC of 0.728 [0.68, 0.78] with sensitivity of 0.946 [0.88, 1.00], specificity of 0.664 [0.60, 0.73], and PPV of 0.448 [0.41, 0.48]. The proposed ensemble model demonstrated improved performance, achieving an AUROC of 0.831 [0.77, 0.89] with a sensitivity of 0.946 [0.88, 1.00], specificity of 0.703 [0.66, 0.75], and PPV of 0.477 [0.46, 0.50]. These improvements were statistically significant (<i>p</i> = 0.0008). <b><i>Conclusion:</i></b> Our multimodal model enhances MT performance by providing statistically significant improvements in PPV and specificity while maintaining high sensitivity. Our framework could be leveraged to reduce the number of benign thyroid resections in patients with indeterminate nodules. However, this study is limited by its single center dataset, lack of external validation, and the use of binarized MT outputs rather than granular malignancy risk probabilities. Future work should validate these findings across diverse populations and larger external datasets for more comprehensive risk stratification.</p>\",\"PeriodicalId\":23016,\"journal\":{\"name\":\"Thyroid\",\"volume\":\" \",\"pages\":\"590-594\"},\"PeriodicalIF\":6.7000,\"publicationDate\":\"2025-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Thyroid\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1089/thy.2024.0584\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/4/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thyroid","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1089/thy.2024.0584","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/4/21 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

摘要

目的:不确定的细胞学(Bethesda III和IV)占活检甲状腺结节的15-30%,需要额外的诊断检查。分子检测(MT)是一种常用的诊断工具,通过下一代细针穿刺(FNA)样本测序来评估恶性肿瘤风险。虽然MT在排除恶性肿瘤方面具有很高的敏感性(97-100%),但其特异性和阳性预测值(PPV)仍然相对较低。本研究提出了一种多模态深度学习模型,该模型将超声(US)成像与MT相结合,通过增强PPV来改善风险分层,同时保持高灵敏度。结合这些模式,利用来自分子和影像学数据的互补信息,解决当前方法的局限性,并为评估不确定结节提供一个强大的框架。方法:我们回顾性分析2016年至2022年在加州大学洛杉矶分校医学中心就诊的333例不确定甲状腺结节患者(259例良性,74例恶性)。我们评估了四种配置:全帧美国图像,256 × 256补丁,128 × 128补丁,以及结合前三种配置的集成模型。临床基线包括Bethesda细胞学和MT结果。采用五重交叉验证对模型进行评估,并按手术结果分层。结果:临床基线(Bethesda + MT) AUROC为0.728[0.68,0.78],敏感性为0.946[0.88,1.00],特异性为0.664 [0.60,0.73],PPV为0.448[0.41,0.48]。所提出的集成模型表现出更好的性能,AUROC为0.831[0.77,0.89],灵敏度为0.946[0.88,1.00],特异性为0.703 [0.66,0.75],PPV为0.477[0.46,0.50]。这些改善具有统计学意义(p = 0.0008)。结论:我们的多模态模型在保持高灵敏度的同时,提供了统计学上显著的PPV和特异性改善,从而提高了MT的性能。我们的框架可用于减少不确定结节患者良性甲状腺切除术的数量。然而,该研究受到其单中心数据集,缺乏外部验证以及使用二值化MT输出而不是颗粒恶性肿瘤风险概率的限制。未来的工作应该在不同的人群和更大的外部数据集上验证这些发现,以进行更全面的风险分层。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Combining Ultrasound Imaging and Molecular Testing in a Multimodal Deep Learning Model for Risk Stratification of Indeterminate Thyroid Nodules.

Objective: Indeterminate cytology (Bethesda III and IV) represents 15-30% of biopsied thyroid nodules and require additional diagnostic testing. Molecular testing (MT) is a commonly used diagnostic tool that evaluatesmalignancy risk through next generation sequencing of fine needle aspiration (FNA) samples. While MT achieves high sensitivity (97-100%) in ruling out malignancy, its specificity and positive predictive value (PPV) remain relatively low. This study proposes a multimodal deep learning model that integrates ultrasound (US) imaging with MT to improve risk stratification by enhancing PPV while maintaining high sensitivity. Combining these modalities leverages complementary information from both molecular and imaging data, addressing limitations in current approaches and offering a robust framework for evaluating indeterminate nodules. Methods: We retrospectively analyzed 333 patients with indeterminate thyroid nodules (259 benign, 74 malignant) at UCLA Medical Center between 2016 and 2022. We evaluated four configurations: whole frame US images, 256 × 256 patches, 128 × 128 patches, and an ensemble model combining the first three configurations. The clinical baseline consisted of Bethesda cytology and MT results. Models were assessed using five fold cross validation stratified by surgical outcomes. Results: The clinical baseline (Bethesda + MT) achieved an AUROC of 0.728 [0.68, 0.78] with sensitivity of 0.946 [0.88, 1.00], specificity of 0.664 [0.60, 0.73], and PPV of 0.448 [0.41, 0.48]. The proposed ensemble model demonstrated improved performance, achieving an AUROC of 0.831 [0.77, 0.89] with a sensitivity of 0.946 [0.88, 1.00], specificity of 0.703 [0.66, 0.75], and PPV of 0.477 [0.46, 0.50]. These improvements were statistically significant (p = 0.0008). Conclusion: Our multimodal model enhances MT performance by providing statistically significant improvements in PPV and specificity while maintaining high sensitivity. Our framework could be leveraged to reduce the number of benign thyroid resections in patients with indeterminate nodules. However, this study is limited by its single center dataset, lack of external validation, and the use of binarized MT outputs rather than granular malignancy risk probabilities. Future work should validate these findings across diverse populations and larger external datasets for more comprehensive risk stratification.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Thyroid
Thyroid 医学-内分泌学与代谢
CiteScore
12.30
自引率
6.10%
发文量
195
审稿时长
6 months
期刊介绍: This authoritative journal program, including the monthly flagship journal Thyroid, Clinical Thyroidology® (monthly), and VideoEndocrinology™ (quarterly), delivers in-depth coverage on topics from clinical application and primary care, to the latest advances in diagnostic imaging and surgical techniques and technologies, designed to optimize patient care and outcomes. Thyroid is the leading, peer-reviewed resource for original articles, patient-focused reports, and translational research on thyroid cancer and all thyroid related diseases. The Journal delivers the latest findings on topics from primary care to clinical application, and is the exclusive source for the authoritative and updated American Thyroid Association (ATA) Guidelines for Managing Thyroid Disease.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信