人工智能在甲状腺结节诊断与分类中的应用：最新进展
The Use of Artificial Intelligence in the Diagnosis and Classification of Thyroid Nodules: An Update.
作者信息
Ludwig Maksymilian, Ludwig Bartłomiej, Mikuła Agnieszka, Biernat Szymon, Rudnicki Jerzy, Kaliszewski Krzysztof
机构信息
Department of General, Minimally Invasive and Endocrine Surgery, Wroclaw Medical University, 50-556 Wroclaw, Poland.
出版信息
Cancers (Basel). 2023 Jan 24;15(3):708. doi: 10.3390/cancers15030708.
Abstract
The incidence of thyroid nodules diagnosed is increasing every year, leading to a greater risk of unnecessary procedures being performed or wrong diagnoses being made. In our paper, we present the latest knowledge on the use of artificial intelligence in diagnosing and classifying thyroid nodules. We particularly focus on the usefulness of artificial intelligence in ultrasonography for the diagnosis and characterization of pathology, as these are the two most developed fields. In our search of the latest innovations, we reviewed only the latest publications of specific types published from 2018 to 2022. We analyzed 930 papers in total, from which we selected 33 that were the most relevant to the topic of our work. In conclusion, there is great scope for the use of artificial intelligence in future thyroid nodule classification and diagnosis. In addition to the most typical uses of artificial intelligence in cancer differentiation, we identified several other novel applications of artificial intelligence during our review.
摘要
甲状腺结节的诊断发病率逐年上升，导致进行不必要手术或误诊的风险增加。在我们的论文中，我们介绍了人工智能在甲状腺结节诊断和分类中的最新知识。我们特别关注人工智能在超声检查中对病理诊断和特征描述的作用，因为这是两个发展最为成熟的领域。在寻找最新创新成果时，我们仅回顾了2018年至2022年发表的特定类型的最新出版物。我们总共分析了930篇论文，从中选出了33篇与我们工作主题最相关的论文。总之，人工智能在未来甲状腺结节分类和诊断中的应用前景广阔。除了人工智能在癌症鉴别中的最典型应用外，我们在综述过程中还发现了人工智能的其他一些新应用。
相似文献
1
The Use of Artificial Intelligence in the Diagnosis and Classification of Thyroid Nodules: An Update.人工智能在甲状腺结节诊断与分类中的应用：最新进展
Cancers (Basel). 2023 Jan 24;15(3):708. doi: 10.3390/cancers15030708.
2
Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network.基于 YOLOv2 神经网络的超声影像中甲状腺结节的自动识别与诊断。
World J Surg Oncol. 2019 Jan 8;17(1):12. doi: 10.1186/s12957-019-1558-z.
3
Use of artificial intelligence and machine learning for estimating malignancy risk of thyroid nodules.使用人工智能和机器学习估算甲状腺结节的恶性风险。
Curr Opin Endocrinol Diabetes Obes. 2020 Oct;27(5):345-350. doi: 10.1097/MED.0000000000000557.
4
AIBx, Artificial Intelligence Model to Risk Stratify Thyroid Nodules.AIBx，甲状腺结节风险分层的人工智能模型。
Thyroid. 2020 Jun;30(6):878-884. doi: 10.1089/thy.2019.0752. Epub 2020 Mar 11.
5
A comparison of artificial intelligence versus radiologists in the diagnosis of thyroid nodules using ultrasonography: a systematic review and meta-analysis.超声检查中人工智能与放射科医生对甲状腺结节诊断的比较：一项系统评价与荟萃分析
Eur Arch Otorhinolaryngol. 2022 Nov;279(11):5363-5373. doi: 10.1007/s00405-022-07436-1. Epub 2022 Jun 29.
6
Artificial Intelligence (AI) Tools for Thyroid Nodules on Ultrasound, From the Special Series on AI Applications.超声甲状腺结节的人工智能（AI）工具，选自 AI 应用特辑。
AJR Am J Roentgenol. 2022 Oct;219(4):1-8. doi: 10.2214/AJR.22.27430. Epub 2022 Apr 6.
7
A Comparison of the Performances of Artificial Intelligence System and Radiologists in the Ultrasound Diagnosis of Thyroid Nodules.人工智能系统与放射科医生在甲状腺结节超声诊断中的表现比较。
Curr Med Imaging. 2022;18(13):1369-1377. doi: 10.2174/1573405618666220422132251.
8
Comparison of British Thyroid Association, American College of Radiology TIRADS and Artificial Intelligence TIRADS with histological correlation: diagnostic performance for predicting thyroid malignancy and unnecessary fine needle aspiration rate.与组织学相关性的英国甲状腺协会、美国放射学院 TIRADS 和人工智能 TIRADS 的比较：预测甲状腺恶性肿瘤和不必要的细针抽吸率的诊断性能。
Br J Radiol. 2021 Jul 1;94(1123):20201444. doi: 10.1259/bjr.20201444. Epub 2021 Jun 9.
9
A Computer-Aided Diagnosis System Using Artificial Intelligence for the Diagnosis and Characterization of Thyroid Nodules on Ultrasound: Initial Clinical Assessment.一种使用人工智能的计算机辅助诊断系统，用于超声检查中甲状腺结节的诊断与特征描述：初步临床评估
Thyroid. 2017 Apr;27(4):546-552. doi: 10.1089/thy.2016.0372. Epub 2017 Feb 28.
10
A Comparative Analysis of Two Machine Learning-Based Diagnostic Patterns with Thyroid Imaging Reporting and Data System for Thyroid Nodules: Diagnostic Performance and Unnecessary Biopsy Rate.两种基于机器学习的甲状腺结节影像报告和数据系统诊断模式的对比分析：诊断性能和不必要的活检率。
Thyroid. 2021 Mar;31(3):470-481. doi: 10.1089/thy.2020.0305. Epub 2020 Sep 9.
引用本文的文献
1
Subtypes detection of papillary thyroid cancer from methylation assay via Deep Neural Network.通过深度神经网络从甲基化检测中进行甲状腺乳头状癌亚型检测。
Comput Struct Biotechnol J. 2025 Apr 29;27:1809-1817. doi: 10.1016/j.csbj.2025.04.034. eCollection 2025.
2
Current AI technologies in cancer diagnostics and treatment.癌症诊断与治疗中的当前人工智能技术。
Mol Cancer. 2025 Jun 2;24(1):159. doi: 10.1186/s12943-025-02369-9.
3
Surveying the Digital Cytology Workflow in Italy: An Initial Report on AI Integration Across Key Professional Roles.意大利数字细胞学工作流程调查：关于人工智能在关键专业角色中的整合的初步报告。
Healthcare (Basel). 2025 Apr 14;13(8):903. doi: 10.3390/healthcare13080903.
4
Comparing ChatGPT 4.0's Performance in Interpreting Thyroid Nodule Ultrasound Reports Using ACR-TI-RADS 2017: Analysis Across Different Levels of Ultrasound User Experience.比较ChatGPT 4.0在使用2017版美国放射学会甲状腺影像报告和数据系统（ACR-TI-RADS）解读甲状腺结节超声报告方面的表现：不同超声用户经验水平的分析
Diagnostics (Basel). 2025 Mar 6;15(5):635. doi: 10.3390/diagnostics15050635.
5
Diagnostic value of deep learning of multimodal imaging of thyroid for TI-RADS category 3-5 classification.甲状腺多模态成像深度学习对TI-RADS 3-5类分类的诊断价值
Endocrine. 2025 Mar 8. doi: 10.1007/s12020-025-04198-8.
6
Exploring the role of artificial intelligence in chemotherapy development, cancer diagnosis, and treatment: present achievements and future outlook.探索人工智能在化疗研发、癌症诊断和治疗中的作用：当前成就与未来展望。
Front Oncol. 2025 Feb 4;15:1475893. doi: 10.3389/fonc.2025.1475893. eCollection 2025.
7
Insights in biomarkers complexity and routine clinical practice for the diagnosis of thyroid nodules and cancer.甲状腺结节和癌症诊断中生物标志物复杂性及常规临床实践的见解
PeerJ. 2025 Jan 20;13:e18801. doi: 10.7717/peerj.18801. eCollection 2025.
8
Holomics and Artificial Intelligence-Driven Precision Oncology for Medullary Thyroid Carcinoma: Addressing Challenges of a Rare and Aggressive Disease.全基因组学与人工智能驱动的甲状腺髓样癌精准肿瘤学：应对一种罕见侵袭性疾病的挑战
Cancers (Basel). 2024 Oct 13;16(20):3469. doi: 10.3390/cancers16203469.
9
Progress Achieved, Landmarks, and Future Concerns in Biomedical and Health Informatics.生物医学与健康信息学的进展、里程碑及未来关注点
Healthcare (Basel). 2024 Oct 15;12(20):2041. doi: 10.3390/healthcare12202041.
10
BRAF Detection in FNAC Combined with Semi-Quantitative Tc-MIBI Technique and AI Model, an Economic and Efficient Predicting Tool for Malignancy in Thyroid Nodules.细针穿刺活检联合半定量锝-甲氧基异丁基异腈技术及人工智能模型检测BRAF，一种用于甲状腺结节恶性肿瘤的经济高效预测工具。
Diagnostics (Basel). 2024 Jun 30;14(13):1398. doi: 10.3390/diagnostics14131398.
本文引用的文献
1
Accuracy of Ultrasound Diagnosis of Thyroid Nodules Based on Artificial Intelligence-Assisted Diagnostic Technology: A Systematic Review and Meta-Analysis.基于人工智能辅助诊断技术的甲状腺结节超声诊断准确性：一项系统评价与Meta分析
Int J Endocrinol. 2022 Sep 23;2022:9492056. doi: 10.1155/2022/9492056. eCollection 2022.
2
Update on the Diagnosis and Management of Medullary Thyroid Cancer: What Has Changed in Recent Years?甲状腺髓样癌诊断与管理的最新进展：近年来有哪些变化？
Cancers (Basel). 2022 Jul 27;14(15):3643. doi: 10.3390/cancers14153643.
3
Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing?用于甲状腺结节特征描述的人工智能：我们目前的进展如何？
Cancers (Basel). 2022 Jul 10;14(14):3357. doi: 10.3390/cancers14143357.
4
Deep Learning-Based Recognition of Different Thyroid Cancer Categories Using Whole Frozen-Slide Images.基于深度学习利用全冰冻切片图像识别不同类型甲状腺癌
Front Bioeng Biotechnol. 2022 Jul 6;10:857377. doi: 10.3389/fbioe.2022.857377. eCollection 2022.
5
A comparison of artificial intelligence versus radiologists in the diagnosis of thyroid nodules using ultrasonography: a systematic review and meta-analysis.超声检查中人工智能与放射科医生对甲状腺结节诊断的比较：一项系统评价与荟萃分析
Eur Arch Otorhinolaryngol. 2022 Nov;279(11):5363-5373. doi: 10.1007/s00405-022-07436-1. Epub 2022 Jun 29.
6
A Comparison of the Performances of Artificial Intelligence System and Radiologists in the Ultrasound Diagnosis of Thyroid Nodules.人工智能系统与放射科医生在甲状腺结节超声诊断中的表现比较。
Curr Med Imaging. 2022;18(13):1369-1377. doi: 10.2174/1573405618666220422132251.
7
Intraoperative frozen section performance for thyroid cancer diagnosis.甲状腺癌诊断的术中冰冻切片表现。
Arch Endocrinol Metab. 2022 Mar 8;66(1):50-57. doi: 10.20945/2359-3997000000445.
8
On the Acceptance of "Fake" Histopathology: A Study on Frozen Sections Optimized with Deep Learning.论对“假”组织病理学的接受：一项关于深度学习优化冰冻切片的研究
J Pathol Inform. 2022 Jan 5;13:6. doi: 10.4103/jpi.jpi_53_21. eCollection 2022.
9
External validation of AIBx, an artificial intelligence model for risk stratification, in thyroid nodules.用于甲状腺结节风险分层的人工智能模型AIBx的外部验证
Eur Thyroid J. 2022 Mar 8;11(2):e210129. doi: 10.1530/ETJ-21-0129.
10
Re-Modelling 99m-Technetium Pertechnetate Thyroid Uptake; Statistical, Machine Learning and Deep Learning Approaches.99m-锝高锝酸盐甲状腺摄取的重新建模；统计、机器学习和深度学习方法
J Nucl Med Technol. 2021 Dec 7. doi: 10.2967/jnmt.121.263081.
Zotero 插件