| 摘要: |
| 目的 应用2.0版人工智能（AI）自动检测系统AI-SONICTM Thyroid对甲状腺结节进行术前超声评估，并与不同年资超声医师应用常规超声检查主观诊断结论进行比较，探讨2.0版AI自动检测系统在甲状腺结节良恶性鉴别诊断中的应用价值。方法 选择2019年8月至2020年1月于我院普通外科接受手术治疗的247例甲状腺结节患者（325枚甲状腺结节）。所有患者术前均由1名有13年甲状腺超声诊断工作经验的高级职称超声医师和1名有4年工作经验的初级职称超声医师分别进行常规超声检查，同时由另1名有20年工作经验的超声医师在不知前2名医师判读结果的条件下利用2.0版AI自动检测系统进行超声检查。采用Kappa检验评价不同年资医师常规超声检查及2.0版AI自动检测系统的诊断结果与术后病理结果的一致性。结果 术后病理确诊恶性结节229枚，良性结节96枚。低年资医师应用常规超声检查诊断甲状腺结节良恶性的灵敏度、特异度、准确度分别为85.15%（195/229）、66.67%（64/96）、79.69%（259/325），高年资超声医师应用常规超声检查诊断甲状腺结节良恶性的灵敏度、特异度、准确度分别为93.45%（214/229）、79.17%（76/96）、89.23%（290/325），2.0版AI自动检测系统诊断甲状腺结节良恶性的灵敏度、特异度、准确度分别为92.58%（212/229）、71.88%（69/96)、86.46%（281/325）。Kappa一致性检验结果显示，高年资医师应用常规超声检查与病理诊断结果一致性较高（Kappa值为0.78，P<0.01），低年资医师应用常规超声检查、2.0版AI自动检测系统与病理诊断结果一致性一般（Kappa值为0.55、0.74，P均<0.01）。结论 2.0版AI自动检测系统AI-SONICTM Thyroid诊断甲状腺结节良恶性的灵敏度、准确度、特异度与高年资医师应用常规超声的检查结果相近，有望成为术前评估甲状腺结节良恶性的可靠辅助手段。 |
| 关键词: 人工智能 高频超声 甲状腺结节 甲状腺影像报告和数据系统 |
| DOI：10.16781/j.0258-879x.2020.10.1077 |
| 投稿时间：2020-03-04修订日期：2020-05-19 |
| 基金项目:国家自然科学基金（81501492）． |
|
| Efficacy of preoperative ultrasound evaluation of thyroid nodules by artificial intelligence automatic detection system version 2.0: a preliminary study |
| GUO Fang-qi1,ZHAO Jia-qi1*,CHEN Rui1,LIU Sheng2 |
(1. Department of Ultrasound, Changzheng Hospital, Naval Medical University(Second Military Medical University), Shanghai 200003, China;
2. Department of General Surgery(Ⅲ), Changzheng Hospital, Naval Medical University(Second Military Medical University), Shanghai 200003, China
*Corresponding author) |
| Abstract: |
| Objective To investigate the efficacy of AI-SONICTM Thyroid system, a version 2.0 artificial intelligence (AI) automatic detection system, in the preoperative ultrasound diagnosis of thyroid nodules, and to evaluate the application value of AI automatic detection system version 2.0 in the differential diagnosis of benign and malignant thyroid nodules by comparing with the subjective diagnosis conclusions of sonographers with different seniorities. Methods A total of 247 patients (325 thyroid nodules) admitted to the Department of General Surgery in our hospital from Aug. 2019 to Jan. 2020 were selected for this study. All patients underwent routine ultrasound examinations by a senior sonographer with 13 years of experience in thyroid ultrasound diagnosis and a junior sonographer with 4 years of work experience. At the same time, the patients were also examined by another sonographer with 20 years of work experience using AI automatic detection system version 2.0, without knowing the diagnosis conclusions of the above two sonographers. Kappa test was used to evaluate the consistency of the results of routine ultrasound examination of sonographers with different seniorities and AI automatic detection system version 2.0 and the postoperative pathological results. Results The postoperative pathology confirmed 229 malignant nodules and 96 benign nodules. The sensitivity, specificity and accuracy in the diagnosis of benign and malignant thyroid nodules were 85.15% (195/229), 66.67% (64/96) and 79.69% (259/325), 93.45% (214/229), 79.17% (76/96) and 89.23% (290/325), and 92.58% (212/229), 71.88% (69/96) and 86.46% (281/325) for junior sonographer, senior sonographer and AI automatic detection system version 2.0, respectively. The Kappa consistency test results showed that the diagnosis result of senior sonographer was highly consistent with the pathological diagnosis result (Kappa value 0.78, P<0.01), while the diagnosis results of junior sonographer and AI automatic detection system version 2.0 were generally consistent with the pathological diagnosis result (Kappa values 0.55 and 0.74, both P<0.01). Conclusion The sensitivity, accuracy and specificity of the AI automatic detection system version 2.0 AI-SONICTM Thyroid in diagnosing benign and malignant thyroid nodules are similar to those of routine ultrasound examination by senior sonographers, and the system might be a reliable auxiliary means for preoperative evaluation of benign and malignant thyroid nodules. |
| Key words: artificial intelligence high-frequency ultrasound thyroid nodules thyroid imaging reporting and data system |
