人与人工智能的合作用于甲状腺结节的超声波诊断:一项临床试验
Axel Bukhave Edström1, Fatemeh Makouei2,3, Kasper Wennervaldt4
1Department of Otorhinolaryngology, Head and Neck Surgery and Audiology, Rigshospitalet University Hospital of Copenhagen, 2100, Copenhagen, Denmark. axel.bukhave.edstroem.01@regionh.dk.
概括
甲状腺超声波的人工智能 (AI) 并没有提高初学者操作员的诊断准确性. 用户体验显著影响了AI诊断性能,准确度在40-100%之间差异很大.
科学领域:
- 医学成像医学成像
- 医学中的人工智能.
- 甲状腺诊断 甲状腺诊断
背景情况:
- 甲状腺超声波 (US) 对于结节的评估至关重要.
- 基于人工智能的诊断系统旨在提高准确性和一致性.
- 了解用户体验对人工智能性能的影响对于临床集成至关重要.
研究的目的:
- 为了评估人工智能系统 (S-Detect) 对甲状腺美国诊断的影响.
- 评估不同级别的用户体验如何影响S-Detect的诊断准确度.
- 为了确定S-Detect是否能改善临床实践中的诊断工作.
主要方法:
- 一项临床试验涉及20名参与者 (学生,新手和经验丰富的医生).
- 参与者使用S-Detect对五名患有结节的患者进行了甲状腺US.
- 结节的分类遵循了欧洲甲状腺成像报告和数据系统 (EU-TIRADS) 的指导方针,有或没有人工智能辅助.
主要成果:
- 在所有参与者中,S-Detect的平均诊断准确率为71.3%.
- 在用户组之间没有观察到精度的显著差异 (p=0.31).
- 活检推准确率在AI之前为69.8%,在AI后为69.2% (p=0.75).
结论:
- 对于初学者和中级超声波操作员来说,S-Detect并没有改善甲状腺诊断工作.
- 操作员的技能显著影响了人工智能产生的诊断,导致准确度的变化.
- 需要进一步的研究来优化人工智能集成和用户在甲状腺诊断方面的培训.
相关概念视频
The Thyroid Gland
The thyroid gland is a small, butterfly-shaped gland located in the neck and covers the anterior surface of the trachea. The gland has two lateral lobes connected by a thin tissue mass called the isthmus. Internally, each lobe comprises many small spherical structures known as thyroid follicles, surrounded by a network of blood vessels.
The follicles have a central cavity lined by simple cuboidal to squamous epithelial cells called follicular cells. These cells produce the glycoprotein...
The follicles have a central cavity lined by simple cuboidal to squamous epithelial cells called follicular cells. These cells produce the glycoprotein...
Ultrasound II: Endoscopic Ultrasound and FibroScan
Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):
Endoscopic Ultrasound (EUS):


