RSNA 2023腹部创伤人工智能挑战:审查和结果
Sebastiaan Hermans1, Zixuan Hu1, Robyn L Ball1
1From the Department of Medical Imaging, St Michael's Hospital, Unity Health Toronto, 30 Bond St, Toronto, ON, Canada M5B 1W8 (S.H., Z.H., H.M.L., I.Y., E.C.); Edward S. Rogers Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada (Z.H., E.S.); The Jackson Laboratory, Bar Harbor, Me (R.L.B.); Department of Radiology, The Ohio State University, Columbus, Ohio (L.M.P.); Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada (F.H.B.); Department of Radiology, Scripps Clinic Medical Group and University of California San Diego, San Diego, Calif (J.D.R.); Radiological Society of North America, Oak Brook, Ill (M.V.); Department of Radiology, Thomas Jefferson University, Philadelphia, Pa (A.E.F.); Department of Radiology, Weill Cornell Medicine, New York, NY (G.S.); Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, Calif (J.M.), Department of Radiology, Vancouver General Hospital, Vancouver, Canada (S.N.); Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (B.S.M.); Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Conn (M.A.D.); Duke University School of Medicine, Durham, NC (K.M.); North York General Hospital, Toronto, Ontario, Canada (E.S.); and Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada (E.C.).
机器学习模型在CT扫描上擅长检测腹部创伤,特别是高度损伤. 这些人工智能模型对未来的研究在诊断创伤损伤方面有希望.
科学领域:
- 放射学和医学成像学 医学成像学
- 人工智能在医学中的应用
- 创伤外科 手术 创伤外科
背景情况:
- 检测腹部创伤对于患者的治疗结果至关重要.
- 机器学习 (ML) 提供了提高诊断准确性的潜力.
- 2023年RSNA AI挑战赛的重点是使用CT扫描检测腹部创伤.
研究的目的:
- 评估2023年RSNA腹部创伤检测AI挑战赛中表现最佳的ML模型的性能.
- 评估模型在CT扫描上检测各种类型的腹部损伤的能力.
主要方法:
- 八个获奖的ML模型的回顾性评估.
- 利用了4274张腹部创伤CT扫描的多中心数据集.
- 模型被评估用于检测固体器官损伤 (肝脏,脏,脏),肠/介质损伤和使用AUC指标的活跃外流.
主要成果:
- 模型在检测固体器官损伤方面表现出很高的性能,平均AUC从0.91到0.94.4不等.
- 在高度固体器官损伤方面,注意到了特殊的表现,平均AUC达到0.98.98.
- 肠/介质损伤和活跃扩张的平均AUC为0.85.
结论:
- 获奖的ML模型在CT扫描上显示出强大的能力来识别创伤性腹部损伤.
- 高度伤害被检测到特别高的准确性.
- 这些模型为未来的AI开发在腹部创伤诊断中建立了性能基线.


