卵巢尾报告和数据系统MRI评分:诊断准确性,观察者之间的协议,以及对机器学习的适用性
Hüseyin Akkaya1, Emin Demirel2, Okan Dilek3
1Department of Radiology, Faculty of Medicine, Ondokuz Mayis University, 55280 Samsun, Turkey.
The British journal of radiology
|October 29, 2024
概括
卵巢-尾报告和数据系统磁共振成像 (O-RADS MRI) 显示了对恶性瘤风险的中等协议. 机器学习,特别是人工神经网络,可以显著提高O-RADSMRI分类准确性.
科学领域:
- 放射学 放射学是指放射学
- 在瘤学瘤学.
- 人工智能的人工智能
背景情况:
- 卵巢-附体报告和数据系统磁共振成像 (O-RADS MRI) 对于标准化对附体病变的评估至关重要.
- 评估观察者之间的一致性和诊断准确性对于完善O-RADSMRI协议至关重要.
- 机器学习 (ML) 在提高诊断性能方面的潜力值得研究.
研究的目的:
- 评估O-RADSMRI的观察者间一致性和诊断准确性.
- 评估机器学习模型对O-RADSMRI数据的适用性.
- 将ML模型的性能与放射科医生评估进行比较.
主要方法:
- 通过使用动态对比增强的盆腔MRI对471个附病变进行了回顾性分析.
- 3名放射科医生根据O-RADSMRI标准对病变进行评估.
- 放射性特征的提取和ML模型的构建 (ANN,SVM,随机森林,天真贝叶斯).
主要成果:
- 对O-RADS 4 (kappa:0.669) 和O-RADS 5 (kappa:0.709) 类别来说,观察者间的共识是最低的.
- 在O-RADS MRI中,预测恶性瘤的AUC为O-RADS 4的74.3%,O-RADS 5的95.5%.
- 人工神经网络 (ANN) 模型获得了最高的性能,在区分O-RADS组时AUC为0.948.
结论:
- 对O-RADS 4-5的O-RADSMRI的观察者间协议和诊断灵敏度需要改进.
- 机器学习模型,特别是ANN,在分类O-RADSMRI类别方面表现出高准确性.
- 将人工智能集成到MRI协议中,有望提高附损伤评估中的诊断性能.
相关概念视频
Magnetic Resonance Imaging
5.0K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.0K
Imaging Studies for Cardiovascular System IV: CMRI
7
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...
7


