在肩部MRI中,使用卷积神经网络算法,高精度检测脊上脂肪透
Juan Pablo Saavedra1, Guillermo Droppelmann2,3,4, Nicolás García2
1School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile.
Frontiers in medicine
|June 12, 2023
概括
深度学习模型使用MRI扫描准确诊断上肌肉脂肪透 (SMFI). 卷积神经网络显示出高精度,在这个关键的预后指标上改进了传统方法.
科学领域:
- 放射学 放射学是一门学科.
- 人工智能的人工智能
- 医疗成像医学成像
背景情况:
- 脊上肌肉脂肪透 (SMFI) 是一个关键的MRI发现,用于肩膀预后.
- 古塔利尔分类是诊断SMFI的传统方法.
- 深度学习 (DL) 算法在SMFI检测中提供了更高的诊断准确性的潜力.
研究的目的:
- 开发和训练卷积神经网络 (CNN) 模型用于SMFI的二进制分类.
- 根据Goutallier的分类,使用肩部MRI对SMFI进行分类.
- 评估DL模型的诊断性能,与既有方法相比.
主要方法:
- 对606名被诊断患有SMFI的患者的肩膀MRI进行了回顾性分析.
- 使用T2加权,Y视图MRI,并自动进行上沟细分.
- 在五种不同的二进制SMFI分类方案上训练了VGG-19,ResNet-50和Inception-v3架构.
- 使用十倍交叉验证评估模型性能,报告AU-ROC,灵敏度和特异性.
主要成果:
- 在各种分类方案中,VGG-19模型实现了高性能,AU-ROC值从0.861到0.991.
- 针对VGG-19的特定性能指标包括精度高达0.973,灵敏度高达0.947,特异性高达0.975.
- 该研究证明了DL模型在准确诊断SMFI时的有效性.
结论:
- 从肩部MRI来看,CNN模型对SMFI诊断具有很高的准确性.
- 在提高SMFI的诊断能力方面,DL方法显示出希望.
- 这些发现表明,人工智能在改善肩膀损伤预后方面可能发挥作用.
相关概念视频
Magnetic Resonance Imaging
5.3K
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...
5.3K
Ultrasonography
4.6K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
During an ultrasonography procedure, a handheld device called...
4.6K


