深度学习模型用于基于磁共振血管造影的莫亚莫亚疾病自动诊断
Mingming Lu1,2, Yijia Zheng3,4, Shitong Liu2
1Department of Radiology, Pingjin Hospital, Characteristic Medical Center of Chinese People's Armed Police Force, Tianjin, China.
EClinicalMedicine
|November 19, 2024
概括
深度学习模型DenseNet-121使用MRA图像准确识别莫亚莫亚病 (MMD). 这种自动化方法显示了与人类放射科医生可比的诊断能力,可能有助于临床工作流程.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 神经学 神经学
背景情况:
- 莫亚莫亚病 (MMD) 的诊断可能具有挑战性.
- 磁共振血管造影 (MRA) 是MMD的关键成像方式.
- 需要自动诊断工具来协助临床医生.
研究的目的:
- 评估基于深度学习的卷积神经网络 (CNN) 的有效性,用于自动识别MMD.
- 将CNN模型的诊断性能与经验丰富的放射科医生进行比较.
主要方法:
- 这是一项追溯性研究,涉及660名参与者 (MMD,动脉样硬化疾病,正常对照).
- 使用MRA图像进行3D CNN模型 (DenseNet-121) 的开发和验证.
- 使用AUC和精度进行性能评估;通过Grad-CAM可视化.
主要成果:
- 在DenseNet-121中,宏观平均AUC为0.977 (内部) 和0.880 (外部).
- 该模型在向性MMD检测中表现出高精度 (0.967).
- 格拉德-CAM可视化显示了类似于人类专家的决策.
结论:
- CNN模型,特别是DenseNet-121是MRA自动诊断MMD的有效方法.
- 这项技术可以减少放射科医生的工作量,并融入临床实践.
更多相关视频
05:23Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders
Published on: May 31, 2024
492
12:24Noninvasive Assessment of Cardiac Abnormalities in Experimental Autoimmune Myocarditis by Magnetic Resonance Microscopy Imaging in the Mouse
Published on: June 20, 2014
9.9K
相关概念视频
01:21Imaging 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
01:24Magnetic Resonance Imaging
4.9K
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...
4.9K