TY -非盟的锅,琼盟——张凯盟——他,林盟——咚,周盟——张,Lei盟——吴,小杭盟——吴,易盟——高,宿州农村PY - 2021 DA - 2021/5/21 TI -自动诊断突出的隆起和磁盘与腰椎磁共振图像通过使用深卷积神经网络:方法开发研究乔-地中海JMIR通知SP - e14755六世- 9 - 5 KW -深度学习KW -对象定位KW -磁盘形成疝KW -磁盘隆起KW -图像分类AB -背景:椎间盘突出和椎间盘突出是腰椎间盘(IVDs)两种常见疾病，常导致麻木、下肢疼痛和腰痛。磁共振成像是诊断腰椎疾病最有效的技术之一，已广泛应用于医院的临床诊断。然而，缺乏有效的工具来解释大量的MR图像，以满足许多放射科医生的要求。目的:本研究的目的是提出一个自动诊断椎间盘突出和突出的系统，可以节省时间，有效地减少放射科医生的工作量。方法:腰椎疾患的诊断高度依赖医学影像。因此，我们选择了两种最常见的疾病——椎间盘突出和椎间盘突出作为研究对象。本研究主要通过分析矢状面与轴向面图像的几何关系，并通过深度卷积神经网络对轴向腰椎间盘MR图像进行分类，识别ivd(腰椎[L] 1至L2、L2- l3、L3-L4、L4-L5、L5至骶椎[S] 1)的位置。结果:该系统包括4个步骤。第一步，使用更快的基于区域的卷积神经网络自动定位矢状图像中的椎体(包括L1、L2、L3、L4、L5和S1)，我们的四倍交叉验证显示准确率为100%。 In the second step, it spontaneously identified the corresponding disk in each axial lumbar disk MR image with 100% accuracy. In the third step, the accuracy for automatically locating the intervertebral disk region of interest in axial MR images was 100%. In the fourth step, the 3-class classification (normal disk, disk bulge, and disk herniation) accuracies for the L1-L2, L2-L3, L3-L4, L4-L5, and L5-S1 IVDs were 92.7%, 84.4%, 92.1%, 90.4%, and 84.2%, respectively. Conclusions: The automatic diagnosis system was successfully built, and it could classify images of normal disks, disk bulge, and disk herniation. This system provided a web-based test for interpreting lumbar disk MR images that could significantly improve diagnostic efficiency and standardized diagnosis reports. This system can also be used to detect other lumbar abnormalities and cervical spondylosis. SN - 2291-9694 UR - https://medinform.www.mybigtv.com/2021/5/e14755 UR - https://doi.org/10.2196/14755 UR - http://www.ncbi.nlm.nih.gov/pubmed/34018488 DO - 10.2196/14755 ID - info:doi/10.2196/14755 ER -