Label Image Ground Truth Data for Lumbar Spine MRI Dataset

This dataset contains the raw label images and ground truth label images of axial view slices of lumbar spine MRI used to train SegNet to detect lumbar spinal stenosis. The four labelled Regions of Interest namely 1) Intervertebral Disc (IVD), 2) Posterior Element (PE), 3) Thecal Sac (TS) and 4) the Area between Anterior and Posterior (AAP) vertebrae elements. The labelling process was carried out by five labellers under supervision of an expert radiologist using the T1-weighted axial-view MRI slice of the last three IVDs. Analysis on the quality of the developed ground truth label images is provided in our paper.

You can download and read the research papers detailing our methodology on boundary delineation for lumbar spinal stenosis detection using the URLs provided in the Related Links at the end of this page. You can also check out other dataset and source code related to this program from that section.

We kindly request you to cite our papers when using our data or program in your research.

本数据集囊括了用于训练 SegNet 检测腰椎狭窄的腰椎MRI轴向切片的原始标签图像及地面真实标签图像。其中标注的四个感兴趣区域分别为：1) 椎间盘（IVD），2) 后部结构（PE），3) 硬脊膜囊（TS）以及4) 前后椎体结构之间的区域。标注过程由五位标注员在资深放射科医生的指导下完成，所使用的是最后三个椎间盘的T1加权轴向MRI切片。关于所开发地面真实标签图像质量的评估详见我们的论文。您可通过页面底部的相关链接下载并阅读详细阐述我们腰椎狭窄边界划分离析方法的研究论文。此外，您还可以在该部分查看与该程序相关的其他数据集和源代码。在使用我们的数据或程序进行您的研究时，我们恳请您引用我们的论文。