ADNI挑选有意义的数据进⾏下载【2】
ADNI数据集本⾝提供处理过的图⽚
有⼀篇论⽂“Non-White Matter Tissue Extraction and Deep Convolutional Neural Network for Alzheimer’s Dia Detection ”中涉及到的预处理的数据如下：
“We u the FDG-PET and MRI data downloaded from ADNI1 datat with each pair of FDG-PET and MRI for same subject and captured at the same time. The MRI and PET images have undergone veral preprocesd steps of rearch groups belonged to the ADNI.”
酸奶的保质期In detail, the MRI images are pre-procesd by steps: gradwarp, B1 non-uniformity and N3. Gradwarp means correction of image geometry distortion due to gradient model, B1 non-uniformity is a correction procedure that us B1 calibration scans to correct image intensity nonuniformity. Finally, a N3 histogram peak sharpening algorithm was applied to reduce intensity non-uniformity of images. （其中，对MRI图像进⾏预处理的步骤有：梯度偏差、B1⾮均匀性和N3。梯度偏差是指梯度模型引起的图像⼏何畸变的校正，B1⾮均匀性是利⽤B1校正扫描对图像强度⾮均匀性进⾏校正的⼀种校正⽅法。最后，采⽤N3直⽅图峰值锐化算法来降低图像的强度不均匀性）
花朵贺卡For the FDG-PET images, a procedure involving dynamic co-registering frames and acquiring averaging from baline PET scan was conducted. PET images were reoriented as AC-PC correction into a standard 160x160x96 voxel image grid, having 1.5mm cubic voxels. The images underwent continued filtering with a scanner-specific filter function to procedure images of a uniform isotropic resolution of 8mm Full Width at Half Maximum (FWHM). （对FDG-PET图像，采⽤动态共配帧和基线PET扫描平均的⽅法。将PET图像重新定向为AC-PC校正，得到标准的160x160x96体素图像⽹格，体素为1.5mm⽴⽅。这些图像在半最⼤值(FWHM)条件下，通过⼀个特定于扫描器的滤波功能，对均匀各向同性分辨率为8mm的全宽图像进⾏连续滤波。）
那么如何针对论⽂中提到的数据进⾏搜索呢？下⾯介绍⼀⼆：
可乐鸡翅放盐吗
我们⾸先搜索AD类的数据，且同时搜索MRI和PET模态的数据，请见上图。单击搜索（SEARCH）后如下图所⽰。
公子哥儿>野生黄鳝可以发现，受试者002_S_0619的图⽚都是MRI模态的，没有PET模态的，所以放弃这是受试者，通过滚动条，继续查找下⼀个受试者，因为我们的⽬的是寻找同⼀年内既有MRI图像⼜有PET图像的受试者，最终把这两种模态的图⽚进⾏配准等多模态分析，可以详见论⽂。接下来继续：
这⾥84.6和84.7岁视为85岁，且存在满⾜条件的图像，所以，就勾选上，然后单击Add to Collection按钮。然后，出现：李光耀
我们可以新建⼀个名字tt5，这时就会收集到tt5这⾥了，见下图
栗栗危惧
护士加
医学影像中⽤的nii和img⽂件类型⽐较多，⼤家可以都试着下载⼀下，看看哪个⽂件类型⽐较⼤。然后看⼀下下载的⽂件命名⾥⾯有⽇期，和上图中的获取⽇期（Acq Date）是否⼀致（肯定不⼀致的）。留下的任务，认真完成啊，然后给我留⾔。若是留⾔⼈数多，我会给⼤家介绍如何在Python读取和处理这些医学影像的
。
