For each patient, the HN dataset provides CT and PET scans and Gross Tumor V olume (GTV) mask, preprocessed according to the pipeline in Fig. 1. Several clinical variables are included, in particular the Locoregional Recurrence (LR) within the follow-up period (median: 43 months; range: 6-112 months), and T-stage at diagnosis. Data are gathered from four different hospitals, each one representing a single cohort. No- tably, each hospital has its own image acquisition equipment and acquisition settings, which is a cause of heterogeneity in image characteristics, in particular resolution of the PET images. Moreover, The HN dataset is highly unbalanced for the LR prognosis, with 15.8% of recurrence (Table I). 解释
时间: 2024-04-26 21:25:42 浏览: 13
这段话是在描述Head-Neck-PET-CT(HN)数据集1中提供的数据。对于每个患者,该数据集提供了经过预处理的CT和PET扫描以及Gross Tumor Volume(GTV)掩模,预处理的管线如图1所示。数据集中还包括几个临床变量,特别是随访期内(中位数为43个月,范围为6-112个月)的局部复发(LR)和诊断时的T分期。数据收集自四个不同的医院,每个医院代表一个单独的队列。值得注意的是,每个医院都有自己的图像采集设备和采集设置,这是图像特征异质性的原因,特别是PET图像的分辨率。此外,HN数据集在LR预后方面高度不平衡,复发率为15.8%(表I)。
相关问题
冒号后面的那句话是什么意思:Combines a dataset and a sampler, and provides an iterable over the given dataset.
这句话的意思是:`Combines a dataset and a sampler, and provides an iterable over the given dataset.` 组合一个数据集和一个采样器,并提供一个可迭代对象,用于遍历给定的数据集。也就是说,`DataLoader` 是 PyTorch 中一个用于加载数据的工具,它可以将数据集和采样器组合在一起,提供一个可迭代对象,方便我们在训练神经网络时批量地读取数据。
The last module in the image preprocessing pipeline extracts a subvolume of the image which contains the GTV . This reduction enables to compute the radiomics features only from the voxels, also reducing the size of the 3D image portion to analyze with DL on the Graphical Processing Unit (GPU) memory. The drawback of this operation is the loss of contextual information near the GTW, thus the normalized size of the subvolume was set to 128 mm3, a reasonable trade-off between the size of the GTVs in the dataset and the amount of context included. The volume of interest was centered in the center of mass of the GTV , also used to center the subvolumes of the CT, PET and GTV mask images. 解释
这段话主要是在介绍医学图像处理中的一个模块,该模块用于提取包含肿瘤区域(GTV)的子体积,并减小图像的尺寸以便能够在显卡内存上进行深度学习分析。这种操作的缺点是在GTV附近会失去一些上下文信息,因此子体积的标准尺寸被设置为128 mm3,这是在GTV数据集的大小和包含的上下文之间做出的一个合理折中。值得一提的是,该子体积是以GTV的重心为中心进行裁剪的,同时也用于对CT、PET和GTV遮罩图像的子体积进行中心对齐。