Lung Phantom

肺幻影数据集是一个肺部病变数据集，它基于美国食品和药物管理局制作的胸部模型，以及12个不同大小的病变阴影 (有效直径10和20毫米)，形状 (球形，椭圆形，浅裂，等) 形状和毛刺形状) 和密度 (-630、-10和100 HU)，并用哥伦比亚大学医学中心扫描仪扫描和记录。其中，CT的扫描参数为120 kVp，100 mAs，准直64*0.625，间距1.375毫米，1.25毫米厚片作为肺核重建图像。
肺幻影数据集由癌症影像档案TCIA 2015年发布，相关论文包括《来自Lung_Phantom的数据: 癌症影像档案》。

The Lung Phantom Dataset is a pulmonary lesion dataset based on the thoracic phantom manufactured by the US Food and Drug Administration (FDA). It includes 12 sets of lesion shadows with varying effective diameters (10 mm and 20 mm), shapes (spherical, elliptical, lobulated, spiculated, etc.) and densities (-630, -10 and 100 Hounsfield Units (HU)). The dataset was scanned and recorded using a scanner from Columbia University Medical Center. The CT scanning parameters were set as 120 kVp, 100 mAs, collimation of 64*0.625, slice spacing of 1.375 mm, and 1.25 mm slice thickness reconstructed with lung kernel.
The Lung Phantom Dataset was released by The Cancer Imaging Archive (TCIA) in 2015. Its associated publications include "Data from Lung_Phantom: The Cancer Imaging Archive".

搜集汇总

背景与挑战

背景概述

Lung Phantom是一个肺部病变CT影像数据集，包含12种不同大小、形状和密度的病变阴影，由TCIA于2015年发布。数据集基于FDA胸部模型，扫描参数详细，适用于医学影像研究。