Application of Fractal Radiomics and Machine Learning for Differentiation of Non-Small Cell Lung Cancer Subtypes on PET/MR Images

The dataset contains 274 magnetic resonance (MR) images with masks of non-small cell lung cancer: adenocarcinoma (ADC) and squamous cell carcinoma (SCC). Radiomics features of the ROIs' images are included. Directory structure:* mask/ - numpy arrays corresponding to the irregular mask of the MRI images +arrays are named: m_<number_image>_<slice_of_image>_ROI.tif * oryg/ - numpy arrays corresponding to original MRI images +arrays are named: o_<number_image>_<slice_of_image>.bmp * MRI_slice_load.py code for data loading and calculating features* Database.xlsx - a .xlsx file with three columns ['NameImage', 'NameMask', 'Group'] corresponding to MRI images, mask images, and group annotations (adenocarcinoma (ADC) and squamous cell carcinoma (SCC))* database_features.xlsx - a .xlsx file with nine sheets of calculated features of every ROI image.本数据集包含274幅带不规则掩码的非小细胞肺癌磁共振成像（Magnetic Resonance, MR）图像，涵盖腺癌（adenocarcinoma, ADC）与鳞状细胞癌（squamous cell carcinoma, SCC）两类病灶，并包含各感兴趣区域（Region of Interest, ROI）图像的放射组学特征。 数据集目录结构如下： - `mask/`：存储对应磁共振图像不规则掩码的numpy数组，文件命名格式为`m_<图像编号>_<图像切片编号>_ROI.tif` - `oryg/`：存储对应原始磁共振图像的numpy数组，文件命名格式为`o_<图像编号>_<图像切片编号>.bmp` - `MRI_slice_load.py`：用于数据加载与特征计算的代码文件 - `Database.xlsx`：包含三列的Excel文件，列名分别为`NameImage`、`NameMask`、`Group`，分别对应磁共振图像文件、掩码图像文件与分组标注信息（腺癌ADC与鳞状细胞癌SCC） - `database_features.xlsx`：包含九个工作表的Excel文件，存储每个感兴趣区域图像的计算得到的放射组学特征。