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.