Lung cancer subclassification using fastai
Fastai API info: https://arxiv.org/pdf/2002.04688.pdf
Direct link to the colab notebook:
https://github.com/bnsreenu/python_for_microscopists/blob/master/Tips_tricks_22_fastai_lung_cancer_classification.ipynb
Data set information:
https://github.com/tampapath/lung_colon_image_set/
https://arxiv.org/ftp/arxiv/papers/1912/1912.12142.pdf
LC25000 Lung and colon histopathological image dataset from: https://academictorrents.com/details/7a638ed187a6180fd6e464b3666a6ea0499af4af
The dataset contains color 25,000 images with 5 classes of 5,000 images each. All images are 768 x 768 pixels in size and are in jpeg file format. Our dataset can be downloaded as a 1.85 GB zip file LC25000.zip. After unzipping, the main folder lung_colon_image_set contains two subfolders: colon_image_sets and lung_image_sets.
The subfolder lung_image_sets contains three secondary subfolders: lung_aca subfolder with 5000 images of lung adenocarcinomas, lung_scc subfolder with 5000 images of lung squamous cell carcinomas, and lung_n subfolder with 5000 images of benign lung tissues.