BWSI Medlytics Course Material Week 3 - Medical Image Processing

Datasets used in this repo:

Mammogram Image Dataset: DDSM: http://marathon.csee.usf.edu/Mammography/Database.html CBIS-DDSM: https://wiki.cancerimagingarchive.net/display/Public/CBIS-DDSM Jpegs and labels were extracted from a tfrecords dataset curated by Eric Scuccimarra: https://www.kaggle.com/skooch Colorectal Histology Dataset: https://zenodo.org/record/53169#.W2hf_NJKh9M Kather JN, Weis CA, Bianconi F, Melchers SM, Schad LR, Gaiser T, Marx A, Zollner F: Multi-class texture analysis in colorectal cancer histology (2016), Scientific Reports (in press)

Notebooks

• Contains notebooks with lessons (and solutions) on Texture Classification, Classification with Convulutional Neural Nets, Classification with Neural Nets, Classification using ImageNet, and Classification using VGG16. Also contains a notebook in progress on segmentation using UNets. All notebooks made by Siddharth Samsi.

Challenge

• Contains the week 3 image analysis challenge (classifying mammogram images) and the evaluation script for submissions. Created by Thomas Possidente

Data

• Contains the histology data for the notebook lessons