# Codes for paper- OPHash: Learning of Organ and Pathology Context Sensitive Hashing for Medical Image Retrieval

Prerequisites

• Ubuntu* 20.04
• Python* 3.9
• NVidia* GPU for training
• 16GB RAM for inference
• CUDA 11.2

Datasets

Large size dataset:

Brain (Figshare), Breast (Kaggle) and Chest and Retina (Mendeley).

Small size dataset:

MedMNIST v2. (#medmnist) (link), (link2)

Sample dataset availabel on './data/'.

Train

python OPHash.py

Trained model will be saved in './models/'. Trained models are available in Here.

Evalutions

python evalution.py

Contributor

The codes/model is contributed by

Asim Manna,
Centre of Excellence in Artificial Intelligence,
Indian Institute of Technology Kharagpur
email: asimmanna17@kgpian.iitkgp.ac.in