Semi-supervised Few-Shot Learning for Medical Image Segmentation

Implementation code for Semi-supervised approach for few-shot semantic medical image segmentation. This method is the first attempt to apply the episodic training paradigm for few-shot medical image segmentation. This method also enriches the feature representation in an unsupervised manner. More specifically, this method boosts the encoder representation with including surrogate task. Experimental results on two well-know Skin Lesion Segmentation data sets have been demonstrated that the proposed method produces promising results. If this code helps with your research please consider citing the following paper:

Abdur. R. Fayjie, R. Azad, Claude Kauffman, Ismail Ben Ayed, Marco Pedersoli and Jose Dolz "Semi-supervised Few-Shot Learning for Medical Image Segmentation", arXiv preprint arXiv, 2020, download link.

Updates

March 20, 2020: Implementation code is available now.

Prerequisties and Run

This code has been implemented in python language using Keras libarary with tensorflow backend and tested in ubuntu OS, though should be compatible with related environment. following Environement and Library needed to run the code:

Python 3
Keras version 2.2.0
tensorflow backend version 1.13.1

Run Demo

Please follow the bellow steps to run the code.
1- Download the FSS1000 dataset from this link and extract the dataset to a folder name fss_dataset.
2- Download the ISIC 2018 train dataset from this link and extract both training dataset and ground truth folders to a folder ISIC2018.
3- Download the ph2 dataset from this link and extract to a folder dataset_PH2Datasetisic18.
4- Run Prepare_ISIC2018.py for data preperation and dividing data to train(unlabeled) and test sets.
5- Run Prepare_ph2.py for data preperation and providing test sets.
6- Run Train_evaluate.py for training and evaluation.