dhrg / dmmn-osteosarcoma

Osteosarcoma Segmentation

This repository provides source code for osteosarcoma segmentation using Deep Multi-Magnification Network. Deep Multi-Magnification Network automatically segments multiple tissue subtypes by a set of patches from multiple magnifications in histopathology whole slide images. The original Deep Multi-Magnification Network paper is published here and its training and inference codes can be found here.

Prerequisites

• Python 3.6.7
• Pytorch 1.3.1
• OpenSlide 1.1.1
• Albumentations

Inference

The main inference codes are slidereader_coords.py and inference.py. You first need to run slidereader_coords.py to generate patch coordinates to be segmented in input whole slide images. After generating patch coordinates, you may run inference.py to generate segmentation predictions of input whole slide images. The segmentation predictions will be saved under imgs/ by default.

You may need to update the following variables before running slidereader_coords.py:

• slides_to_read: the list of whole slide images
• coord_file: an output file listing all patch coordinates

In addition to model_path and out_path, you may need to update the following variables before running inference.py:

• n_classes: the number of tissue subtype classes + 1
• test file: the list of patch coordinates generated by slidereader_coords.py
• data_path: the path where whole slide images are located

Please download the pretrained osteosarcoma model here.

Note that segmentation predictions will be generated in 4-bit BMP format. The size limit for 4-bit BMP files is 2³² pixels.

License

This project is under the CC-BY-NC 4.0 license. See LICENSE for details. (c) MSK

Acknowledgments

• This code is inspired by pytorch-semseg and MICCAI 2017 Robotic Instrument Segmentation.

Reference

If you find our work useful, please cite our paper:

@article{ho2023,
  title={Deep Learning-Based Objective and Reproducible Osteosarcoma Chemotherapy Response Assessment and Outcome Prediction},
  author={Ho, David Joon and Agaram, Narasimhan P. and Jean, Marc-Henri and Suser, Stephanie D. and Chu, Cynthia and Vanderbilt, Chad M. and Meyers, Paul A. and Wexler, Leonard H. and Healey, John H. and Fuchs, Thomas J. and Hameed, Meera R.},
  journal={The American Journal of Pathology},
  year={2023}
}