/CS640-UBCOCEAN-Competition

Primary LanguagePython

CS640 Course Project

Competition Link

Installation Instructions

For installation instructions, refer to Installation Guide

Introduction

Our project involved tackling the UBC OCEAN competition, where we were provided with 70% of the data to build a model. Later, our code was evaluated on a hidden test set comprising 30% of the available data.

Steps

  1. Create Graph from image

Creating Graph

Image Source: Graph Transformer(Yi et al.)
  1. Creating graph based models on this data.

For more detailed description checkout Project Summary

Model architecture

Project Presentation

Project Report

References

  • Lu, M., Williamson, D., Chen, T., Chen, R., Barbieri, M., & Mahmood, F. (2021). Data-efficient and weakly supervised computational pathology on whole-slide images. Nature Biomedical Engineering, 5, 1-16. DOI

  • Wang, X., Yang, S., Zhang, J., Wang, M., Zhang, J., Yang, W., Huang, J., & Han, X. (2022). Transformer-based unsupervised contrastive learning for histopathological image classification. Medical Image Analysis, 81, 102559. DOI

  • Zheng, Y., Gindra, R., Green, E., Burks, E., Betke, M., Beane, J., & Kolachalama, V. (2022). A Graph-Transformer for Whole Slide Image Classification. IEEE Transactions on Medical Imaging, PP. DOI

  • Bradski, G. (2000). The OpenCV Library. Dr. Dobb's Journal of Software Tools. Link

  • Otsu, N. (1979). A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. Syst. Man Cybern. Link

  • He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv

  • Ilse, M., Tomczak, J. M., & Welling, M. (2018). Attention-based Deep Multiple Instance Learning. arXiv