https://github.com/cv-inside/mv-kidney-stones

This repository hosts the script that was utilized for report the results of the conference article: “Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies”

https://github.com/cv-inside/mv-kidney-stones

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org, researchgate.net, scholar.google
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (10.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

This repository hosts the script that was utilized for report the results of the conference article: “Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies”

Basic Info
  • Host: GitHub
  • Owner: CV-INSIDE
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 28.9 MB
Statistics
  • Stars: 1
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme

README.md

Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies

This repository has the code to implement the methods described in the conference article: Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies, developed as part of the project "RECONDITE: Deep learning and image analysis methods for improving the endoscopic identification of kidney stones composition" at Tecnologico de Monterrey and Université de Lorraine.

Abstract

This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single view extraction backbones by 4% on average. Moreover, in comparison to the state-of-the-art, the fusion of the deep features improved the overall results up to 11% in terms of kidney stone classification accuracy.

[ArXiv]


Contents

Organization

No additional content directories are declared.

Contributors

Code for algorithms, applications and tools contributed by:

Elias Villalvazo-Avila, Francisco Lopez-Tiro, Jonathan El-Beze, Jacques Hubert, Miguel Gonzalez-Mendoza, Gilberto Ochoa, [Christian Daul](https://scholar.google.com/citations?

Please email us your comments, criticism, and questions at gilberto.ochoa@tec.mx

Reference

If you use functions from this script in your work, please use the BibTex entry below for citation.

[ArXiv]

@article{villalvazo2022improved, title={Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies}, author={Villalvazo-Avila, Elias and Lopez-Tiro, Francisco and El-Beze, Jonathan and Hubert, Jacques and Gonzalez-Mendoza, Miguel and Ochoa-Ruiz, Gilberto and Daul, Christian}, journal={arXiv preprint arXiv:2211.02967}, year={2022} }

Owner

Computer Vision for Image aNalysiS & bIomeDical Engineering. Tecnologico de Monterrey. School of Engineering and Sciences

GitHub Events

Total
Last Year