Regression Concept Vectors (RCVs)

This repository contains the development of the interpretability and perturbation robustness for the analysis of histopathology images by convolutional neural networks.

16
mentions
1
contributor
Get started
57 commits | Last update: October 29, 2020

Cite this software

Choose a version:
[[ releases[selectedIndex].tag ]]
  • [[release.tag]]
DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a reference manager file format:
[[ fileFormats[selectedFileFormatIndex].displayName ]]
  • [[ format.displayName ]]
Download file

What Regression Concept Vectors (RCVs) can do for you

  • Extraction of concept measures from manual nuclei annotations
  • Correlation analysis between concepts and network prediction
  • Analysis of the concept learning dynamics during training
  • Perturbation analysis by bidirectional relevance scores

Recent work on Testing with Concept Activation Vectors (TCAV) proposed directional derivatives to quantify the in uence of user-defined concepts on the network output [1]. However, diagnostic concepts are often continuous measures that might be counter intuitive to describe by their presence or absence. In this paper, we extend TCAV from a classification problem to a regression problem by computing Regression Concept Vectors (RCVs). Instead of seeking a discriminator between two concepts, we seek the direction of greatest increase of the measures for a single continuous concept. We measure the relevance of a concept with bidirectional relevance scores, Br. The Br scores assume positive values when increasing values of the concept measures positively affect classification and negative in the opposite case.

Read more
Tags
  • Medical image data
  • Machine learning
Programming Language
  • Python
License
  • MIT
Source code

Participating organizations

Mentions

2 Blog posts

1 Book section

3 Conference papers

1 Journal article

2 Presentations

7 Reports

Projects with Regression Concept Vectors (RCVs)

Contributors

  • Mara Graziani
    Haute École Spécialisée de Suisse Occidentale HES-SO Valais (HESSO)
Contact person
Mara Graziani
Haute École Spécialisée de Suisse Occidentale HES-SO Valais (HESSO)
Mail Mara

Information for page maintainers

OAI-PMH metadata:
429 Client Error: TOO MANY REQUESTS for url: https://zenodo.org/record/4157222
citation metadata:
no valid CITATION.cff found in any release.
Show