Data

Tools

Indexes

Applications

Experiments

Open Source Science

infernocalibnet

Calibrating neural networks with Bayesian nonparametric regression (Inferno) to quantify uncertainty and improve prediction reliability.

https://github.com/m4siko/infernocalibnet

Science Score: 26.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (14.5%) to scientific vocabulary

Keywords

bayesian-regression image-classification inferno machine-learning neural-networks uncertainty-quantification x-ray-images
Last synced: 6 months ago · JSON representation

Repository

Calibrating neural networks with Bayesian nonparametric regression (Inferno) to quantify uncertainty and improve prediction reliability.

Basic Info
Statistics
  • Stars: 1
  • Watchers: 2
  • Forks: 0
  • Open Issues: 16
  • Releases: 0
Topics
bayesian-regression image-classification inferno machine-learning neural-networks uncertainty-quantification x-ray-images
Created over 1 year ago · Last pushed 8 months ago
Metadata Files
Readme License Code of conduct Citation

README.md

InfernoCalibNet

InfernoCalibNet Banner

Uncertainty aware predictions for medical AI using CNN and Bayesian nonparametrics framework (Inferno)

License: GPL v3 Contributor Covenant InfernoCalibNet

Table of Contents

Overview

Through uncertainty aware modeling, this research explores the application of Bayesian regression and convolutional neural networks (CNNs) to assist medical decision making. The CNN serves as a feature extractor in this configuration, converting complex visual input into a vector of real valued class values. These ratings are treated as structured summaries of the visual information rather than as final judgments.
This project uses Inferno, a Bayesian method that turns the CNNs raw confidence scores (logits) into well adjusted probability estimates. By adjusting for patient specific base rates and incorporating previous data, this statistical module allows clinicians to make decisions based on presented benefit rather than strict classification. Because the final decision is visible, individualized and based on Bayesian reasoning, the design eliminates the need to "explain" the CNN itself by separating prediction from action. Through a series of hypothetical experiments created to mirror the needs of personalized medicine, the project investigates Inferno's durability and medicinal usefulness. GradCAM heatmaps, which visually highlight where the CNN focuses its attention based on features from the base layer of the network, are included alongside the calibrated outputs. The combined probabilistic and location outputs are meant to help clinicians go beyond classification and provide informed, personalized medicine by helping them customize treatment choices for specific patients.

System Architecture (project workflow)

InfernoCalibNet System Architecture

Repository Structure

Installation

Quick Start

Note: The Inferno R-package provides Bayesian nonparametric calibration software package for CNN outputs.

Clone the repository without submodules

bash git clone https://github.com/589664/InfernoCalibNet.git

Clone the repository with submodules

bash git clone --recurse-submodules https://github.com/589664/InfernoCalibNet.git

If already cloned without submodules

bash git submodule update --init --recursive

Usage Examples

Citation

If you use this software or refer to its documentation, please consider citing:

bibtex @software{infernoCalibNet, author = {Maksim Ohvrill and PierGianLuca Porta Mana}, title = {InfernoCalibNet: Bayesian Calibration of CNN Outputs to Aid Clinical Decision-Making}, year = {2024}, version = {1.0}, date = {2024-06-02}, url = {https://m4siko.github.io/InfernoCalibNet/} }

You can also click the "Cite this repository" button on GitHub for other formats.

Acknowledgements

Maintained with love & passion by @m4siko

Owner

  • Name: Maksim Ohvrill
  • Login: m4siko
  • Kind: user
  • Location: Bergen, Norway
  • Company: Western University of Applied Sciences

Developer and researcher. Calibrating neural networks with Bayesian nonparametric regression to improve uncertainty quantification in medical imaging.

GitHub Events

Total
  • Issues event: 1
  • Watch event: 1
  • Delete event: 1
  • Push event: 55
  • Create event: 1
Last Year
  • Issues event: 1
  • Watch event: 1
  • Delete event: 1
  • Push event: 55
  • Create event: 1

Dependencies

pyproject.toml pypi
  • joblib >=1.4.2
  • matplotlib >=3.9.2
  • numpy >=1.26.4
  • pandas >=2.2.3
  • python-dotenv *
  • scikit-learn >=1.5.2
  • scipy >=1.14.1
  • seaborn >=0.13.2