Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors

RESOURCE

Abstract

This software offers methods and functions for training calibrated out-of-distribution detectors for medical image classification tasks. It includes functionalities for training, synthesizing data augmentations, calibration, and out-of-distribution detection. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.
Developers:
Narayanaswamy, Vivek [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Release Date:
2023-06-05
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Version:
0.1
Licenses:
MIT License
Sponsoring Org.:
Code ID:
108775
Site Accession Number:
LLNL-CODE-850636
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Narayanaswamy, Vivek S. Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors. Computer Software. https://github.com/LLNL/OODmedic. USDOE National Nuclear Security Administration (NNSA). 05 Jun. 2023. Web. doi:10.11578/dc.20230627.1.
Narayanaswamy, Vivek S. (2023, June 05). Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors. [Computer software]. https://github.com/LLNL/OODmedic. https://doi.org/10.11578/dc.20230627.1.
Narayanaswamy, Vivek S. "Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors." Computer software. June 05, 2023. https://github.com/LLNL/OODmedic. https://doi.org/10.11578/dc.20230627.1.
@misc{ doecode_108775,
title = {Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors},
author = {Narayanaswamy, Vivek S.},
abstractNote = {This software offers methods and functions for training calibrated out-of-distribution detectors for medical image classification tasks. It includes functionalities for training, synthesizing data augmentations, calibration, and out-of-distribution detection. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.},
doi = {10.11578/dc.20230627.1},
url = {https://doi.org/10.11578/dc.20230627.1},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20230627.1}},
year = {2023},
month = {jun}
}