augmentations-for-the-unknown

This repository contains the official implementation of "Data-Agnostic Augmentations for Unknown Variations - Out-of-Distribution Generalisation in MRI Segmentation", under review at MIDL 2025.

https://github.com/miagrouput/augmentations-for-the-unknown

Science Score: 54.0%

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

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (3.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

This repository contains the official implementation of "Data-Agnostic Augmentations for Unknown Variations - Out-of-Distribution Generalisation in MRI Segmentation", under review at MIDL 2025.

Basic Info
  • Host: GitHub
  • Owner: MIAGroupUT
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 1.61 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed 11 months ago
Metadata Files
Readme License Citation

README.md

Augmentations for the Unknown

This repository contains the official implementation of "Data-Agnostic Augmentations for Unknown Variations - Out-of-Distribution Generalisation in MRI Segmentation", under review at MIDL 2025.

Our work explores novel data augmentation techniques designed to improve model generalization in medical imaging, especially in scenarios with unseen domain shifts and rare cases.

Pretrained Models and Testing Data

Pretrained models and the testing data can be found at Zenodo.

Poster

Poster

Owner

  • Name: Mathematics of Imaging & AI Group
  • Login: MIAGroupUT
  • Kind: organization
  • Location: Netherlands

Citation (CITATION.cff)

cff-version: 1.2.0
message: If you use this software, please cite both the article from preferred-citation and the software itself.
authors:
  - family-names: Vaish
    given-names: Puru
  - family-names: Meister
    given-names: Felix
  - family-names: Heimann
    given-names: Tobias
  - family-names: Brune
    given-names: Christoph
  - family-names: Wolterink
    given-names: Jelmer M.
title: 'Data-Agnostic Augmentations for Unknown Variations: Out-of-Distribution Generalisation in MRI Segmentation'
version: 1.0.0
date-released: '2025-05-16'
preferred-citation:
  authors:
    - family-names: Vaish
      given-names: Puru
      orcid: "https://orcid.org/0000-0002-5180-5293"
    - family-names: Meister
      given-names: Felix
    - family-names: Heimann
      given-names: Tobias
    - family-names: Brune
      given-names: Christoph
      orcid: "https://orcid.org/0000-0003-0145-5069"
    - family-names: Wolterink
      given-names: Jelmer M.
      orcid: "https://orcid.org/0000-0001-5505-475X"
  title: 'Data-Agnostic Augmentations for Unknown Variations: Out-of-Distribution Generalisation in MRI Segmentation'
  doi: 10.48550/arXiv.2505.10223
  type: conference-paper
  pages: 1-29
  year: '2025'
  collection-title: International Conference on Medical Imaging with Deep Learning
  conference: {MIDL 2025}
  publisher: {Proceedings of Machine Learning Research}

GitHub Events

Total
  • Watch event: 1
  • Member event: 1
  • Push event: 13
  • Create event: 2
Last Year
  • Watch event: 1
  • Member event: 1
  • Push event: 13
  • Create event: 2