Preparing Ultrasound Imaging Data for Artificial Intelligence Tasks: Anonymisation, Cropping, and Tagging

Dimitrios Pechlivanis, Stylianos Didaskalou, Eleni Kaldoudi, Eleni Kaldoudi, George Drosatos

2025

Abstract

Ultrasound imaging is a widely used diagnostic method in various clinical contexts, requiring efficient and accurate data preparation workflows for artificial intelligence (AI) tasks. Preparing ultrasound data presents challenges such as ensuring data privacy, extracting diagnostically relevant regions, and associating contextual metadata. This paper introduces a standalone application designed to streamline the preparation of ultrasound DICOM files for AI applications across different medical use cases. The application facilitates three key processes: (1) anonymisation, ensuring compliance with privacy standards by removing sensitive metadata; (2) cropping, isolating relevant regions in images or video frames to enhance the utility for AI analysis; and (3) tagging, enriching files with additional metadata such as anatomical position and imaging purpose. Built with an intuitive interface and robust backend, the application optimises DICOM file processing for efficient integration into AI workflows. The effectiveness of the tool is evaluated using a dataset of Deep Vein Thrombosis (DVT) ultrasound images, demonstrating significant improvements in data preparation efficiency. This work establishes a generalizable framework for ultrasound imaging data preparation while offering specific insights into DVT-focused AI workflows. Future work will focus on further automation and expanding support to additional imaging modalities as well as evaluating the tool in a clinical setting.

Paper Citation

in Harvard Style

Pechlivanis D., Didaskalou S., Kaldoudi E. and Drosatos G. (2025). Preparing Ultrasound Imaging Data for Artificial Intelligence Tasks: Anonymisation, Cropping, and Tagging. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 951-958. DOI: 10.5220/0013379400003911

in Bibtex Style

@conference{healthinf25,
author={Dimitrios Pechlivanis and Stylianos Didaskalou and Eleni Kaldoudi and George Drosatos},
title={Preparing Ultrasound Imaging Data for Artificial Intelligence Tasks: Anonymisation, Cropping, and Tagging},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={951-958},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013379400003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Preparing Ultrasound Imaging Data for Artificial Intelligence Tasks: Anonymisation, Cropping, and Tagging
SN - 978-989-758-731-3
AU - Pechlivanis D.
AU - Didaskalou S.
AU - Kaldoudi E.
AU - Drosatos G.
PY - 2025
SP - 951
EP - 958
DO - 10.5220/0013379400003911
PB - SciTePress