Authors: Paraskevas Pegios, Manxi Lin, Nina Weng, Morten Bo Søndergaard Svendsen, Zahra Bashir, Siavash Bigdeli, Anders Nymark Christensen, Martin Tolsgaard, Aasa Feragen

Published on: March 13, 2024

Impact Score: 7.6

Arxiv code: Arxiv:2403.08700

Summary

• What is new: Use of diffusion-based counterfactual explainable AI to create high-quality ultrasound images from low-quality ones.
• Why this is important: Difficulty in producing high-quality obstetric ultrasound images due to various factors like less experienced sonographers and fetal or maternal dynamics.
• What the research proposes: A method that uses diffusion-based counterfactual explainable AI to generate realistic, high-quality standard planes from low-quality non-standard ones.
• Results: Effective generation of plausible counterfactual images of increased quality through both quantitative and qualitative evaluation.

Technical Details

Technological frameworks used: Diffusion-based counterfactual explainable AI

Models used: nan

Data used: Obstetric ultrasound images

Potential Impact

Healthcare sector, particularly companies and markets involved in obstetric care, medical imaging, and AI-driven diagnostic tools.

Want to implement this idea in a business?

We have generated a startup concept here: ImagiNate.