Related Experiment Video
Updated: Jun 26, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.7K
Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics
Rucha Deshpande1, Varun A Kelkar2, Dimitrios Gotsis2
1Dept. of Biomedical Engineering, Washington University in St. Louis, St. Louis, Missouri, USA.
Arxiv
|May 15, 2024
Summary
The 2023 AAPM Grand Challenge on Deep Generative Models (DGMs) for medical imaging revealed that domain-specific evaluations are crucial for assessing DGM performance and guiding future development. Rankings varied significantly based on evaluation metrics, highlighting the need for tailored assessments.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computational Science
Background:
- The 2023 AAPM Grand Challenge focused on Deep Generative Models (DGMs) for learning medical image statistics.
- This initiative aimed to advance DGM development and establish domain-relevant assessment methods in medical imaging.
Conclusions:
- The Grand Challenge underscored the critical need for domain-specific evaluation frameworks to guide DGM design and deployment in medical imaging.
- The study demonstrated that DGM specifications should be tailored to their intended use cases.
