Generative artificial intelligence enables the generation of bone scintigraphy images and improves generalization of deep learning models in data-constrained environments
Generative AI enables the targeted generation of bone scintigraphy images representing different clinical conditions. Our findings point to the potential of synthetic data to overcome challenges in data sharing and in developing reliable and prognostic deep learning models in data-limited environments.
Authors
- Durval C. Costa (ORCID: https://orcid.org/0000-0001-8039-4924)
- Alexander Haug (ORCID: https://orcid.org/0000-0002-8308-6174)
- Roberto Sciagrà
- Clemens P. Spielvogel (ORCID: https://orcid.org/0000-0002-4409-8324)
- Jing Ning (ORCID: https://orcid.org/0000-0002-5289-331X)
- Josef Yu (ORCID: https://orcid.org/0000-0003-1426-1538)
- Felix Hofer (ORCID: https://orcid.org/0000-0002-0185-7511)
- Francisco P. M. Oliveira (ORCID: https://orcid.org/0000-0001-9468-8894)
- Luca Camoni (ORCID: https://orcid.org/0000-0003-1654-323X)
- Christian Nitsche (ORCID: https://orcid.org/0000-0002-0141-7639)
- A. Monaci
- Kilian Kluge (ORCID: https://orcid.org/0000-0002-4224-7314)
- Marcus Hacker (ORCID: https://orcid.org/0000-0002-4222-4083)
- Cláudia S. Constantino (ORCID: https://orcid.org/0000-0003-4320-8437)
- Katharina Mascherbauer (ORCID: https://orcid.org/0000-0001-9681-1833)
- Francesco Bertagna (ORCID: https://orcid.org/0000-0003-2980-5964)
- Domenico Albano (ORCID: https://orcid.org/0000-0003-0810-6494)
- Zewen Jiang (ORCID: https://orcid.org/0009-0005-0172-868X)
- Katarina Kumpf
- David Haberl
- Maria Starace
Institutions
- Champalimaud Foundation (PT)
- Azienda Socio Sanitaria Territoriale degli Spedali Civili di Brescia (IT)
- Christian Doppler Laboratory for Thermoelectricity (AT)
- University of Florence (IT)
- Medical University of Vienna (AT)
- University of Brescia (IT)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2025-01-29
- DOI
- https://doi.org/10.1007/s00259-025-07091-8
- Citations
- 4
- Primary Topic
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 3.22
Funders
- Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung
- Universität Wien
- Medizinische Universität Wien
- Christian Doppler Forschungsgesellschaft
- Siemens Healthineers