Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis
The proposed method achieves efficient spatial-frequency domain fusion, significantly improving image generation quality. Experiments on the Patch Camelyon dataset show superior performance over eight state-of-the-art models across five metrics. This approach advances automated histopathological image generation with potential for clinical applications.
Authors
- Cheng Chi (ORCID: https://orcid.org/0000-0001-9056-0498)
- Tao Zhou (ORCID: https://orcid.org/0000-0002-8145-712X)
- Marzia Hoque Tania (ORCID: https://orcid.org/0000-0002-4496-1896)
- Jin Ma (ORCID: https://orcid.org/0009-0004-9528-7012)
- Qifeng Liu (ORCID: https://orcid.org/0000-0002-1224-3750)
Institutions
- The University of Sydney (AU)
- Nanchang University (CN)
- UNSW Sydney (AU)
- Second Affiliated Hospital of Nanchang University (CN)
Publication Details
- Journal
- BMC Bioinformatics
- Published
- 2025-01-27
- DOI
- https://doi.org/10.1186/s12859-025-06057-9
- Citations
- 4
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 9.92