EUVIMEDEUVIMED entdecken
Crossref

Bias Correction using content adaptation for medical image translation

Huiyan Lin, Haojin Li, Mingyang Ou, Jiajun Lin, Heng Li

Computational Biomedicine · 2025

DOI: 10.70401/cbm.2026.0011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Biomedicine, 2025. Verfasst von Huiyan Lin und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Medical image translation is widely used for data augmentation and cross-domain adaptation in clinical image analysis. However, the nature of medical imaging makes it challenging to collect high-quality samples for the training of translation models. Because of the limited access to and costly expense of medical images, distribution bias is commonly observed between the source and target samples, and this finally leads the models to mismatch the target domain.

Methods

To promote medical image translation, a bias correction method, named content adaptation, has been proposed in this study to align the training samples in the data space. Based on the invariant medical topological structure, paired samples are constructed from weakly paired and unpaired data using content adaptation to correct the distribution bias and promote the image-to-image translation.

Results

Experiments on retinal fundus image translation and COVID-19 CT synthesis demonstrate that the proposed method effectively suppresses structural hallucination and improves both visual quality and quantitative performance. Consistent gains are observed across multiple backbone models under different supervision settings. The results suggest that explicit anatomical alignment provides an effective and model-agnostic way to mitigate distribution bias in medical image translation. By bridging weakly paired data with paired translation paradigms, the proposed approach enhances structural fidelity without requiring strong supervision.

Conclusion

This work presents a topology-guided content adaptation strategy that improves robustness and reduces hallucination in medical image translation. The proposed framework is general and can be readily integrated into existing translation models, offering a practical solution for data-scarce medical imaging scenarios.

Zitieren

APA

Lin, H., Li, H., Ou, M., Lin, J., & Li, H. (2025). Bias Correction using content adaptation for medical image translation. Computational Biomedicine. https://doi.org/10.70401/cbm.2026.0011

Vancouver

Lin H, Li H, Ou M, Lin J, Li H. Bias Correction using content adaptation for medical image translation. Computational Biomedicine. 2025. doi:10.70401/cbm.2026.0011

BibTeX
@article{Lin2025,
  author = {Lin, Huiyan and Li, Haojin and Ou, Mingyang and Lin, Jiajun and Li, Heng},
  title = {Bias Correction using content adaptation for medical image translation},
  journal = {Computational Biomedicine},
  year = {2025},
  doi = {10.70401/cbm.2026.0011}
}
Kostenlos starten →