EUVIMEDEUVIMED entdecken
Crossref

MC-DiffNet: Mask-Constrained and Cycle-Consistent Diffusion Network for Unpaired Ultrasound Image Enhancement

Nuo Chen, Yongquan Zhang, Guolin Chen, Jinhao Zhao, Changmiao Wang, Amirmehdi Yazdani, Hai Wang

IEEE Transactions on Emerging Topics in Computing · 2026-04 · 14 (2) · 678-690

DOI: 10.1109/tetc.2026.3695050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Emerging Topics in Computing, 2026-04. Verfasst von Nuo Chen und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Major Program of Zhejiang Provincial Philosophy and Social Science Planning, Planning Program of Humanities and Social Sciences of the Ministry of Education, First Class Discipline of Zhejiang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasound imaging is a valuable tool in clinical diagnostics due to its real-time feedback and non-invasive nature. Despite these advantages, it often suffers from issues like low contrast, speckle noise, and blurred anatomical boundaries, which can compromise the accuracy of diagnoses. Although diffusion models have proven effective for image restoration, their use in enhancing unpaired ultrasound images is limited. Another limitation is lacking of structural constraints and region-specific guidance. To address these challenges, we introduce MC-DiffNet, a multi-task, diffusion-based enhancement framework designed specifically for clinical ultrasound images in unpaired settings. Furthermore, the use of lesion masks provides structural guidance that enables the model to focus on pathological characteristics in ultrasound images. The framework incorporates three principal modules: a Cycle-Consistency Path, a Mask-Constrained Module, and a Context-Aware Classification Path. The Cycle-Consistency Path ensures consistency in unpaired training through degradation-reconstruction consistency. The Mask-Constrained Module incorporates lesion-aware structural constraints into the Structural Similarity Index Measure (SSIM) loss, aiming to maintain anatomical accuracy. Meanwhile, the Context-Aware Classification Path guides the enhancement process using semantic-level features. Together, these modules enable MC-DiffNet to enhance diagnostically significant regions with precision while preserving anatomical integrity. Experiments conducted on public ultrasound datasets reveal that our method outperforms existing techniques in both peak signal-to-noise ratio and SSIM. Remarkably, when applied to real-world unpaired datasets, MC-DiffNet offers improved structural fidelity and visual clarity. Further evaluation suggests that the enhanced images generated by our framework are beneficial for subsequent segmentation tasks, underscoring the clinical relevance and robustness of our approach.

Förderung

  • Major Program of Zhejiang Provincial Philosophy and Social Science Planning
  • Planning Program of Humanities and Social Sciences of the Ministry of Education
  • First Class Discipline of Zhejiang
  • Zhejiang University of Finance and Economics Statistics
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Zhejiang Provincial Bureau of Statistics Statistical Research Preferred Project

Zitieren

APA

Chen, N., Zhang, Y., Chen, G., Zhao, J., Wang, C., Yazdani, A., & Wang, H. (2026). MC-DiffNet: Mask-Constrained and Cycle-Consistent Diffusion Network for Unpaired Ultrasound Image Enhancement. IEEE Transactions on Emerging Topics in Computing, 14(2), 678-690. https://doi.org/10.1109/tetc.2026.3695050

Vancouver

Chen N, Zhang Y, Chen G, Zhao J, Wang C, Yazdani A, et al. MC-DiffNet: Mask-Constrained and Cycle-Consistent Diffusion Network for Unpaired Ultrasound Image Enhancement. IEEE Transactions on Emerging Topics in Computing. 2026;14(2):678-690. doi:10.1109/tetc.2026.3695050

BibTeX
@article{Chen2026,
  author = {Chen, Nuo and Zhang, Yongquan and Chen, Guolin and Zhao, Jinhao and Wang, Changmiao and Yazdani, Amirmehdi and Wang, Hai},
  title = {MC-DiffNet: Mask-Constrained and Cycle-Consistent Diffusion Network for Unpaired Ultrasound Image Enhancement},
  journal = {IEEE Transactions on Emerging Topics in Computing},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {678--690},
  doi = {10.1109/tetc.2026.3695050}
}
Kostenlos starten →