<i>MedDelinea</i>: Scalable and Efficient Medical Image Segmentation via Controllable Diffusion Transformers


Deshmukh G., Susladkar O. K., Jha D., Keles E., Aktas E., Medetalibeyoglu A., ...More

8th International Conference on Medical Imaging with Deep Learning-MIDL, Utah, United States Of America, 9 - 11 July 2025, vol.301, pp.327-345, (Full Text)

  • Publication Type: Conference Paper / Full Text
  • Volume: 301
  • City: Utah
  • Country: United States Of America
  • Page Numbers: pp.327-345
  • Istanbul University Affiliated: Yes

Abstract

We introduce MedDelinea, a novel medical image segmentation architecture that leverages a controllable module, drawing inspiration from ControlNet, within the Diffusion Transformers (DiT) framework. By doing so, we effectively address three key challenges inherent to segmentation tasks: (1) limited availability of labeled data, (2) variability in image modalities, and (3) the need for precise boundary delineation. MedDelinea is pre-trained on a large-scale medical dataset, thereby mitigating overfitting risks and enabling efficient transfer across diverse imaging scenarios with minimal fine-tuning requirements. The modular design of MedDelinea facilitates scalable and efficient computation, while maintaining high-quality segmentation performance in both supervised and zero-shot settings. Through extensive empirical evaluations on multiple datasets, we demonstrate that MedDelinea outperforms existing state-of-the-art segmentation approaches, showcasing its potential for robust and accurate medical image analysis.