<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., ...Daha Fazla

8th International Conference on Medical Imaging with Deep Learning-MIDL, Utah, Amerika Birleşik Devletleri, 9 - 11 Temmuz 2025, cilt.301, ss.327-345, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 301
  • Basıldığı Şehir: Utah
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.327-345
  • İstanbul Üniversitesi Adresli: Evet

Özet

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.