Log into the student web
Edit content at umu.se
Enhancing Image-to-image translation by integrating texture information into the generation process
Di Feola, et al. "Multi-Scale Texture Loss for CT denoising with GANs." arXiv:2403.16640 (2024).
Di Feola, Pompilio et. al. "Texture Aware StarGAN for CT data harmonization" (submitted to IJCNN 2025).
Multi-Prompt Vision-Language Modeling for Multimodal Medical Data Generation
Molino, et al. "MedCoDi-M: A Multi-Prompt Foundation Model for Multimodal Medical Data Generation." arXiv preprint arXiv:2501.04614 (2025).
Molino, et al. "Any-to-Any Vision Language Model for Multimodal X-ray Imaging and Radiological Report Generation." (submitted to IJCNN 2025).
Towards Virtual Scanning via Cross-Modal Image-to-Image translation
Guarrasi, et al. "Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin" (submitted to IJCNN 2025).
Di Feola, et. al. "From Many models to One: A Unified approach for Whole Body CT-to-to-PET translation " (manuscript under preparation).
Bridging the performance gap between Paired and Unpaired Image-to-Image translation
Di Feola, et al. "A comparative study between paired and unpaired Image Quality Assessment in Low-Dose CT Denoising." 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS). IEEE, 2023.
Di Feola, et al. "Bridging Paired and Unpaired I2I translation with a paired virtual loss function" (manuscript under preparation).
Adapting on the Fly: Strengthening Models Against Out-of-Distribution Data
Iele, et. al. "Test-Time Adaptation for Medical Image-to-Image translation", (manuscript under preparation).
3D Whole-Body Image Translation with Brownian Bridge Diffusion
Bridging Local and Global Intelligence: Federated Learning & Knowledge Distillation for Generative Models
Leveraging Generative AI for Simulating Patient Scenarios Over Time
