"False"
Skip to content
printicon
Main menu hidden.
Staff photo Giulia Romoli

Giulia Romoli

Multimodal, generative AI applied to biomedical images

Contact

E-mail

Works as

Affiliation
Location
5A, Målpunkt H62, Norrlands universitetssjukhus Umeå universitet, 901 85 Umeå SE

My research focuses on AI-driven analysis of biomedical images for clinical applications, with particular emphasis on lung cancer. I am using multimodal generative models to translate information across imaging modalities (CT, MRI and PET), to assess whether the information that drives clinical decisions, such as lesions, is preserved in the translated images. I am also developing physics-constrained diffusion models to simulate cancer progression under different scenarios, so that the forecasts stay consistent with mechanistic models of tumour biology.

Complex, intelligent and software intensive systems: Proceedings of the 20th International conference on complex, intelligent, and software intensive systems (CISIS-2026), volume 2, Cham: Springer 2027 : 26-38
Bonifacio, Anna; Iele, Irene; Romoli, Giulia; et al.
ACM-BCB 2026 - 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
Aksu, Fatih; Ciuffetti, Laura; Di Feola, Francesco; et al.
Ital-IA-TW 2025. Thematic Workshops at Ital-IA 2025: Joint Proceedings of the Thematic Workshops at Ital-IA 2025colocated with the 5th National Conference on Artificial Intelligence, organized by CINI (Ital-IA 2025)
Tortora, Matteo; Romoli, Giulia; Guarrasi, Valerio; et al.

Research groups

Group member