LUMINATE
Multimodal lung cancer screening research using low-dose CT, low-dose FDG PET/CT, and AI risk prediction.
PNRR Research Project
LUMINATE
Multimodal lung cancer screening research using low-dose CT, low-dose FDG PET/CT, and AI risk prediction.
Overview
LUMINATE addresses lung cancer screening through artificial intelligence, multimodal imaging, and technologies for early detection and characterisation. The project combines low-dose CT, low-dose FDG PET/CT, and clinical information to improve risk assessment.
The UCBM engineering unit contributes AI models for predicting lung cancer risk using clinical and imaging data, within a multi-centre project coordinated by Ospedale San Raffaele.
Research Directions
- Early detection and characterisation of suspicious lung nodules.
- AI models for lung cancer risk prediction from clinical and imaging data.
- Integration of low-dose CT and low-dose FDG PET/CT in screening workflows.
Related Publications
- Virtual Scanning for NSCLC Histology: Investigating the Discriminatory Power of Synthetic PETarXiv preprint arXiv:2605.02746, 2026generative AI medical imaging multimodal learning
- Lesion-Aware Generative Artificial Intelligence for Virtual Contrast-Enhanced Mammography in Breast Cancer2025radiomics oncology generative AI
- Augmented intelligence for multimodal virtual biopsy in breast cancer using generative artificial intelligence2025oncology multimodal learning generative AI
- Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin2025medical imaging generative AI
- Multimodal Doctor-in-the-Loop: A Clinically-Guided Explainable Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer2025radiomics oncology multimodal learning
- Doctor-in-the-Loop: An explainable, multi-view deep learning framework for predicting pathological response in non-small cell lung cancer2025explainability oncology medical imaging
- Can Foundation Models Really Segment Tumors? A Benchmarking Odyssey in Lung CT Imaging2025foundation models medical imaging
- NSCLC histological subtype classification from CT scans using generalist 3D medical foundation models2025radiomics oncology foundation models
- Multi-stage intermediate fusion for multimodal learning to classify non-small cell lung cancer subtypes from CT and PET2025radiomics oncology multimodal learning
- Enhancing NSCLC Histological Subtype Classification: A Federated Learning Approach Using Triplet Loss2025radiomics oncology medical imaging