Authors & Publications

Luigi Manco, MP

Luigi Manco is a Medical Physicist actively engaged in research on advanced applications of physics in medicine, with a specific focus on quantitative medical imaging. He strongly believes in multidisciplinarity as a fundamental driver of innovation in healthcare, and in the role of the medical physicist as a provider of methodological and technological tools in support of clinicians and, ultimately, patients. His continuous interaction with physicians from different medical specialties has shaped a scientific vision centered on medical images as high-dimensional data sources rather than mere visual representations. Strongly aligned with Gillies’ 2015 paradigm, “Images are more than pictures, they are data,” he has systematically worked on the development of predictive radiomics models aimed at supporting and enhancing clinical decision-making processes. His research is grounded in the application of physical principles to personalized medicine, with particular emphasis on robustness, reproducibility, and multicenter validation. A central aspect of his scientific contribution is the promotion of standardized radiomics pipelines, designed to minimize methodological variability and to improve the reliability, comparability, and generalizability of radiomics and data-driven deep learning studies across institutions. He is one of the proponents of RADAR, an initiative conceived to provide shared methodological and computational tools to multidisciplinary scientific communities, fostering standardization, transparency, and scientific rigor in quantitative imaging research.

Luca Urso, MD

Luca Urso is an Assistant Professor of Nuclear Medicine at the University of Ferrara (Italy) and a clinical investigator with extensive experience in oncologic PET/CT, theranostics, and multicenter clinical research. His scientific activity focuses on the integration of advanced imaging biomarkers into clinical decisionmaking, with a growing specialization in radiomics, AIassisted image analysis, and methodological rigor in quantitative imaging. He serves as Principal Investigator in several national and international prospective studies and contributes to guideline development and scientific dissemination through active roles in AIMN (Italian Association of Nuclear Medicine) study groups, editorial boards, and international collaborations. His work aims to promote reproducible, clinically meaningful radiomic research and to support the translation of quantitative imaging tools into everyday practice.

Luca Filippi, MD

Luca Filippi is an Associate Professor of Nuclear Medicine, whose research activity focuses on the development and clinical validation of artificial intelligence and radiomics methodologies applied to medical imaging. His work is centered on the design of robust radiomics pipelines for PET/CT and multimodal imaging, including image preprocessing, semiautomatic and automatic segmentation, feature extraction, harmonization of multicenter datasets, and advanced statistical and machine learning–based classification approaches. A key component of his research is the application of AI-driven methods for structured analysis and classification of scientific literature and imaging data, with particular attention to reproducibility, feature stability, and bias control. His activity aims to bridge methodological innovation and clinical applicability, supporting the development of reliable, interpretable AI tools for oncologic and neurologic imaging research. As Vice Secretary of the AIMN Study Group on AI and Radiomics, Luca Filippi promotes educational activities in the field through the organization of webinars and in-person training events.

Giovanni Scribano, Researcher

Giovanni Scribano is a medical physics Researcher and software developer working in the field of quantitative medical imaging and oncology. He holds a master’s degree in physics and is currently a postgraduate student in medical physics. His research focuses on the development of predictive models for clinical decision support, with particular attention to radiomics, genomics, and multimodal imaging. He works mainly in Python, combining big data analysis, image processing, machine learning, deep learning, and his contributions are supported by peer-reviewed scientific publications. He collaborates closely with multidisciplinary teams, believing that meaningful innovation in healthcare emerges from the integration of diverse expertise.