IPIS conceptual starting point is the one of an Artificial Intelligence (AI) framework, in which the mathematical formulation of the data analysis methods is associated to the search for automatic procedures for their implementation. Therefore, the project will devote methodological Work Packages (WPs) to the study of numerical methods in regularization theory, optimization, and numerical linear algebra crucial for the realization of automatic pipelines.
Mathematical approaches to imaging sciences are currently of two kinds: data-driven machine learning (ML) searches for hidden correlations among data, exploiting highly populated historical databases; model-driven inverse problems theory explicitly accounts for the mathematical model of signal formation and is particularly reliable in applications where large training sets are not available. IPIS aims at integrating these two paradigms by exploiting physical forward models to describe data generation, and prior models to identify data descriptors and decrease the conditioning of the numerical problem.
Besides representing a framework for the development of basic research in mathematical imaging, IPIS is also an application-oriented proposal, where the computational techniques of the methodological WPs will be mainstreamed into an application WP devoted to four imaging modalities: linear and non-linear tomographies, optical imaging, Fourier-based imaging, and parametric imaging. Further, two specific WPs will work at the implementation and validation of software tools, and at their showcasing across the scientific community, via a dissemination campaign based on an open-source, open-data strategy.
More specifically, IPIS is organized in six work packages (WPs) described below.
WP1 ensures the smooth coordination of the project by overseeing administrative and organizational aspects and by managing personnel, time, reporting and financial aspects. It facilitates communication between partners, organizes regular consortium meetings, and is responsible for establishing and maintaining the project website. This work package provides the foundation for effective collaboration and progress tracking across the entire initiative.
WP2 focuses on the formulation and implementation of computational methods for imaging. The work includes designing general and unified regularization methods, optimizing these methods for practical use, and advancing the underlying numerical linear algebra. The goal is to create robust and efficient algorithms that support the project’s broader imaging objectives.
WP3 aims to construct a common theoretical framework that connects inverse problems (IPs) with machine learning (ML) approaches in imaging. The work includes advancing regularization theory for IPs within ML contexts, developing ML-based regularization techniques, and applying ML methods to improve image reconstruction. This integration supports the project’s goal of bridging classical and data-driven approaches in imaging science.
WP4 focuses on applying the project’s inversion and regularization methods to real-world imaging problems across different key domains: linear and non-linear tomography, EIT in medical imaging and geophysics, optical imaging, Fourier-based imaging and X-ray solar imaging, and parametric imaging. It includes the development of advanced techniques such as AI-enhanced regularization for CT and PET, deconvolution and blind deconvolution methods for super-resolution light microscopy, and parametric modeling for PET tracer kinetics. This work package ensures that the theoretical and computational advances of the project are translated into impactful, application-driven results.
WP5 is dedicated to the development, validation, and deployment of software tools that embody the project's methodological advances. It includes rigorous testing of prototype implementations and culminates in the release of scikit-IPIS, an open-source software package with user-friendly graphical interfaces. This work package ensures the project’s outcomes are accessible, usable, and reproducible by the wider scientific and industrial communities.
WP6 aims to maximize the visibility and impact of the project through targeted dissemination and engagement activities. Key initiatives include organizing the IPIS Workshop on inverse problems in imaging sciences, launching a Guest Investigator Programme, and hosting a Stakeholder Workshop. This work package ensures the project's outcomes reach relevant communities and contribute to long-term impact and collaboration.