Design and integration of AI solutions in oncology and healthcare infrastructures : bridging the gap between AI innovation and clinical practice

<p dir="ltr">Artificial intelligence (AI) is driving major changes across numerous fields, with healthcare emerging as one of the areas with the greatest potential for impact. In medical imaging, AI has the potential to enhance patient care through personalized treatment planning and early disease detection, while simultaneously supporting clinicians by optimizing their workload, and automating complex tasks such as radiological image analysis. Over the past decade, substantial progress has been made in medical AI research, leading to highly accurate and robust models in controlled experimental settings. However, bringing these AI tools into everyday clinical use has proven challenging. Despite many scientific breakthroughs, only few AI systems are currently being adopted in clinical settings.</p><p dir="ltr">This PhD thesis focuses on understanding why that gap exists, and how to bridge it. The work explores the technical, organizational, and ethical barriers that slow down AI adoption in healthcare, and proposes new ways to make AI more practical, transparent, and trustworthy in clinical environments.</p><p dir="ltr">A key result of this research is MAIA, a collaborative platform designed to bring together doctors, radiologists, and AI researchers. MAIA provides a shared space where experts can jointly develop and test AI tools under realistic clinical conditions. By combining research methods with everyday medical workflows, MAIA helps accelerate the transition from experimental AI models to clinical tools. The platform has been successfully deployed in both research and hospital environments, demonstrating its effectiveness in accelerating the integration of AI into medical practice.</p><p dir="ltr">Building on this foundation, the thesis also introduces MONet, a framework that makes it easier to adapt and reuse state-of-the-art medical image segmentation models for different healthcare applications. It enables smooth integration of AI into various clinical settings, from federated learning across different institutions to human-in-the-loop smart annotation tools, ensuring that research innovations can be efficiently transferred into real-world practice.</p><p dir="ltr">Finally, as a methodological contribution to the field, the thesis investigates the incorporation of anatomical and contextual prior knowledge into existing deep learning frameworks, with the goal of improving model interpretability and anatomical awareness. These methods were evaluated on different clinical tasks, such as lung lobe segmentation on chest CT, breast cancer treatment response prediction, and lymphoma segmentation on whole-body PET/CT, with the findings suggesting that the relevance of anatomical priors is task-dependent and can vary significantly across contexts.</p><p dir="ltr">In summary, the thesis work aims to contribute to bridging the gap between AI research and clinical implementation by developing collaborative infrastructures, adaptable frameworks, and methodological insights that support the trustworthy, transparent, and effective integration of AI technologies in medical imaging practice.</p><h3>List of scientific papers</h3><p dir="ltr">Paper A. <b>Simone Bendazzoli</b>, Sanna Persson, Mehdi Astaraki, Sebastian Pettersson, Vitali Grozman, Rodrigo Moreno. MAIA: A Collaborative Medical AI Platform for Integrated Healthcare Innovation. [Accepted; Preprint] <a href="https://doi.org/10.48550/arXiv.2507.19489" rel="noreferrer" target="_blank">https://doi.org/10.48550/arXiv.2507.19489</a></p><p dir="ltr">Paper B. <b>Simone Bendazzoli</b>, Mehdi Astaraki, Antonios Tzortzakakis, Andréas Abrahamsson, Björn Engelbrekt Wahlin, Sofia Brunori, Maria Holstensson, Rodrigo Moreno. MONet-FL: Extending nnU-Net with MONAI for Clinical Federated Learning. In: Zamzmi, G., et al. Bridging Regulatory Science and Medical Imaging Evaluation; and Distributed, Collaborative, and Federated Learning. MICCAI 2025. Lecture Notes in Computer Science, vol 16135. Springer, Cham. <a href="https://doi.org/10.1007/978-3-032-05663-4_10" rel="noreferrer" target="_blank">https://doi.org/10.1007/978-3-032-05663-4_10</a></p><p dir="ltr">Paper C. <b>Simone Bendazzoli</b>, Emelie Bäcklin, Örjan Smedby, Birgitta Janerot-Sjoberg, Bryan Connolly, Chunliang Wang. Lung vessel connectivity map as anatomical prior knowledge for deep learning-based lung lobe segmentation. Journal of Medical Imaging, vol. 11, no. 04, Jul. 2024. <a href="https://doi.org/10.1117/1.jmi.11.4.044001" rel="noreferrer" target="_blank">https://doi.org/10.1117/1.jmi.11.4.044001</a></p><p dir="ltr">Paper D. <b>Simone Bendazzoli</b>, Mehdi Astaraki, Yanbo Li, Rodrigo Moreno, Örjan Smedby, Hong Lu, Chunliang Wang. Designing Radio-dynamics Features for PCR Prediction in Breast DCE-MRI. [Manuscript]</p><p dir="ltr">Paper E. <b>Simone Bendazzoli</b>, Antonios Tzortzakakis, Andreas Abrahamsson, Björn Engelbrekt Wahlin, Örjan Smedby, Maria Holstensson, Rodrigo Moreno. Anatomy-Aware Lymphoma Lesion Detection in Whole-Body PET/CT. [Manuscript]</p>