SPP 2177:  Radiomics: Next Generation of Biomedical Imaging

• Subject Area: Medicine ; Computer Science, Systems and Electrical Engineering ; Mathematics
• Term: since 2019
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 402688427

Compared to the first funding period of the Priority Programme we want to focus on the clinical implementation and value of advanced image analysis as well as the application of these techniques to gain deeper understanding of the role of imaging phenotypes in large-scale population cohorts. There is still not doubt that biomedical imaging plays an increasingly central role in the management of various disease settings in modern medicine. In addition, imaging is progressively more incorporated in research settings, including the formation of large-scale, population-based cohorts, such as the German National Cohort (NAKO Gesundheitsstudie). In parallel, with the advent of powerful, large scale computational power facilities and growing on-site expertise, advanced post-processing methods, including Artificial Intelligence, Deep-Learning, or Radiomics, are used to abstract descriptive, diagnostic, or prognostic information from high-resolution imaging data. As such, these derived parameters (“imaging phenotypes”) complement traditionally available and used image information, such as manual measurements of diameters or the mere presence of disease states and allow for high-volume, reproducible, and high-quality interpretation skills. However, despite these successful endeavours, there is still only early evidence that such advanced computer-based imaging post-processing provides incremental diagnostic and prognostic information in the field of personalised medicine, and algorithms have not fully entered the clinical arena yet. Given the great promise, the PP is designed to further develop and establish the role of advanced image interpretation approaches in different clinical scenarios in personalised medicine, including prevention of disease development.The aims of SPP2177 Phase 2 comprise: Aim 1 Determination of the diagnostic clinical value of advanced post-processing methods of human imaging data in different clinically relevant and/or in basic research settings; Aim 2 Determination of the prognostic value of advanced post-processing methods of human imaging data in clinically relevant settings and/or in basic research settings. The overall goal of the project is to further guarantee an efficient coordination and administration of the in order to further enhance the collaboration between the specific research projects within the programme, and with external stakeholders on national and international level in academia and industry. The activities of the coordinator and his team comprise the organization of retreats, conferences and workshops, support of visiting scientists, the coordination of outreach and public relation activities, the monitoring of gender measures, the control of programme finances and the establishment of communication and reporting structures. Coordination will also ensure scientific coherence of the projects. This project will support administration of central funds needed to organize and coordinate PP-internal activities.

• DFG Programme: Priority Programmes
• International Connection: Switzerland

Projects

• A whole body Radiomics approach in patients with metastatic melanoma undergoing systemic therapy: Fully automated longitudinal segmentation and Deep Learning-based outcome prediction (Applicants Eigentler, Thomas ;  Gerken, Annika ;  Othman, Ahmed ;  Peisen, Felix )
• Assessment of organ-specific biological age based on whole-body MR data from the German National Cohort Study. Phase II: Correlation with epidemiological, functional and clinical data (Applicants Gatidis, Sergios ;  Küstner, Thomas ;  Yang, Bin )
• Automated longitudinal characterization of the choroid plexus and glymphatic system in multiple sclerosis: facilitation of biomarker extraction and improvement of patient stratification (Applicants Gonzalez Escamilla, Ph.D., Gabriel ;  Groppa, Sergiu ;  Kronfeld, Andrea ;  Mukhopadhyay, Ph.D., Anirban ;  Othman, Ahmed )
• Coordination Funds (Applicant Bamberg, Fabian )
• DEvelopment and dEployment of a Pipeline for automated LymphoNodal profiling and staging: DEEP-LN (Applicants Baeßler, Bettina ;  Persigehl, Thorsten )
• Development and validation of artificial intelligence models using CT data and spatial dose distributions for the prediction of radiation pneumonitis in lung cancer patients treated within the multicenter prospective REQUITE trial (Applicants Peeken, Jan C. ;  Schnabel, Ph.D., Julia )
• Diagnostic and prognostic value of coronary artery flow and morphology in a multicentre randomised trial of computed tomography versus invasive angiography: clinical radiomics analysis (Applicant Dewey, Marc )
• Disentangling the interplay between the brain and the cardiovascular system: a population-based quantitative whole-body MRI approach (Applicants Hosp, Jonas Aurel ;  Rau, Alexander ;  Reisert, Marco ;  Weiss, Jakob )
• Epidemiologic, genetic and translational analyses of radiomics-based kidney features of two large, population-based studies (Applicants Kellner, Elias ;  Köttgen, Anna ;  Russe, Maximilian )
• Exploration of the Prognostic Value of Radiomics Analysis and Deep Learning of Coronary Plaques on Computed Tomography for Cardiovascular Events (Applicants Dewey, Marc ;  Rief, Matthias ;  Wald, Christian )
• Graph Learning and Pathophysiological Models: Towards a New Classification of White Matter Lesions in Multiple Sclerosis (Applicants Mühlau, Mark ;  Rückert, Ph.D., Daniel ;  Wiestler, Benedikt )
• Image-based personalized prediction of residual risk and prognosis of cardio/cerebrovascular disease (Applicants Hennemuth, Anja ;  Schulz-Menger, Jeanette-Esther ;  Villringer, Kersten )
• Imaging Biomarkers of Human Skeletal Muscle (Mass, Morphology and Texture Features of Muscle Groups in the Body Trunk and Thigh) in Sarcopenia and Cardiometabolic Disease (Applicants Kiefer, Lena Sophie ;  Schick, Fritz ;  Yang, Bin )
• MRI radiomics-based long-term evaluation and identification of imaging biomarkers for growth prediction of distinct nodular lesions in plexiform neurofibromas in NF1 (Applicants Ristow, Inka ;  Werner, René )
• Multimodal radiomics using MRI and amino acid PET in neuro-oncology (Applicants Galldiks, Norbert ;  Lohmann, Philipp )
• Next-generation image analytics for chemotherapy and survival prediction in pancreatic ductal adenocarcinoma (Applicant Braren, Rickmer Früdd )
• Next-generation imaging biomarkers in neuro-oncology using artificial intelligence: overcoming key challenges towards clinically applicable AI (Applicants Maier-Hein, Klaus ;  Vollmuth, Philipp )
• Patterns of white matter lesions in the brain: impact of air pollution on the variability of lifetime trajectories (Applicants Caspers, Svenja ;  Peters, Annette ;  Schneider, Alexandra )
• Phenotyping/Signature of adipose tissue compartments: A Radiomic, Cluster-based and geographic Analysis in the German National Cohort (Applicants Bamberg, Fabian ;  Kauczor, Hans-Ulrich ;  Machann, Jürgen ;  Nattenmüller, Johanna ;  Norajitra, Tobias ;  Rospleszcz, Susanne )
• Potential of Radiomics and AI in the prediction of breast cancer risk and mutation status in high risk patients with confirmed mutation or calculated high risk status (PRo-mics-BrCa) (Applicants Engel, Christoph ;  Fallenberg, Eva Maria ;  Hahn, Horst Karl ;  Ingrisch, Michael ;  Schmutzler, Rita Katharina )
• Prediction of treatment response and outcome in locally advanced rectal cancer using radiomics and deep learning: an example case to demonstrate a general purpose deep-learning-based processing pipeline for image classification. (Applicants Attenberger, Ulrike I. ;  Baeßler, Bettina ;  Hesser, Jürgen ;  Zöllner, Frank Gerrit )
• Radioclinomics for prediction of treatment response to immune checkpoint therapy and molecular targeted therapies in patients with metastatic malignant melanoma. (Applicant Umutlu, Lale )
• Structured prospective validation of published radiomics models and assessment of their applicability for clinical translation (Applicant Löck, Steffen )

• Spokesperson: Professor Dr. Fabian Bamberg