HOLY-2020 - Improved treatment stratification for HL

Cancer cells need a lot of sugar (also: glucose) for their rapid replication and the growth of a tumour. It is possible to visualize the sugar consumption by an imaging technique called Positron Emission Tomography (PET). This is done by providing the patient with minuscule amounts of radioactively labelled molecules of sugar; their path inside the body can then be tracked from the outside within a few minutes. PET is well-established in the diagnosis and treatment monitoring of Hodgkins lymphoma (HL). HL is a type of tumour that can be characterized by its sugar consumption. Thus, PET enables early monitoring of treatment response, that is shows if the lymphoma shrinks or grows, reflecting whether the therapy is working or not working. So far, only very basic information of the acquired PET images is used. Since the biology of HL is linked to its metabolism, we aim to analyze PET images in more detail by using artificial intelligence algorithms. By doing so, we seek to identify those patients specifically who suffer from aggressive HL and who are in need of more intense treatment. The same algorithms can hopefully be used also to identify patients with a favourable prognosis and who require less intense treatments with fewer side effects. All in all, our anticipated combination of PET imaging with AI postprocessing holds the potential for personalized treatment planning with immediate and long-term benefits to patients.

Artificial Intelligence Enhances Prognosis and Treatment Planning in Hodgkin Lymphoma International Study Paves the Way for More Personalized, Less Side-Effect Intensive Cancer Therapies An international research team has developed innovative methods to improve the treatment of patients with early-stage Hodgkin lymphoma. Central to the project was the use of artificial intelligence (AI) to analyze PET/CT imaging data alongside clinical information. The goal is to provide more accurate predictions of disease progression and tailor treatments to individual patients, minimizing side effects and improving quality of life. Background: Hodgkin lymphoma primarily affects young people, and current clinical models often fail to accurately predict which patients need more intensive treatment, resulting in unnecessary side effects. The research team used advanced imaging techniques, machine learning, and radiomic analysis to explore new ways of assessing risk. Key Findings: Fuzzy Radiomics: A novel approach to image analysis that accounts for blurry or uncertain boundary areas in scans, improving accuracy in predicting disease progression, especially in small tumors. AI-based Image Harmonization: Using Generative Adversarial Networks (GANs), the team was able to harmonize PET scans acquired from different clinics, reducing inconsistencies and improving the reliability of the analysis. Combining Clinical and Imaging Data: Integrating imaging data with genetic and clinical parameters led to more precise predictions of disease progression, outperforming traditional models. Faster Image Analysis with New Methods: A simplified technique using 2D image projections delivered results comparable to traditional 3D scans, while significantly reducing computational complexity. International Collaboration as the Key to Success The project was conducted in collaboration with research institutions in Vienna, Paris, and Barcelona. This international partnership enabled the analysis of a large patient cohort and the independent validation of the findings-a crucial step for the future clinical application of AI in healthcare. Conclusion: This research demonstrates how advanced imaging and artificial intelligence can work together to create more personalized, effective, and less harmful cancer therapies. The next step will be to conduct prospective studies to integrate these new methods into clinical practice.