Multimodal AI-driven analysis in breast and lung cancer: insights from the OPTIMA prototyping workshop.
Abdollahyan M., Gadaleta E., James LGE., Thorn GJ., Corz JC., Singh V., Hettich M., Schneider L., Maiques O., Hijazy A., Golozar A., Rivas JG., Cornford P., Nicolleti R., Abbott T., Tan EH., Newby D., Papanastasiou G., Bussmann M., De Meulder B., Chelala C., PIONEER consortium and the OPTIMA consortium .
This paper reports on insights from the OPTIMA (Optimal Treatment for Patients with Solid Tumours in Europe Through Artificial Intelligence) prototyping workshop held in Berlin from November 6 to November 8, 2024. Through integrated analysis of clinical, genomic, imaging and pathology data, we addressed the following key challenges in breast and lung cancer management: utility of comprehensive genomic profiling in metastatic breast cancer settings; relevance of tumor heterogeneity for predicting treatment response; development of less invasive technologies for assessing tumor biology; and treatment outcomes in early stages of small cell lung cancer. Our findings demonstrate the potential of computational analysis using multiple data modalities to identify cancer molecular subtypes and enhance treatment selection and monitoring while highlighting important areas for future development to achieve the research objectives of the OPTIMA consortium.