In recent years, we have accumulated multiplex immunofluorescence images from over 7000 cancer patients, comprising multilayered visuals with various markers delineating cell types and their locations within the cancerous tissue. We used these images in different subprojects. The main project was to use these images to build AI methods, including interpretable models to predict therapy response and survival. However, we did not proceed with this project at this computationally intensive level, mainly because the main PhD student involved was on long sick leave. Now we hope to enter the project data analysis stage, which requires SUPR computational resource support. Furthermore, we have added two additional aspects of tissue analysis, supported by a PhD student and a postdoc, So Takata. Hui Yu uses multiplex images to define nerve structures in cancer tissue. So Takata now also uses different image types (Metabolomics (around 20 cases) and in situ sequencing images (around 25 cases)) from the same patients. They will be integrated with different computationally intensive methods. It is still difficult to foresee the need for computational resources, but our local computers are not powerful enough, so we are migrating the coding environment to the HPC and have started analysis. Therefore, we are convinced that the resources are being used.