Novel computational and imaging tools are enhancing biomedical research precision. Virginia Commonwealth University launched TACIT, a machine learning algorithm that accelerates cell type assignment from complex multiplexed imaging by leveraging marker-thresholding and spatial multiomics integration, promising new insights into tissue biology and cancer research. Concurrently, Tokyo researchers unveiled MHP-Net, an AI model capable of segmenting liver tumors from CT images with small datasets, outperforming existing methodologies and facilitating improved diagnostics. Additionally, integrative cross-modal imaging genomics research is progressing, aiming to combine multi-omics and imaging data with AI to unravel comprehensive molecular and phenotypic disease architectures.