Copy number variations (CNVs) drive cancer progression. So far, spatial CNV inference has relied on whole transcriptome-based sequencing technologies. However, advances in image‐based spatial transcriptomics (iST) now enable high-plex gene measurement in situ. Here, we introduce an approach that adapts CNV inference to iST data, enabling spatial mapping of malignant clones and the tumor microenvironment, at single-cell resolution. Additionally, we assess how panel size and detection efficiency influence CNV inference. ### Competing Interest Statement S.M.S is co-founder of spatialist AB, a spatial omics consultancy company. H.H. is co-founder and Chief Scientific Officer of Omniscope, a Scientific Advisory Board member at Nanostring/Bruker and Mirxes, a consultant for Moderna and Singularity, and has received honoraria from Genentech. M.N. is co-founder of VoxlBio AB, a spatial omics reagents company. Swedish Research Council, https://ror.org/03zttf063, 2024-02533 Cancerfonden, 24-3457 Horizon Europe Mission on Cancer, 101136552 Swiss National Science Foundation, 222136 MCIN/AEI/10.13039/501100011033 and FSE+, RYC2022-035848-I MICIU/AEI/10.13039/501100011033/ FEDER/UE, PID2023-148687OB-I00 European Union’s H2020 research and innovation program, 848028 European Research Council (ERC), 810287 Ministerio de Ciencia e Innovación (MCI), PID2020-115439GB-I00, PLEC2021-007654 LaCaixa Foundation, HR22-0031, HR22-0172 Generalitat de Catalunya through the Suport Grups de Recerca AGAUR, 2021-SGR ERA-NET Neuron/Ministerio de Ciencia e Innovación (MCI), PCI2022-133012 ASPIRE Award from The Mark Foundation for Cancer Research Scientific Foundation of the Spanish Association Against Cancer U-CAN Erling Persson Foundation