Back to all papers

Predicting homologous recombination deficiency and treatment responses using a computed tomography-based foundation model: a preclinical study.

February 10, 2026pubmed logopapers

Authors

Kuang S,Schuitmaker L,Wu M,Salahuddin Z,van der Wiel A,van de Laak J,Lieuwes N,Biemans R,Jung J,Yaromina A,Dubois LJ,Woodruff HC,Lambin P

Affiliations (4)

  • Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Faculty of Health, Medicine and Life Sciences, Maastricht University, Maastricht, Netherlands. [email protected].
  • Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Faculty of Health, Medicine and Life Sciences, Maastricht University, Maastricht, Netherlands.
  • Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK.
  • Department of Radiology and Nuclear Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University Medical Center + , Maastricht, Netherlands.

Abstract

Homologous recombination deficiency (HRD) can lead to genomic instability, increased cancer susceptibility, and enhanced sensitivity to DNA-targeting therapies. Although radiomics has been used for various medical applications, its application in animal studies remains largely unexplored, primarily due to the typically limited availability of preclinical data. In this study, we applied a state-of-the-art foundation model (FM) on preclinical computed tomography (CT) images in mice, aiming to: (i) distinguish HRD status within isogenic xenografts, and (ii) predict differential therapeutic responses of CP-506, a novel hypoxia-activated DNA-crosslinking agent. The dataset comprises micro-CT scans of 307 mice with balanced HRD status, collected both before and after CP-506 or control treatment. The FM demonstrated robust HRD classification performance, achieving an AUC of 0.88 on the test set, which significantly outperformed the handcrafted radiomics and supervised deep learning (sDL). The highest AUC (0.93) was achieved in the consensus subgroup (71%) between sDL and FM. Additionally, HRD-related features predicted DNA damage and growth delay following the treatment. Interpretability analysis indicated the important role of texture heterogeneity in HRD classification. Therefore, these results suggest that FM successfully overcomes the data scarcity in animal studies and enables HRD classification and treatment response prediction from preclinical CT imaging.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.