PREDICTOME

Team: Georg Langs, Yen Tan, Christoph Bock, Paulina Gebhart, Ivana Janícková, Thomas Helbich, Bettina Roethlin, Valentin Militevic, Zsuzsanna Bago-Horvath, Daphne Resch, Thomas Spiegel, Katja Pinker, Christian Singer, Martin Ortner

Project Summary

Breast cancer (BC) is the most common cancer and the second leading cause of cancer death in women. Many patients with BC can be cured with existing therapies, but side effects cause substantial physiological and psychological burden. Early prediction of individual risk and therapy response is essential for advancing personalized BC therapy. Toward the goal of avoiding over-treatment in low-risk patients, gene expression signatures can already identify patients who may safely avoid chemotherapy. Pushing personalization further, it seems realistic that integrating functional imaging in combination with multi-omics profiling will accurately identify a subset of BC patients who can safely forgo curative surgery. Here we pursue the hypothesis that integrative ML analysis of functional imaging (PET/MRI) and multi-omics profiling of tumor biopsies and liquid biopsy at early response can predictively identify patients that will achieve pathological complete response (pCR) following neoadjuvant chemotherapy (NACT), with the future perspective of avoiding resective surgery in these patients. PREDICTOME will develop a validated ML model for predicting pCR in BC towards safely omitting surgery in low-risk patients based on multi-omics dynamics during early NACT response. To this end, it will combine a large, well-characterized retrospective cohort with long-term follow-up data with the power of a prospective cohort, including multi-omics analysis of early molecular responses to.

Publications

• Fürböck, C., Perkonigg, M., Helbich, T., Pinker, K., Romeo, V. and Langs, G., 2022, September. Identifying Phenotypic Concepts Discriminating Molecular Breast Cancer Sub-Types. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VII(pp. 276-286).
• Romeo, V., Helbich, T.H. and Pinker, K., 2022. Breast PET/MRI Hybrid Imaging and Targeted Tracers. Journal of Magnetic Resonance Imaging.
• Stolz M, Farr A, Tendl-Schulz KA, Frommlet F, Reckendorfer H, Koperek O, Neudert B, Marhold M, Heber U, Exner R, Singer CF, Bartsch R, Bago-Horvath Z. HER2/CEP17 ratio predicts residual cancer burden after neoadjuvant dual HER2 blockade: real-world data in patients with primary HER2-amplified breast cancer. Virchows Arch. 2025 Aug 5. doi:10.1007/s00428-025-04203-5. Epub ahead of print. PMID: 40762650.
• Janíčková, I., Tan, Y.Y., Helbich, T.H., Miloserdov, K., Bago-Horvath, Z., Heber, U. and Langs, G., 2025, September. Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 606-615). Cham: Springer Nature Switzerland. https://arxiv.org/abs/2509.14872 
• Kamran, M., Bernathova, M., Varga, R., Singer, C. F., Bago-Horvath, Z., Helbich, T., ... & Seeböck, P. (2025, September). LesiOnTime-Joint Temporal and Clinical Modeling for Small Breast Lesion Segmentation in Longitudinal DCE-MRI. In Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care (pp. 329-339). Cham: Springer Nature Switzerland. https://arxiv.org/abs/2508.00496 
• Brandstätter, S., Köller, M., Seeböck, P., Blessing, A., Oberndorfer, F., Pochepnia, S., ... & Langs, G. (2025). Semantic Mosaicing of Histo-Pathology Image Fragments using Visual Foundation Models. In Proc. MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL).  arXiv preprint arXiv:2508.03524. https://arxiv.org/abs/2508.03524 
• Fürböck, C., Weiser, P., Mitic, B., Seeböck, P., Helbich, T., & Langs, G. (2025). No Modality Left Behind: Dynamic Model Generation for Incomplete Medical Data. in Proc. MICCAI Workshop on Machine Learning in Clinical Decision Systems ML-CDS arXiv preprint arXiv:2509.11406. https://arxiv.org/abs/2509.11406v1 
• Daphne Resch, Oğuz Lafci, Paola Clauser, Pascal Baltzer, Zsuzsanna Bago-Horvath, Yen Tan, Georg Langs, Thomas Helbich (2025). Assessment of Early Therapy Response to Neoadjuvant Chemotherapy of Breast Cancer Patients with multiparametric 18F-Fluorodeoxyglucose (18F-FDG)-PET/MRI using Radiomic Shape Features - Preliminary Results of the PREDICTOME-Study. Oral Presentation at European Congress of Radiology (ECR) 2025.
• Daphne Resch, Oğuz Lafci, Nina Pirringer-Pötsch, Pascal Baltzer, Zsuzsanna Bago-Horvath, Yen        Tan3, Georg Langs, Thomas Helbich (2025). Assessment of Early Therapy Response to Neoadjuvant Chemotherapy of Breast Cancer Patients with multiparametric 18F-Fluorodeoxyglucose (18F-FDG)-PET/MRI: Preliminary Results of the PREDICTOME-Study. Abstract presented at European Congress of Radiology (ECR) 2025.
   

Image: MedUni Wien/Georg Langs