Predicting response to neoadjuvant chemotherapy in muscle-invasive bladder cancer via interpretable multimodal deep learning
Building accurate prediction models and identifying predictive biomarkers for treatment response in Muscle-Invasive Bladder Cancer (MIBC) are essential for improving patient survival but remain challenging due to tumor heterogeneity, despite numerous related studies. To address this unmet need, we developed an interpretable Graph-based Multimodal Late Fusion (GMLF) deep learning framework. Integrating histopathology and cell type data from standard H&E images with gene expression profiles derived from RNA sequencing from the SWOG S1314-COXEN clinical trial (ClinicalTrials.gov NCT02177695 2014-06-25), GMLF uncovered new histopathological, cellular, and molecular determinants of response to neoadjuvant chemotherapy. Specifically, we identified key gene signatures that drive the predictive power of our model, including alterations in TP63, CCL5, and DCN. Our discovery can optimize treatment strategies for patients with MIBC, e.g., improving clinical outcomes, avoiding unnecessary treatment, and ultimately, bladder preservation. Additionally, our approach could be used to uncover predictors for other cancers.
Authors
- Colin P. Dinney (ORCID: https://orcid.org/0000-0002-8969-711X)
- Joshua J. Meeks (ORCID: https://orcid.org/0000-0002-5444-5510)
- Ian M. Thompson (ORCID: https://orcid.org/0000-0003-0833-952X)
- Dan Theodorescu (ORCID: https://orcid.org/0000-0002-8708-8206)
- M. Scott Lucia
- Melissa Plets (ORCID: https://orcid.org/0009-0005-1449-0674)
- Siamak Daneshmand (ORCID: https://orcid.org/0000-0001-6224-9598)
- Seth P. Lerner (ORCID: https://orcid.org/0000-0002-6379-2581)
- Matthew Brendel (ORCID: https://orcid.org/0000-0003-3417-4597)
- David J. McConkey (ORCID: https://orcid.org/0000-0003-1971-0638)
- Olivier Elemento (ORCID: https://orcid.org/0000-0002-8061-9617)
- Mohamed Osman (ORCID: https://orcid.org/0000-0002-7909-0621)
- Daniel L. Gustafson (ORCID: https://orcid.org/0000-0002-3063-1669)
- Catherine M. Tangen
- Thomas W. Flaig (ORCID: https://orcid.org/0000-0001-6145-9040)
- Fei Wang (ORCID: https://orcid.org/0000-0002-1759-2570)
- Zilong Bai
- Bishoy M. Faltas
- Woonyoung Choi
Institutions
- Northwestern University (US)
- Cedars-Sinai Medical Center (US)
- The University of Texas MD Anderson Cancer Center (US)
- Johns Hopkins University (US)
- Baylor College of Medicine (US)
- Cornell University (US)
- Children's Hospital of San Antonio (US)
- USC Norris Comprehensive Cancer Center (US)
- University of Colorado Cancer Center (US)
- Weill Cornell Medicine (US)
- University of Colorado Denver (US)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-03-22
- DOI
- https://doi.org/10.1038/s41746-025-01560-y
- Citations
- 17
- Primary Topic
- Bladder and Urothelial Cancer Treatments
- Type
- article
- Field-Weighted Citation Impact
- 34.11