Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The CHIMERA challenge benchmarked 13 competitive multimodal architectures across 159 submissions to predict BCG immunotherapy response subtypes and time-to-progression survival using histopathology, structured clinical variables, and RNA-seq across 368 high-risk bladder cancer patients. Top-performing models reached a weighted F1 of 0.73 on subtype classification and a concordance index of 0.68 on survival prediction, though post-challenge auditing uncovered marked performance degradation under cross-cohort shifts and missing tabular data. Crucially, ablation and error analyses revealed that while whole-slide histopathology partially compensates for missing structured pathology data in subtyping tasks, progression modeling strictly demands multi-omic synergy and consistently fails on specific subgroups like T1 substages.
Histopathology can substitute for missing clinical tabular features in cancer subtyping, but multimodal survival prediction remains acutely fragile to tabular data dropouts and cohort shifts regardless of model architecture.
High-risk non-muscle-invasive bladder cancer (HR-NMIBC) carries substantial risks of recurrence and progression, while current clinical risk stratification remains limited. CHIMERA was established as a multimodal AI challenge to benchmark prediction in HR-NMIBC under standardized evaluation. Task BRS predicts RNA-seq-defined BCG Response Subtypes from histopathology and structured clinicopathological data, whereas Task Progression models time-to-progression using histopathology, structured data, and RNA sequencing. A multimodal dataset of 368 patients was divided into public training and hidden validation and test sets. In total, 159 submissions were made, and 13 top-performing models were selected for benchmarking. The best models achieved a weighted F1 score of 0.73 for Task BRS and a C-index of 0.68 for Task Progression. Post-challenge analyses revealed task-dependent modality contributions, cohort-dependent performance degradation, and sensitivity to missing structured data. In Task BRS, histopathology partly compensated for pathology-derived structured variables, whereas progression models showed greater dependence on complementary inputs. Cross-model error analysis further identified patients that were consistently difficult across different architectures, with T1 substage associated with prediction difficulty. These findings highlight barriers to transportability and the importance of missingness-aware modeling and independent multi-institutional validation. CHIMERA provides a standardized multimodal benchmark for bladder cancer and a framework for studying not only model performance, but also robustness, information sufficiency, and patient-level prediction failure.