# A Multi-Cohort Validation of Censoring-Aware Conformal Lower Predictive Bounds for Pathology Survival Models

arXiv: https://arxiv.org/abs/2608.04025 · HTML: https://mlsanity.com/paper/2608.04025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology](https://mlsanity.com/paper/2403.06800/) (2024)
- [Continuous and Discrete-Time Survival Prediction with Neural Networks](https://mlsanity.com/paper/1910.06724/) (2019)
- [Effective Ways to Build and Evaluate Individual Survival Distributions](https://mlsanity.com/paper/1811.11347/) (2018)
- [Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2311.07125/) (2023)
- [Conformalized Survival Analysis](https://mlsanity.com/paper/2103.09763/) (2021)
- [2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification](https://mlsanity.com/paper/2412.00678/) (2024)
- [DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2407.03575/) (2024)
- [Conformalized survival analysis with adaptive cutoffs](https://mlsanity.com/paper/2211.01227/) (2022)
- [Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration](https://mlsanity.com/paper/2405.07374/) (2024)
- [AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification](https://mlsanity.com/paper/2406.15303/) (2024)
- [Doubly Robust Conformalized Survival Analysis with Right-Censored Data](https://mlsanity.com/paper/2412.09729/) (2024)
- [DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction](https://mlsanity.com/paper/2510.00053/) (2025)
- [Generating crossmodal gene expression from cancer histopathology improves multimodal AI predictions](https://mlsanity.com/paper/2502.00568/) (2025)
- [Conformal Survival Bands for Risk Screening under Right-Censoring](https://mlsanity.com/paper/2505.04568/) (2025)
- [Mamba2MIL: State Space Duality Based Multiple Instance Learning for Computational Pathology](https://mlsanity.com/paper/2408.15032/) (2024)
- [PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis](https://mlsanity.com/paper/2507.18848/) (2025)
- [Conformal predictive intervals in survival analysis: a re-sampling approach](https://mlsanity.com/paper/2408.06539/) (2024)
- [Good Rankings, Wrong Probabilities: A Calibration Audit of Multimodal Cancer Survival Models](https://mlsanity.com/paper/2604.04239/) (2026)
- [MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis](https://mlsanity.com/paper/2604.15729/) (2026)
- [Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction](https://mlsanity.com/paper/2604.24679/) (2026)
- [History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes](https://mlsanity.com/paper/2605.06581/) (2026)

## Abstract (arXiv)

Whole-slide survival models commonly provide risk rankings without calibrated statements about individual event times. We evaluate fixed-cutoff drcosarc, a post-hoc conformal wrapper for discrete-time multiple-instance learning survival heads using frozen UNI2-h representations, in an internal 18-configuration sweep across five TCGA cohorts and an external five-configuration evaluation across three CPTAC cohorts. We distinguish configuration--fold--split summaries of the inverse-probability-of-censoring-weighted (IPCW) estimate and median lower predictive bound (LPB) from a hierarchy-aware patient-ensemble estimand of the mean drcosarc--naive LPB difference. At α=0.1, the drcosarc IPCW estimate was nearest 0.90 in KIRC, LUAD, and STAD. Patient-ensemble drcosarc--naive intervals excluded zero in KIRC, KIRP, STAD, UCEC, and CPTAC-CCRCC, but included zero in internal LUAD, CPTAC-LUAD, CPTAC-UCEC, and the internal LUSC extension. In a 20-replicate low-censoring semi-synthetic setting with known event times, drcosarc empirical coverage was 0.9129 [0.9053, 0.9207]. An exploratory analysis supported a head-error-by-censoring interaction within that data-generating process. In a two-cohort ABMIL sensitivity analysis, increasing the hazard grid to K=16 raised localized marginal IPCW estimates above the prespecified 0.87 threshold and yielded positive paired LPB differences, although worst-group estimates remained below 0.87. Overall, performance was cohort dependent, and its interpretation changed with the patient-level unit, estimand, and censoring assumptions.