# MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification

arXiv: https://arxiv.org/abs/2506.17140 · HTML: https://mlsanity.com/paper/2506.17140/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 13 of 13)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis](https://mlsanity.com/paper/2406.16192/) (2024)
- [Generative models improve fairness of medical classifiers under distribution shifts](https://mlsanity.com/paper/2304.09218/) (2023)
- [RudolfV: A Foundation Model by Pathologists for Pathologists](https://mlsanity.com/paper/2401.04079/) (2024)
- [Current Pathology Foundation Models are unrobust to Medical Center Differences](https://mlsanity.com/paper/2501.18055/) (2025)
- [DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology](https://mlsanity.com/paper/2306.13384/) (2023)
- [The Clever Hans Effect in Unsupervised Learning](https://mlsanity.com/paper/2408.08041/) (2024)
- [Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Study](https://mlsanity.com/paper/2411.05489/) (2024)
- [Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit'e, and Aignostics](https://mlsanity.com/paper/2501.05409/) (2025)
- [AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnostics](https://mlsanity.com/paper/2406.14866/) (2024)
- [Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology](https://mlsanity.com/paper/2312.09792/) (2023)

## Built on by (most cited first, 7 of 7)

- [Atlas 2 -- Foundation models for clinical deployment](https://mlsanity.com/paper/2601.05148/) (2026)
- [Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology](https://mlsanity.com/paper/2509.17847/) (2025)
- [Semi-Supervised Domain Adaptation with Latent Diffusion for Pathology Image Classification](https://mlsanity.com/paper/2601.17228/) (2026)
- [In-Context Multiple Instance Learning](https://mlsanity.com/paper/2606.06458/) (2026)
- [Robustifying pathology foundation models via fine-tuning](https://mlsanity.com/paper/2607.22861/) (2026)
- [HERO: Histology Encoder for Robust Representation in Oncology](https://mlsanity.com/paper/2609.35943/) (2026)
- [Representation Disentanglement for Fair Chest X-Ray Diagnosis](https://mlsanity.com/paper/2610.06041/) (2026)

## Abstract (arXiv)

Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to varying conditions such as staining, scanner, hospital, and demographics is still a limiting factor: if trained on overrepresented subpopulations, models regularly struggle with less frequent patterns, leading to shortcut learning and biased predictions. Large-scale foundation models have not fully eliminated this issue. Therefore, we propose a novel approach explicitly modeling such metadata into a Metadata-guided generative Diffusion model framework (MeDi). MeDi allows for a targeted augmentation of underrepresented subpopulations with synthetic data, which balances limited training data and mitigates biases in downstream models. We experimentally show that MeDi generates high-quality histopathology images for unseen subpopulations in TCGA, boosts the overall fidelity of the generated images, and enables improvements in performance for downstream classifiers on datasets with subpopulation shifts. Our work is a proof-of-concept towards better mitigating data biases with generative models.