# FRAME: Separating sampling variation from performance disparities in medical image analysis

arXiv: https://arxiv.org/abs/2608.25981 · HTML: https://mlsanity.com/paper/2608.25981/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 69 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [Disparities in Dermatology AI: Assessments Using Diverse Clinical Images](https://mlsanity.com/paper/2111.08006/) (2021)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [TorchXRayVision: A library of chest X-ray datasets and models](https://mlsanity.com/paper/2111.00595/) (2021)
- [CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats](https://mlsanity.com/paper/2405.19538/) (2024)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology](https://mlsanity.com/paper/2503.14911/) (2025)
- [De-biasing "bias" measurement](https://mlsanity.com/paper/2205.05770/) (2022)
- [Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms](https://mlsanity.com/paper/2201.07856/) (2022)
- [PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children](https://mlsanity.com/paper/2203.10612/) (2022)

## Abstract (arXiv)

Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidence of bias. Yet a perfectly fair model also produces a positive difference, which grows as subgroups shrink. Some mitigation methods remove demographic information from models because they assume that it produces the difference. Here we introduce Fair-model Reference And Mechanism Evaluation (FRAME). Its first step compares each reported difference with the difference expected from a perfectly fair model at the same subgroup counts. Its second step tests whether candidate causes of any excess over this fair-model reference change the difference when they are injected into model features. We evaluated 36 encoders on nine datasets in three modalities and audited 89 published differences across six modalities. For 10 frozen encoders and 13 chest radiograph findings, the reference is a median 41% of the race difference and 22% of the age difference. It is exceeded by 40 of 53 published differences in sensitivity or false positive rate and by one of 36 in the area under the receiver operating characteristic curve (AUROC). Adding race information to the features of two encoders does not change the race difference significantly. At matched disease performance, mitigation reduces the race difference by less than its spread across three pretraining seeds (medians 0.005 and 0.012) and the age difference by more (0.008 and 0.006). Image-text pretraining raises the worst-group AUROC for race by a median 0.049 over self-supervised pretraining. Reporting the fair-model reference beside every new and published subgroup difference could direct mitigation to the differences above it.