ArticleEBioMedicine2024
Drop the shortcuts: image augmentation improves fairness and decreases AI detection of race and other demographics from medical images.
Article in EBioMedicine, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed, 20 citations in OpenAlex.
- Improving racial fairness in brain age models using style-transfer synthesis.bioRxiv : the preprint server for biology · 2026Article
- Deceptive bias measurement in deep learning: Assessing shortcut reliance in TCGA cancer models.PLOS digital health · 2026Article
- Deep learning model for body weight estimation from computed tomography scout images incorporating sex and height.Radiological physics and technology · 2026Article
- Discriminating HFrEF vs HFpEF from chest radiographs: Mitigating demographic performance gaps via augmentation and multimodal fusion.PLOS digital health · 2026Article
- Decipher-MR: a vision-language foundation model for 3D MRI representations.NPJ digital medicine · 2026Article
- Diffusion-synthesized Chest X-rays improve fairness and diagnostic performance.PLOS digital health · 2026Article
- RoentMod: a synthetic chest X-ray modification model to identify and correct image interpretation model shortcuts.NPJ digital medicine · 2026Article
- Artificial intelligence in anesthesiology education: transformative applications, challenges, and future perspectives.Frontiers in medicine · 2026Review
- Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses.NPJ digital medicine · 2025Review
- Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review.Journal of imaging informatics in medicine · 2025Article
- Re-identification of patients from imaging features extracted by foundation models.NPJ digital medicine · 2025Article
- Leveraging artificial intelligence to validate traditional biomarkers and drug targets in liver cancer recovery: a mini review.Frontiers in pharmacology · 2025Review
- Article
- The risk of shortcutting in deep learning algorithms for medical imaging research.Scientific reports · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors at 4 institutions in 2 countries.
Funding
Abstract
backgroundIt has been shown that AI models can learn race on medical images, leading to algorithmic bias. Our aim in this study was to enhance the fairness of medical image models by eliminating bias related to race, age, and sex. We hypothesise models may be learning demographics via shortcut learning and combat this using image augmentation.
methodsThis study included 44,953 patients who identified as Asian, Black, or White (mean age, 60.68 years ±18.21; 23,499 women) for a total of 194,359 chest X-rays (CXRs) from MIMIC-CXR database. The included CheXpert images comprised 45,095 patients (mean age 63.10 years ±18.14; 20,437 women) for a total of 134,300 CXRs were used for external validation. We also collected 1195 3D brain magnetic resonance imaging (MRI) data from the ADNI database, which included 273 participants with an average age of 76.97 years ±14.22, and 142 females. DL models were trained on either non-augmented or augmented images and assessed using disparity metrics. The features learned by the models were analysed using task transfer experiments and model visualisation techniques.
findingsIn the detection of radiological findings, training a model using augmented CXR images was shown to reduce disparities in error rate among racial groups (-5.45%), age groups (-13.94%), and sex (-22.22%). For AD detection, the model trained with augmented MRI images was shown 53.11% and 31.01% reduction of disparities in error rate among age and sex groups, respectively. Image augmentation led to a reduction in the model's ability to identify demographic attributes and resulted in the model trained for clinical purposes incorporating fewer demographic features.
interpretationThe model trained using the augmented images was less likely to be influenced by demographic information in detecting image labels. These results demonstrate that the proposed augmentation scheme could enhance the fairness of interpretations by DL models when dealing with data from patients with different demographic backgrounds.
fundingNational Science and Technology Council (Taiwan), National Institutes of Health.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.