Towards Fair Medical AI: Adversarial Debiasing of 3D CT Foundation Embeddings

• URL: http://arxiv.org/abs/2502.04386v1
• Date: Wed, 05 Feb 2025 20:32:42 GMT
• Title: Towards Fair Medical AI: Adversarial Debiasing of 3D CT Foundation Embeddings
• Authors: Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman, Vishwa S. Parekh,
• Abstract summary: Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional (3D) computed tomography (CT) data, generating compact, information-rich embeddings with 1408 features. These embeddings have been shown to encode demographic information, such as age, sex, and race, which poses a significant risk to the fairness of clinical applications. We propose a Variation Autoencoder (VAE) based adversarial debiasing framework to transform these embeddings into a new latent space where demographic
• Score: 13.985136866888379
• License:
• Abstract: Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional (3D) computed tomography (CT) data, generating compact, information-rich embeddings with 1408 features that achieve state-of-the-art performance on downstream tasks such as intracranial hemorrhage detection and lung cancer risk forecasting. However, these embeddings have been shown to encode demographic information, such as age, sex, and race, which poses a significant risk to the fairness of clinical applications. In this work, we propose a Variation Autoencoder (VAE) based adversarial debiasing framework to transform these embeddings into a new latent space where demographic information is no longer encoded, while maintaining the performance of critical downstream tasks. We validated our approach on the NLST lung cancer screening dataset, demonstrating that the debiased embeddings effectively eliminate multiple encoded demographic information and improve fairness without compromising predictive accuracy for lung cancer risk at 1-year and 2-year intervals. Additionally, our approach ensures the embeddings are robust against adversarial bias attacks. These results highlight the potential of adversarial debiasing techniques to ensure fairness and equity in clinical applications of self-supervised 3D CT embeddings, paving the way for their broader adoption in unbiased medical decision-making.

Related papers

• Demographic Predictability in 3D CT Foundation Embeddings [0.0]
  Self-supervised foundation models have been successfully extended to encode 3D computed tomography (CT) images. We evaluate whether these embeddings capture demographic information, such as age, sex, or race.
  arXiv  Detail & Related papers  (2024-11-28T04:26:39Z)
• Mortality Prediction of Pulmonary Embolism Patients with Deep Learning and XGBoost [0.5942186563711294]
  Pulmonary Embolism (PE) is a leading cause of mortality and critical illness. Conventional clinical methods have limited success in predicting 30-day in-hospital mortality of PE patients.
  arXiv  Detail & Related papers  (2024-11-27T05:15:55Z)
• Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning [52.249748801637196]
  3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. We propose a novel probabilistic-aware weakly supervised learning pipeline, specifically designed for 3D medical imaging.
  arXiv  Detail & Related papers  (2024-03-05T00:46:53Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Generative models improve fairness of medical classifiers under distribution shifts [49.10233060774818]
  We show that learning realistic augmentations automatically from data is possible in a label-efficient manner using generative models. We demonstrate that these learned augmentations can surpass ones by making models more robust and statistically fair in- and out-of-distribution.
  arXiv  Detail & Related papers  (2023-04-18T18:15:38Z)
• Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection [10.953610196636784]
  We propose a Contour Attention Preserving (CAP) method based on lung cavity edge extraction. Experimental results indicate that the proposed method achieves state-of-the-art performance in multiple adversarial defense and generalization tasks.
  arXiv  Detail & Related papers  (2022-11-30T08:01:23Z)
• PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training [52.895952593202054]
  We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation. PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state. Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
  arXiv  Detail & Related papers  (2022-07-24T07:45:47Z)
• Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation [2.3867305921818573]
  The application of deep learning in survival analysis (SA) gives the opportunity to utilize unstructured and high-dimensional data types uncommon in traditional survival methods. This allows to advance methods in fields such as digital health, predictive maintenance and churn analysis. We propose 1) a multi-task variational autoencoder (VAE) with survival objective, yielding survival-oriented embeddings, and 2) a novel method HazardWalk that allows to model hazard factors in the original data space.
  arXiv  Detail & Related papers  (2021-10-21T17:46:03Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples [74.92488215859991]
  We propose a novel 3D-based coarse-to-fine framework to efficiently tackle these challenges. The proposed 3D-based framework outperforms their 2D counterparts by a large margin since it can leverage the rich spatial information along all three axes. We conduct experiments on three datasets, the NIH pancreas dataset, the JHMI pancreas dataset and the JHMI pathological cyst dataset.
  arXiv  Detail & Related papers  (2020-10-29T15:39:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.