An investigation into the causes of race bias in AI-based cine CMR segmentation

• URL: http://arxiv.org/abs/2408.02462v1
• Date: Mon, 5 Aug 2024 13:40:33 GMT
• Title: An investigation into the causes of race bias in AI-based cine CMR segmentation
• Authors: Tiarna Lee, Esther Puyol-Anton, Bram Ruijsink, Sebastien Roujol, Theodore Barfoot, Shaheim Ogbomo-Harmitt, Miaojing Shi, Andrew P. King,
• Abstract summary: We perform a series of classification and segmentation experiments on cine cardiac magnetic resonance (CMR) images from the UK Biobank. We find that race can be predicted with high accuracy from the images alone, but less accurately from ground truth segmentations. Most attention in the classification models was focused on non-heart regions, such as subcutaneous fat.
• Score: 7.279664622541276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial intelligence (AI) methods are being used increasingly for the automated segmentation of cine cardiac magnetic resonance (CMR) imaging. However, these methods have been shown to be subject to race bias, i.e. they exhibit different levels of performance for different races depending on the (im)balance of the data used to train the AI model. In this paper we investigate the source of this bias, seeking to understand its root cause(s) so that it can be effectively mitigated. We perform a series of classification and segmentation experiments on short-axis cine CMR images acquired from Black and White subjects from the UK Biobank and apply AI interpretability methods to understand the results. In the classification experiments, we found that race can be predicted with high accuracy from the images alone, but less accurately from ground truth segmentations, suggesting that the distributional shift between races, which is often the cause of AI bias, is mostly image-based rather than segmentation-based. The interpretability methods showed that most attention in the classification models was focused on non-heart regions, such as subcutaneous fat. Cropping the images tightly around the heart reduced classification accuracy to around chance level. Similarly, race can be predicted from the latent representations of a biased segmentation model, suggesting that race information is encoded in the model. Cropping images tightly around the heart reduced but did not eliminate segmentation bias. We also investigate the influence of possible confounders on the bias observed.

Related papers

• Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images [5.952011729053457]
  We present a general, structured, scalable framework for evaluating bias in neural image compression models.<n>We show that traditional distortion metrics are ineffective in capturing bias in neural compression models.<n>We additionally show the bias can be attributed to compression model bias and classification model bias.
  arXiv  Detail & Related papers  (2025-05-05T18:27:11Z)
• Does a Rising Tide Lift All Boats? Bias Mitigation for AI-based CMR Segmentation [8.635755620107242]
  We use oversampling, importance reweighing and Group DRO as well as combinations of these techniques to mitigate the race bias. We find that bias can be mitigated using oversampling, significantly improving performance for the underrepresented Black subjects. Group DRO also improves performance for Black subjects but not significantly, while reweighing decreases performance for Black subjects.
  arXiv  Detail & Related papers  (2025-03-21T12:17:43Z)
• Classes Are Not Equal: An Empirical Study on Image Recognition Fairness [100.36114135663836]
  We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. Data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification.
  arXiv  Detail & Related papers  (2024-02-28T07:54:50Z)
• An investigation into the impact of deep learning model choice on sex and race bias in cardiac MR segmentation [8.449342469976758]
  We investigate how imbalances in subject sex and race affect AI-based cine cardiac magnetic resonance image segmentation. We find significant sex bias in three of the four models and racial bias in all of the models.
  arXiv  Detail & Related papers  (2023-08-25T14:55:38Z)
• Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases [62.54519787811138]
  We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. We rank images within their classes based on spuriosity, proxied via deep neural features of an interpretable network. Our results suggest that model bias due to spurious feature reliance is influenced far more by what the model is trained on than how it is trained.
  arXiv  Detail & Related papers  (2022-12-05T23:15:43Z)
• Decoupled Mixup for Generalized Visual Recognition [71.13734761715472]
  We propose a novel "Decoupled-Mixup" method to train CNN models for visual recognition. Our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions to train CNN models. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts.
  arXiv  Detail & Related papers  (2022-10-26T15:21:39Z)
• A systematic study of race and sex bias in CNN-based cardiac MR segmentation [6.507372382471608]
  We present the first systematic study of the impact of training set imbalance on race and sex bias in CNN-based segmentation. We focus on segmentation of the structures of the heart from short axis cine cardiac magnetic resonance images, and train multiple CNN segmentation models with different levels of race/sex imbalance. We find no significant bias in the sex experiment but significant bias in two separate race experiments, highlighting the need to consider adequate representation of different demographic groups in health datasets.
  arXiv  Detail & Related papers  (2022-09-04T14:32:00Z)
• Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification [57.53567756716656]
  We study the problem of developing debiased chest X-ray diagnosis models without knowing exactly the bias labels. We propose a novel algorithm, pseudo bias-balanced learning, which first captures and predicts per-sample bias labels. Our proposed method achieved consistent improvements over other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-18T11:02:18Z)
• "Just Drive": Colour Bias Mitigation for Semantic Segmentation in the Context of Urban Driving [8.147652597876862]
  Convolutional neural networks have been shown to rely on colour and texture rather than geometry. In this paper, we attempt to alleviate biases encountered by semantic segmentation models in urban driving scenes, via an iteratively trained unlearning algorithm.
  arXiv  Detail & Related papers  (2021-12-02T10:56:19Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Reading Race: AI Recognises Patient's Racial Identity In Medical Images [9.287449389763413]
  There is no known correlation for race on medical imaging that would be obvious to the human expert interpreting the images. Standard deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities.
  arXiv  Detail & Related papers  (2021-07-21T21:10:16Z)
• Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation [1.6386696247541932]
  "Fairness" in AI refers to assessing algorithms for potential bias based on demographic characteristics such as race and gender. Deep learning (DL) in cardiac MR segmentation has led to impressive results in recent years, but no work has yet investigated the fairness of such models. We find statistically significant differences in Dice performance between different racial groups.
  arXiv  Detail & Related papers  (2021-06-23T13:27:35Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)

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.