# Intrinsic Bias Identification on Medical Image Datasets

arXiv: https://arxiv.org/abs/2203.12872 · HTML: https://mlsanity.com/paper/2203.12872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [A Survey on Bias in Visual Datasets](https://mlsanity.com/paper/2107.07919/) (2021)
- [Shape-Texture Debiased Neural Network Training](https://mlsanity.com/paper/2010.05981/) (2020)
- [iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making](https://mlsanity.com/paper/1806.01059/) (2018)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [Debiasing Skin Lesion Datasets and Models? Not So Fast](https://mlsanity.com/paper/2004.11457/) (2020)
- [Does enhanced shape bias improve neural network robustness to common corruptions?](https://mlsanity.com/paper/2104.09789/) (2021)
- [Fast GPU-Enabled Color Normalization for Digital Pathology](https://mlsanity.com/paper/1901.03088/) (2019)

## Abstract (arXiv)

Machine learning based medical image analysis highly depends on datasets. Biases in the dataset can be learned by the model and degrade the generalizability of the applications. There are studies on debiased models. However, scientists and practitioners are difficult to identify implicit biases in the datasets, which causes lack of reliable unbias test datasets to valid models. To tackle this issue, we first define the data intrinsic bias attribute, and then propose a novel bias identification framework for medical image datasets. The framework contains two major components, KlotskiNet and Bias Discriminant Direction Analysis(bdda), where KlostkiNet is to build the mapping which makes backgrounds to distinguish positive and negative samples and bdda provides a theoretical solution on determining bias attributes. Experimental results on three datasets show the effectiveness of the bias attributes discovered by the framework.