Fairness in Breast Cancer Diagnosis with Deep Learning

This paper aims to explore the effectiveness of machine learning models for the classification of breast cancer images trained with data from a demographic region and tested or used in a different demographic region. Artificial intelligence has the potential to be integrated into the imaging process to reduce workload and broaden screening audiences. However, artificial intelligence has sometimes been shown to demonstrate bias in medical applications. Most available breast cancer images are collected in North American, European, or East Asian countries, and there is limited data available from other regions. Bias between demographics could lead to some groups being under-diagnosed, resulting in worsened prognoses. In this work, a high-performance breast cancer classification model with AUC of up to 0.7415 on ultrasound images and 0.8920 on mammogram images has been developed. The model is trained and tested on a variety of datasets, some specifically collected in Ghana to compare with publicly available datasets from the UK, Portugal, and Poland. Experiments were conducted to determined any bias between different demographic regions. A significant decrease in performance was found in five of the six experiments conducted.