asmelashteka/Afro-Chest-X-ray

Chest X-ray Imaging Dataset for Multiple Cardio-respiratory Diseases in Ethiopia # Afro Chest X-ray The **Chest X-ray Imaging Dataset for Multiple Cardio-respiratory Diseases in Ethiopia** (**Afro Chest X-ray** for short) is a project funded by the LacunaFund whose aim is to close the gap in health disparities by fostering interdisciplinary collaborations that create, expand, or aggregate labeled training and evaluation datasets. ## Description Cardio-respiratory diseases (cardiovascular and respiratory diseases) are recognized as serious, worldwide public health concerns that have remained among the leading causes of death globally. There are not many publicly available datasets from Africa making it difficult to determine whether tools and techniques developed in other geographies are as effective in our context. In this project, we propose to create a labeled chest X-ray dataset for multiple cardio respiratory diseases in Ethiopia. We will publish the dataset as open source. We believe this dataset will stimulate researchers and practitioners in Africa and beyond to push the limits of current methods to adapt them to the African context and build assistive technologies that could empower the scarce radiologists. ## Impact We envision this dataset to have an impact primarily in research and applications of the medical imaging domain. It will also be essential for researchers in natural language processes and entrepreneurs in medical imaging. Below we highlight some relevant research directions: **Bias in Machine learning:** This dataset will be useful to study the effect of selection bias in building machine learning models for X-ray images. There are massive datasets such as CheXpert gathered from different populations. The typical way to leverage models trained on big dadaist's in one population and apply them to another is through transfer learning. Our project will enable researchers to study the implications of selection bias in machine learning. For instance, how models trained on a big dataset from a different population and ada …