TorchXRayVision: A library of chest X-ray datasets and models
This library addresses the need for standardized tools in medical imaging research, particularly for chest X-ray analysis, but it is incremental as it builds on existing datasets and models without introducing new methods.
The authors introduced TorchXRayVision, an open-source library that provides a unified interface and pre-processing for multiple public chest X-ray datasets, along with pre-trained deep learning models for classification and representation learning to serve as baselines or feature extractors.
TorchXRayVision is an open source software library for working with chest X-ray datasets and deep learning models. It provides a common interface and common pre-processing chain for a wide set of publicly available chest X-ray datasets. In addition, a number of classification and representation learning models with different architectures, trained on different data combinations, are available through the library to serve as baselines or feature extractors.