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.
Project Summary: To build a public open dataset of chest X-ray and CT images of patients which are positive or suspected of COVID-19 or other viral and bacterial pneumonias (MERS, SARS, and ARDS.). Data will be collected from public sources as well as through indirect collection from hospitals and physicians. All images and data will be released publicly in this GitHub repo.
This is a web based (but locally run) prototype system for diagnosing chest X-ray images. The patient data remains on your computer and all computation occurs in your browser.
We discuss how gene-gene interaction graphs (same pathway, protein-protein, co-expression, or research paper text association) can be used to impose a bias on a deep neural network model similar to the spatial bias imposed by convolutions on an image. We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used.
We show that cross domain image-to-image translation can be subject to bias due to matching the data distribution of the target domain. We specifically show results when using conditional GAN and CycleGAN.
This work develops a method to count heterogeneous objects, such as
cell nuclei or sealions. We develop a deep learning based system to
that takes as input an image and returns a count of the objects inside
and justification for the prediction in the form of weak localization.