World's first open source Convolutional Artificial Neural Network for Covid19 Diagnosis, from XRay images of lungs
share
It is public knowledge that a medical degree is not required to produce artificial intelligence based models that can contribute to healthcare in very important ways, including automated disease diagnosis. Nowadays, computer scientists work in concert with doctors and or medical information/doctor feedback, as seen for example in the popular online machine learning/artificial intelligence competition platform, Kaggle, rife with several hundreds of gigabytes of healthcare datasets and freely available albeit powerful “kernels” or artificial intelligence software code. Notably, with dollar values of up to hundreds of thousands of USD, healthcare Kaggle competition winners have been known to be outside of the medical degree world. Countries with aggressive/thorough testing, seem to face lower mortality rates (eg South Korea, <1% mortality rate) versus countries with terrible/barely existent testing/screening, (eg USA >3.5% mortality rate, close to the global mortality rate of~3.4% ). This paper serves to contribute to extensive testing efforts, to help minimize potentially exponential spread in newly affected regions, and otherwise aid in control even after wide-spread. On March 19, 2020, Epidemiologist Larry Brilliant, (who helped to stop smallpox), says we can beat the novel coronavirus—but first, we need lots more testing. As such, this paper concerns the application of the Convolutional Artificial Neural Network via machine learning library Tensorflow/Keras, on the task of Covid19 detection.
READ FULL TEXT
