The problem CORAY20 solves

While CT scans have been useful in helping providers detect COVID-19, clinicians are discouraged from using these medical images for coronavirus diagnosis.

Investigators from NIH and NVIDIA set out to develop and evaluate a deep learning algorithm to detect COVID-19 on chest CT using data from a globally diverse, multi-institutional dataset. The team obtained COVID-19 CT scans from four hospitals across China, Italy, and Japan, where there was a wide variety of clinical timing and practice for CT use in outbreak settings.

In total, we have used 2,724 scans from 2,619 patients in this study. The study included two models that we used in series to come up with the COVID-19 final classification model.

The first model was a segmentation model that was used to define the lung regions which were subsequently used by the classification model. Initially, the team developed two classification models – one utilizing the entire lung region with fixed input size (full 3D), and one utilizing the average score of multiple regions within each lung at fixed image resolution (hybrid 3D).

When distinguishing between COVID-19 and other conditions, the model achieved validation accuracy of 89.494 percent.

Challenges we ran into

Due to low GPU power, it took approx 10 hours to Trail the model.