To demonstrate its potential, they trained an AI model to achieve an accuracy of 85% — accuracy they say could be improved with further model optimization.
Next, the researchers manually selected clinical COVID-19 scans by reading the captions.
The team concedes that because the data set is small, training models on it could lead to overfitting, when the model performs well on the training data but generalizes badly to testing data.
To mitigate this problem, they pretrained an AI system on the National Institute of Health’s ChestX-ray14 data set — a large collection of chest X-ray images — and fine-tuned it on the COVID-CT data set.
Concerningly, it’s unclear whether any of the researchers notified patients whose scans they scraped from the publicly available studies.

Comments to: Researchers release data set of CT scans from coronavirus patients

Your email address will not be published. Required fields are marked *

Attach images - Only PNG, JPG, JPEG and GIF are supported.

Login

Welcome to Typer

Brief and amiable onboarding is the first thing a new user sees in the theme.
Join Typer
Registration is closed.