External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules

What is it about?

Estimation of the risk of malignancy in pulmonary nodules detected by computed tomography is central in clinical management. The use of artificial intelligence (AI) offers an opportunity to improve risk prediction. A new machine learning derive AI algorithm, the Lung Cancer Prediction Convolutional Neural Network (LCP-CNN) was able to outperform the best available risk prediction model by using radiomic data alone. It allows a larger proportion of benign nodules to be identified without missing cancers than the Brock model. This has the potential to substantially reduce the proportion of surveillance CT scans required and thus save significant resources.

Featured Image