Integration of Convolutional Neural Networks for Pulmonary Nodule Malignancy Assessment in a Lung Cancer Classification Pipeline

TL;DR

This paper presents a method using 3D CNNs to assess pulmonary nodule malignancy and integrates it into an existing lung cancer detection pipeline, significantly improving its predictive performance.

Contribution

The novel contribution is the integration of a 3D CNN-based malignancy assessment into an automated lung cancer detection pipeline, enhancing its accuracy.

Findings

Adding malignancy probabilities improved F1 score by 14.7%.

Using transfer learning for malignancy model outperformed baseline by 11.8%.

Integration of predictive models enhances lung cancer prediction despite limited data.

Abstract

The early identification of malignant pulmonary nodules is critical for better lung cancer prognosis and less invasive chemo or radio therapies. Nodule malignancy assessment done by radiologists is extremely useful for planning a preventive intervention but is, unfortunately, a complex, time-consuming and error-prone task. This explains the lack of large datasets containing radiologists malignancy characterization of nodules. In this article, we propose to assess nodule malignancy through 3D convolutional neural networks and to integrate it in an automated end-to-end existing pipeline of lung cancer detection. For training and testing purposes we used independent subsets of the LIDC dataset. Adding the probabilities of nodules malignity in a baseline lung cancer pipeline improved its F1-weighted score by 14.7%, whereas integrating the malignancy model itself using transfer learning outperformed the baseline prediction by 11.8% of F1-weighted score. Despite the limited size of the lung cancer datasets, integrating predictive models of nodule malignancy improves prediction of lung cancer.