Lung nodule classification on CT scan patches using 3D convolutional neural networks

TL;DR

This paper presents a robust 3D CNN-based system for lung nodule classification on CT scans, incorporating advanced cropping, filtering, and augmentation techniques to improve accuracy and efficiency, achieving state-of-the-art results.

Contribution

Introduces three methodological improvements for lung nodule classification, enhancing robustness and performance across diverse clinical data.

Findings

Achieved Macro ROC AUC of 0.9176 and F1-score of 0.7658 for multiclass classification.

Reached Binary ROC AUC of 0.9383 and F1-score of 0.8668 for binary classification.

Outperformed previous approaches on the LIDC-IDRI dataset.

Abstract

Lung cancer remains one of the most common and deadliest forms of cancer worldwide. The likelihood of successful treatment depends strongly on the stage at which the disease is diagnosed. Therefore, early detection of lung cancer represents a critical medical challenge. However, this task poses significant difficulties for thoracic radiologists due to the large number of studies to review, the presence of multiple nodules within the lungs, and the small size of many nodules, which complicates visual assessment. Consequently, the development of automated systems that incorporate highly accurate and computationally efficient lung nodule detection and classification modules is essential. This study introduces three methodological improvements for lung nodule classification: (1) an advanced CT scan cropping strategy that focuses the model on the target nodule while reducing computational cost; (2) target filtering techniques for removing noisy labels; (3) novel augmentation methods to improve model robustness. The integration of these techniques enables the development of a robust classification subsystem within a comprehensive Clinical Decision Support System for lung cancer detection, capable of operating across diverse acquisition protocols, scanner types, and upstream models (segmentation or detection). The multiclass model achieved a Macro ROC AUC of 0.9176 and a Macro F1-score of 0.7658, while the binary model reached a Binary ROC AUC of 0.9383 and a Binary F1-score of 0.8668 on the LIDC-IDRI dataset. These results outperform several previously reported approaches and demonstrate state-of-the-art performance for this task.