3D multi-scale deep convolutional neural networks for pulmonary nodule detection

TLDR

Deep learning has advanced computer‑aided pulmonary nodule detection, yet varying nodule sizes and visual similarity to vessels and shadows make accurate CT identification challenging. This study introduces two 3‑D multi‑scale deep convolutional neural networks—one for nodule candidate detection and another for false‑positive reduction—to improve detection accuracy. The candidate network employs a Res2SENet backbone with multi‑scale Res2Net modules and squeeze‑and‑excitation units, followed by a region‑proposal network enhanced with context‑enhancement and spatial‑attention modules, while the reduction network uses the same multi‑scale modules to classify candidates; the final score is a weighted average of both networks’ probabilities. On the LUNA16 dataset, the combined approach achieved superior nodule detection performance compared to existing methods.

Abstract

With the rapid development of big data and artificial intelligence technology, computer-aided pulmonary nodule detection based on deep learning has achieved some successes. However, the sizes of pulmonary nodules vary greatly, and the pulmonary nodules have visual similarity with structures such as blood vessels and shadows around pulmonary nodules, which make the quick and accurate detection of pulmonary nodules in CT image still a challenging task. In this paper, we propose two kinds of 3D multi-scale deep convolution neural networks for nodule candidate detection and false positive reduction respectively. Among them, the nodule candidate detection network consists of two parts: 1) the backbone network part Res2SENet, which is used to extract multi-scale feature information of pulmonary nodules, it is composed of the multi-scale Res2Net modules of multiple available receptive fields at a granular level and the squeeze-and-excitation units; 2) the detection part, which uses a region proposal network structure to determine region candidates, and introduces context enhancement module and spatial attention module to improve detection performance. The false positive reduction network, also composed of the multi-scale Res2Net modules and the squeeze-and-excitation units, can further classify the nodule candidates generated by the nodule candidate detection network and screen out the ground truth positive nodules. Finally, the prediction probability generated by the nodule candidate detection network is weighted average with the prediction probability generated by the false positive reduction network to obtain the final results. The experimental results on the publicly available LUNA16 dataset showed that the proposed method has a superior ability to detect pulmonary nodules in CT images.