LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection

TL;DR

LSSANet introduces a novel slice grouping mechanism to efficiently capture long-range dependencies in 3D CT images, significantly improving pulmonary nodule detection accuracy while reducing computational costs.

Contribution

The paper proposes LSSG, a new non-local mechanism that enhances CNNs for pulmonary nodule detection by capturing long-range dependencies efficiently.

Findings

Outperforms existing methods on PN9 dataset

Effectively captures long-range dependencies across slices

Reduces computational cost of non-local operations

Abstract

Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection. However, existing CNN based pulmonary nodule detection methods lack the ability to capture long-range dependencies, which is vital for global information extraction. In computer vision tasks, non-local operations have been widely utilized, but the computational cost could be very high for 3D computed tomography (CT) images. To address this issue, we propose a long short slice-aware network (LSSANet) for the detection of pulmonary nodules. In particular, we develop a new non-local mechanism termed long short slice grouping (LSSG), which splits the compact non-local embeddings into a short-distance slice grouped one and a long-distance slice grouped counterpart. This not only reduces the computational burden, but also keeps long-range dependencies among any elements across slices and in the whole feature map. The proposed LSSG is easy-to-use and can be plugged into many pulmonary nodule detection networks. To verify the performance of LSSANet, we compare with several recently proposed and competitive detection approaches based on 2D/3D CNN. Promising evaluation results on the large-scale PN9 dataset demonstrate the effectiveness of our method. Code is at https://github.com/Ruixxxx/LSSANet.