Integrating Feature and Image Pyramid: A Lung Nodule Detector Learned in Curriculum Fashion

TL;DR

This paper introduces a novel lung nodule detection method combining feature and image pyramids with curriculum training, improving sensitivity and reducing training time on CT images.

Contribution

It proposes a multi-scale feature integration approach with a dynamic sampling curriculum to enhance detection accuracy and training efficiency in lung nodule analysis.

Findings

Outperforms previous state-of-the-art methods.

Halves training time on LUNA16 dataset.

Achieves higher recall for small nodules.

Abstract

Lung nodules suffer large variation in size and appearance in CT images. Nodules less than 10mm can easily lose information after down-sampling in convolutional neural networks, which results in low sensitivity. In this paper, a combination of 3D image and feature pyramid is exploited to integrate lower-level texture features with high-level semantic features, thus leading to a higher recall. However, 3D operations are time and memory consuming, which aggravates the situation with the explosive growth of medical images. To tackle this problem, we propose a general curriculum training strategy to speed up training. An dynamic sampling method is designed to pick up partial samples which give the best contribution to network training, thus leading to much less time consuming. In experiments, we demonstrate that the proposed network outperforms previous state-of-the-art methods. Meanwhile, our sampling strategy halves the training time of the proposal network on LUNA16.