Multi-Scale Gradual Integration CNN for False Positive Reduction in Pulmonary Nodule Detection

TL;DR

This paper introduces a novel multi-scale CNN architecture for reducing false positives in pulmonary nodule detection on CT scans, significantly improving detection accuracy over existing methods.

Contribution

The paper proposes a multi-scale, gradually integrated CNN that effectively captures contextual information for false positive reduction in pulmonary nodule detection.

Findings

Achieved state-of-the-art CPM scores of 0.908 and 0.942 on LUNA16 datasets.

Outperformed existing methods by a large margin in false positive reduction.

Demonstrated the effectiveness of multi-scale and gradual integration strategies.

Abstract

Lung cancer is a global and dangerous disease, and its early detection is crucial to reducing the risks of mortality. In this regard, it has been of great interest in developing a computer-aided system for pulmonary nodules detection as early as possible on thoracic CT scans. In general, a nodule detection system involves two steps: (i) candidate nodule detection at a high sensitivity, which captures many false positives and (ii) false positive reduction from candidates. However, due to the high variation of nodule morphological characteristics and the possibility of mistaking them for neighboring organs, candidate nodule detection remains a challenge. In this study, we propose a novel Multi-scale Gradual Integration Convolutional Neural Network (MGI-CNN), designed with three main strategies: (1) to use multi-scale inputs with different levels of contextual information, (2) to use abstract information inherent in different input scales with gradual integration, and (3) to learn multi-stream feature integration in an end-to-end manner. To verify the efficacy of the proposed network, we conducted exhaustive experiments on the LUNA16 challenge datasets by comparing the performance of the proposed method with state-of-the-art methods in the literature. On two candidate subsets of the LUNA16 dataset, i.e., V1 and V2, our method achieved an average CPM of 0.908 (V1) and 0.942 (V2), outperforming comparable methods by a large margin. Our MGI-CNN is implemented in Python using TensorFlow and the source code is available from 'https://github.com/ku-milab/MGICNN.'