MD-NDNet: a multi-dimensional convolutional neural network for false-positive reduction in pulmonary nodule detection

• Published in: Physics in medicine & biology Vol. 65; no. 23; pp. 235053 - 235066
• Main Authors: Wu, Zhan, Ge, Rongjun, Shi, Gonglei, Zhang, Lu, Chen, Yang, Luo, Limin, Cao, Yu, Yu, Hengyong
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 07.12.2020
• Subjects: Computer Science; deep convolutional neural networks (DCNNs); Early Detection of Cancer - methods; False Positive Reactions; false-positive reduction; Humans; Imaging, Three-Dimensional - methods; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Medical Imaging; multi-dimensional nodule correlation features; Neural Networks, Computer; pulmonary nodule; Solitary Pulmonary Nodule - diagnostic imaging; Solitary Pulmonary Nodule - pathology; Tomography, X-Ray Computed - methods; multi-dimension nodule correlation features; deep convolutional neural networks (DCNNs); false positive reduction; Pulmonary nodule
• ISSN: 0031-9155; 1361-6560; 1361-6560
• DOI: 10.1088/1361-6560/aba87c

Pulmonary nodule false-positive reduction is of great significance for automated nodule detection in clinical diagnosis of low-dose computed tomography (LDCT) lung cancer screening. Due to individual intra-nodule variations and visual similarities between true nodules and false positives as soft tissues in LDCT images, the current clinical practices remain subject to shortcomings of potential high-risk and time-consumption issues. In this paper, we propose a multi-dimensional nodule detection network (MD-NDNet) for automatic nodule false-positive reduction using deep convolutional neural network (DCNNs). The underlying method collaboratively integrates multi-dimensional nodule information to complementarily and comprehensively extract nodule inter-plane volumetric correlation features using three-dimensional CNNs (3D CNNs) and spatial nodule correlation features from sagittal, coronal, and axial planes using two-dimensional CNNs (2D CNNs) with attention module. To incorporate different sizes and shapes of nodule candidates, a multi-scale ensemble strategy is employed for probability aggregation with weights. The proposed method is evaluated on the LUNA16 challenge dataset in ISBI 2016 with ten-fold cross-validation. Experiment results show that the proposed framework achieves classification performance with a CPM score of 0.9008. All of these indicate that our method enables an efficient, accurate and reliable pulmonary nodule detection for clinical diagnosis.