Automatic pulmonary ground‐glass opacity nodules detection and classification based on 3D neural network

Abstract

Pulmonary ground-glass opacity (GGO) nodules are more likely to be malignant compared with solid solitary nodules. Due to indistinct boundaries of GGO nodules, the detection and diagnosis are challenging for doctors. Therefore, designing an automatic GGO nodule detection and classification scheme is significantly essential. Methods: In this paper, we proposed a two-stage 3D GGO nodule detection and classification framework. First, we used a pretrained 3D U-Net to extract lung parenchyma. Second, we adapted the architecture of Mask region-based convolutional neural networks (RCNN) to handle 3D medical images. The 3D model was then applied to detect the locations of GGO nodules and classify lesions (benign or malignant). The class-balanced loss function was also used to balance the number of benign and malignant lesions. Finally, we employed a novel false positive elimination scheme called the feature-based weighted clustering (FWC) to promote the detection accuracy further. Results:The experiments were conducted based on fivefold cross-validation with the imbalanced data set. Experimental results showed that the mean average precision could keep a high level (0.5182) in the phase of detection. Meanwhile, the false positive rate was effectively controlled, and the competition performance metric (CPM) reached 0.817 benefited from the FWC algorithm. The comparative statistical analyses with other deep learning methods also proved the effectiveness of our proposed method. Conclusions: We put forward an automatic pulmonary GGO nodules detection and classification framework based on deep learning. The proposed method locate and classify nodules accurately, which could be an effective tool to help doctors in clinical diagnoses.

Research in the application of artificial intelligence to lung cancer diagnosis

“…The model effectively learned the spatial heterogeneities of pulmonary nodules and solved the multi-view discrepancy problem; it will provide substantial assistance to physicians. Ma et al ( 20 ) developed an improved 3D Mask regional CNN for the detection and classification of pulmonary GGNs using a pre-trained 3D U-Net to extract the lung parenchyma, a 3D target detection network to locate the lesion and determine its malignancy status, and a feature-based weighted clustering algorithm to remove false images. The mean detection accuracy was high, and the “false alarm” rate was low.…”

A transparent artificial intelligence framework to assess lung disease in pulmonary hypertension

“…Deep learning approaches are used to quantify pulmonary ground-glass opacity nodules detection 5 , and emphysema regions using High-Resolution Computed Tomography scans of patients with chronic obstructive pulmonary disease 6 . Moreover, deep learning tries to automate the detection of PH existence or absence 7 , 8 and predict elevated pulmonary artery pressure 9 .…”

A hybrid machine learning technique for early prediction of lung nodules from medical images using a learning‐based neural network classifier

“…6 Lung nodules are classified as solid, partially solid, or ground glass density nodules. 7,8 Solid nodules are high gray value nodules that cannot be separated from surrounding tissues 9 ; ground glass density nodules are low gray value nodules that can be recognized from surrounding tissues. 10 Solid nodules comprise solid soft tissue of varying densities.…”