Segmentation and classification of ground glass nodule on CT images

Abstract

The symptoms of lung cancer mainly manifest as lung nodules. The recognition and diagnosis of a ground glass nodule (GGN) are relatively difficult, and its image features are not easy to extract. To improve the accuracy of segmentation and invasive classification of GGN, a region adaptive Markov random field (MRF) model and a two‐channel integrated network based on densely connected convolutional neural networks (DenseNet) are developed in this paper. First, the lung parenchyma is segmented coarsely, and the corresponding contour is repaired. Afterwards, the fuzzy C‐means (FCM) clustering algorithm and a simple MRF model for the coarse segmentation of GGN are applied. Then, the region adaptive MRF model for the fine segmentation of GGN is used. Moreover, the two‐channel integrated network based on DenseNet is used for GGN invasive classification. Results show that the average value of the overlapping area ratio of the segmentation result to that obtained by one physician was 0.9144, and the accuracy of the proposed GGN invasive classification model, the specificity, sensitivity, and the area under curve were 92.553%, 87.500%, 97.826%, and 0.9715, respectively. The proposed segmentation method can segment GGN more accurately, and the corresponding GGN invasive classification model achieved satisfying classification performance.

Lung cancer detection by using probabilistic majority voting and optimization techniques

“…A region adaptive Markov random field model and DenseNet‐based two‐channel integrated network has been developed to increase the accuracy of ground glass nodule segmentation and invasive classification. When the accuracy of the proposed system is examined, the results demonstrate that it is equal to 92.553% 38 . A technique called the optimized hybrid of fuzzy c‐means and majority vote has been proposed to determine the missing values in the data set, and the accuracy of the proposed system is 93.7% 39 .…”

“…When the accuracy of the proposed system is examined, the results demonstrate that it is equal to 92.553%. 38 A technique called the optimized hybrid of fuzzy c-means and majority vote has been proposed to determine the missing values in the data set, and the accuracy of the proposed system is 93.7%. 39 A method has been presented to train the neural network on all whole-slide images using only slide-level diagnoses.…”

A novel lung nodule accurate detection of computerized tomography images based on convolutional neural network and probability graph model

“…In current, many endeavors have been made efforts of applying deep learning networks works on automatic telling lung nodules from other similar tissues of the lung such as weasand and vessel. Deep learning framework, typically the use of convolutional neural networks (CNNs), achieves significant improvement in lung nodules segmentation, 4 localization, 5 and classification 6 works. However, the detection accuracy of pulmonary nodules is still insufficient.…”