Artificial Intelligence Algorithm-Based Feature Extraction of Computed Tomography Images and Analysis of Benign and Malignant Pulmonary Nodules

Abstract

This study was aimed to explore the effect of CT image feature extraction of pulmonary nodules based on an artificial intelligence algorithm and the image performance of benign and malignant pulmonary nodules. In this study, the CT images of pulmonary nodules were collected as the research object, and the lung nodule feature extraction model based on expectation maximization (EM) was used to extract the image features. The Dice similarity coefficient, accuracy, benign and malignant nodule edges, internal signs, and adjacent structures were compared and analyzed to obtain the extraction effect of this feature extraction model and the image performance of benign and malignant pulmonary nodules. The results showed that the detection sensitivity of pulmonary nodules in this model was 0.955, and the pulmonary nodules and blood vessels were well preserved in the image. The probability of burr sign detection in the malignant group was 73.09% and that in the benign group was 8.41%. The difference was statistically significant (P < 0.05). The probability of malignant component leaf sign (69.96%) was higher than that of a benign component leaf sign (0), and the difference was statistically significant (P < 0.05). The probability of cavitation signs in the malignant group (59.19%) was higher than that in the benign group (3.74%), and the probability of blood vessel collection signs in the malignant group (74.89%) was higher than that in the benign group (11.21%), with statistical significance (P < 0.05). The probability of the pleural traction sign in the malignant group was 17.49% higher than that in the benign group (4.67%), and the difference was statistically significant (P < 0.05). In summary, the feature extraction effect of CT images based on the EM algorithm was ideal. Imaging findings, such as the burr sign, lobulation sign, vacuole sign, vascular bundle sign, and pleural traction sign, can be used as indicators to distinguish benign and malignant nodules.

Figure 1

Technology roadmap.

Figure 2

Effect drawings of lung parenchyma image segmentation at each stage. (a) CT image of lung; (b) binarized lung CT image; (c) thoracic image; (d) chest cavity image; (e) binarized lung parenchyma image; (f) pulmonary parenchyma mask; (g) lung parenchyma image; (h) initial contour of lung nodules.

Figure 3

Comparison of ROC curve and ROC curve scores of four types of pulmonary nodule detection models. (a) ROC curve of the four types of models; (b) corresponding ROC curve score. a: ETROCAD model; b: M5LCAD model; c: ZNET model; d: model based on ES algorithm.

Figure 4

Comparison of segmentation effects of different segmentation methods. (a) Original nodule image; (b) gold standard image; (c) LBF model image; (d) ACM model image; (e) EM model image.

Figure 5

DSC curves of the three segmentation methods.

Figure 6

CT images of benign and malignant pulmonary nodules. The marked red areas in (a), (b), and (c) indicated benign nodules; the marked red areas in (d), (e), and (f) diagrams indicated malignant nodules.

Figure 7

Proportion of benign and malignant pulmonary nodules. A, B, C, D, E, and F represent the burr sign, lobulation sign, vacuole sign, bronchial inflation sign, vascular set number sign, and pleural traction sign, respectively. ^∗ Compared with benign group, P < 0.05.