Computed Tomography Image under Convolutional Neural Network Deep Learning Algorithm in Pulmonary Nodule Detection and Lung Function Examination

Abstract

The objective of this study was to perform segmentation and extraction of CT images of pulmonary nodules based on convolutional neural networks (CNNs). The Mask-RCNN algorithm model is a typical end-to-end image segmentation model, which uses the R-FCN structure for nodule detection. The effect of applying the two algorithm models to the computed tomography (CT) diagnosis of pulmonary nodules was analyzed, and different indexes of pulmonary nodule CT images in lung function examination after algorithm optimization were compared. A total of 56 patients diagnosed with pulmonary nodules by surgery or puncture were taken as the research objects. Based on the Mask-RCNN algorithm, a model for CT image segmentation processing of pulmonary nodules was proposed. Subsequently, the 3D Faster-RCNN model was used to label the nodules in the pulmonary nodules. The experimental results showed that the trained Mask-RCNN algorithm model can effectively complete the segmentation task of lung CT images, but there was a little jitter at the boundary. The speed of R-FCN algorithm for nodular detection was 0.172 seconds/picture, and the accuracy was 88.9%. CT scans were performed on the 56 patients based on a deep learning algorithm. The results showed that 30 cases of malignant pulmonary nodules were confirmed, and the diagnostic accuracy was 93.75%. There were 22 benign lesions, the diagnostic accuracy was 91.67%, and the overall diagnostic accuracy was 92.85%. This study effectively improved the diagnostic efficiency of CT images of pulmonary nodules, and the accuracy of CT images in the diagnosis of pulmonary nodules was analyzed and evaluated. It provided theoretical support for the follow-up diagnosis of pulmonary nodules and the treatment of lung cancer. It also significantly improved the diagnostic effect and detection efficiency of pulmonary nodules.

Figure 1

Schematic diagram of Mask-RCNN algorithm segmentation.

Figure 2

Schematic diagram of R-FCN model structure.

Figure 3

Location-sensitive feature map of R-FCN.

Figure 4

Comparison of the segmentation effect of Mask-RCNN algorithm on lung CT images (the box represents the automatic selection and labeling of lung parenchyma by Mask-RCNN algorithm, and the dotted line represents the further automatic segmentation of lung parenchyma).

Figure 5

Comparison of the detection effect of R-FCN algorithm on CT images of pulmonary nodules (the box represents the automatic segmentation labeling of pulmonary nodules by R-FCN algorithm).

Figure 6

Comparison of the diagnostic accuracy of CT and MRI on CT images of pulmonary nodules.

Figure 7

Enhanced peak CT scan parameters of different types of pulmonary nodules.

Figure 8

CT scan parameters of the ratio of aortic enhancement value of different pulmonary nodules.