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

Shangjie Wu,Enas Abdulhay,Jing Li,Jian Huang,Chan Zhang

doi:10.1155/2021/3417285

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.

Highlights

Pulmonary nodules are considered to be a multi-system and multi-organ granulomatous disease with unknown etiology at present, which often occurs in the lungs, bilateral hilar lymph nodes, eyes, skin, and other organs, and the incidence in the chest is as high as 80%–90% [1]
Erefore, a model for computed tomography (CT) image analysis of pulmonary nodules was proposed based on convolutional neural networks (CNNs) deep learning technology, and a comparison of different indexes of lung function examination of pulmonary nodules CT images was conducted after the optimization of the algorithm. e results of this study were intended to provide reference for the improvement of clinical diagnosis and treatment of patients with pulmonary nodules
Image Segmentation Results Based on Mask-RCNN Algorithm Model. e deep learning framework for algorithm models was TensorFlow. is learning framework has a high degree of flexibility and strong portability, which supports multi-language and automatic differentiation

Summary

Introduction

Pulmonary nodules are considered to be a multi-system and multi-organ granulomatous disease with unknown etiology at present, which often occurs in the lungs, bilateral hilar lymph nodes, eyes, skin, and other organs, and the incidence in the chest is as high as 80%–90% [1]. Lung cancer has generally entered the middle and late stages, and the best treatment period has been missed At this time, the optimal treatment period has been missed, so the early diagnosis of lung cancer is extremely important. If early pulmonary nodules are diagnosed and treated in advance and its early symptoms and related indicators are studied, it can effectively improve the early diagnosis rate and survival rate of lung cancer patients. E second is adopting the algorithm to automate the detection of pulmonary nodules in CT images, which can effectively improve the diagnostic efficiency of radiologists and improve the poor diagnostic effect caused by subjective differences. Erefore, a model for CT image analysis of pulmonary nodules was proposed based on CNN deep learning technology, and a comparison of different indexes of lung function examination of pulmonary nodules CT images was conducted after the optimization of the algorithm. e results of this study were intended to provide reference for the improvement of clinical diagnosis and treatment of patients with pulmonary nodules

Methods

Results

85 Max pool with a 2 by 2 filter and stride 2