Deep Learning-Based CT Images in Pulmonary Function Assessment of Patients Who Underwent Laparoscopic Surgery under Guidance of Electrical Impedance Tomography

Chen Zhu,Bin Wang,Lei Li,Tianzuo Li,Gustavo Ramirez

doi:10.1155/2021/9889488

Abstract

This research aimed to study the application of CT images based on deep learning in pulmonary function assessment of patients who underwent laparoscopic surgery under the guidance of electrical impedance tomography (EIT). Sixty patients undergoing laparoscopic surgery were taken as the research subjects, who were randomly labelled as control group and experimental group. Based on deep learning, the empty convolution-combined fully convolutional neural network optimization algorithm (ECFCNN) was proposed, which was adopted to evaluate the pulmonary function of 60 patients and was compared with convolutional neural network (CNN) algorithm. The clarity of the edge contour of the image segmented by ECFCNN was better than that segmented by CNN. Average arterial pressure (MAP) and heart rate (HR) were recorded before induction (T1), 10 min before pneumoperitoneum (T2), 10 min after pneumoperitoneum (T3), 10 min before extubation (T4), and 10 min after extubation (T5), respectively. Oxygenation index (PaO2/FiO2), alveolary-arterial partial pressure of oxygen (A-ADO2), and respiratory index (RI) were recorded. The sharpness of the segmentation image edge contour of the algorithm model in this study was higher than that of the convolutional neural network. Compared with T1, T2-T4 MAP in 2 groups was decreased ( P < 0.05 ). Compared with T1, T2-T5 HR was significantly decreased ( P < 0.05 ). Compared with T2, T5 PaO2/FiO2 in control group was significantly decreased ( P < 0.05 ). Compared with the control group, T5 A-aDO2 was decreased ( P < 0.05 ). To sum up, EIT-guided lung protective ventilation can assess the pulmonary function of patients who underwent laparoscopic surgery, reduce the incidence of atelectasis, and improve postoperative lung oxygenation.

Highlights

In recent years, with the continuous progress of surgical operations, the requirements for the size of the wound, the degree of pain, and the prognosis of the operation have become higher and higher
ECFCNN algorithm was proposed, which was compared with convolutional neural network (CNN) algorithm and applied to the evaluation of pulmonary function of 60 patients undergoing laparoscopic surgery. e loss function and Dice coefficient of the ECFCNN model and the CNN model were compared in Figure 2. e loss of the CNN model was 0.0523 and the Dice coefficient was 0.9635, while the loss of the ECFCNN model was 0.0469 and the Dice coefficient was 0.9712. e loss function and Dice coefficient of ECFCNN model were obviously better than those of CNN model. e segmented images of the ECFCNN model can describe the overall outline of the lung
General Statistics of Patients Undergoing Laparoscopic Surgery. e two groups of patients undergoing laparoscopic surgery were compared in terms of gender, age, and weight, and no considerable difference was found (P > 0.05). e operation time, anesthesia time, and pneumoperitoneum time were compared; the difference was not considerable (P > 0.05), as illustrated in Figure 3. erefore, there was no evident difference in the general information of the two groups of patients, and comparative experiments can be carried out

Summary

Introduction

With the continuous progress of surgical operations, the requirements for the size of the wound, the degree of pain, and the prognosis of the operation have become higher and higher. Laparoscopic surgery has the advantages of small wounds, low blood loss, short recovery time, and small recovery scars. At present, it is widely utilized clinically [1]. E clinical routine examination items are mainly lung volume measurement, pulmonary ventilation function measurement, and arterial blood gas analysis [3]. Whether it is a patient with healthy pulmonary function or a patient with impaired pulmonary function, EIT can clearly image the blood flow of the lungs, and the results match with CT scans [4]. It can organize large amounts of data in an orderly manner, extract image features, and efficiently deal with intricate problems [8]

Methods

Results

Conclusion