Publications by authors named "Ganhua Zeng"

3 Publications

  • Page 1 of 1

Application of Deep Learning in Lung Cancer Imaging Diagnosis.

J Healthc Eng 2022 3;2022:6107940. Epub 2022 Jan 3.

Thoracic Surgery Department, GanZhou People's Hospital, Ganzhou 341000, China.

Lung cancer is one of the malignant tumors with the highest fatality rate and nearest to our lives. It poses a great threat to human health and it mainly occurs in smokers. In our country, with the acceleration of industrialization, environmental pollution, and population aging, the cancer burden of lung cancer is increasing day by day. In the diagnosis of lung cancer, Computed Tomography (CT) images are a fairly common visualization tool. CT images visualize all tissues based on the absorption of X-rays. The diseased parts of the lung are collectively referred to as pulmonary nodules, the shape of nodules is different, and the risk of cancer will vary with the shape of nodules. Computer-aided diagnosis (CAD) is a very suitable method to solve this problem because the computer vision model can quickly scan every part of the CT image of the same quality for analysis and will not be affected by fatigue and emotion. The latest advances in deep learning enable computer vision models to help doctors diagnose various diseases, and in some cases, models have shown greater competitiveness than doctors. Based on the opportunity of technological development, the application of computer vision in medical imaging diagnosis of diseases has important research significance and value. In this paper, we have used a deep learning-based model on CT images of lung cancer and verified its effectiveness in the timely and accurate prediction of lungs disease. The proposed model has three parts: (i) detection of lung nodules, (ii) False Positive Reduction of the detected nodules to filter out "false nodules," and (iii) classification of benign and malignant lung nodules. Furthermore, different network structures and loss functions were designed and realized at different stages. Additionally, to fine-tune the proposed deep learning-based mode and improve its accuracy in the detection Lung Nodule Detection, Noudule-Net, which is a detection network structure that combines U-Net and RPN, is proposed. Experimental observations have verified that the proposed scheme has exceptionally improved the expected accuracy and precision ratio of the underlined disease.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2022/6107940DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749371PMC
January 2022

A study of clinical implementation of ventricular septal defect closure using three transthoracic approaches.

Am J Transl Res 2021 15;13(10):11833-11841. Epub 2021 Oct 15.

Department of Cardiac Surgery, Ganzhou People's Hospital Ganzhou 341000, Jiangxi Province, China.

Objective: To investigate the clinical implementation of ventricular septal defect closure using the three transthoracic approaches.

Methods: A total of 70 children with septal defects admitted to our hospital from January 2017 to December 2020 were selected as the study subjects. Among them, 10 children with the left thorax-right ventricle-left ventricle approach were assigned to Group A, 8 children with the right thorax-atrium dextrum-right ventricle-left ventricle approach were assigned to Group B, and 52 children with the subxyphoid-right ventricle-left ventricle approach were assigned to Group C. The surgical indices were recorded, the success rates of closure and cardiopulmonary function indices were compared, electrocardiogram (ECG), echocardiogram and X-ray film were investigated at 1, 3 and 12 months after surgery, and the incidence of complications was recorded.

Results: There was no statistically significant difference in the success rate of closure among the three groups ( > 0.05). The duration of intracardiac operations in Groups A and C was remarkably shorter than that in Group B, and the duration of skin incision and suture and hospital stay in Groups A and B were noticeably shorter than those in Group C ( < 0.05). After surgery, there was statistically significant difference in the contents of creatine kinase MB (CK-MB) isoenzyme, lactate dehydrogenase (LDH), serum malondialdehyde (MDA) and superoxide dismutase (SOD) among the three groups ( > 0.05). Airway resistance (Raw), oxygenation index (OI), and alveolar-arterial oxygen gradient (AaDO) indicated that the postoperative pulmonary function in Group C was more effectively protected. There was no statistically significant difference in the incidence of complications among the three groups ( > 0.05).

Conclusion: Ventricular septal defect closure using the three transthoracic approaches exhibited a high success rate and a high safety profile.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8581886PMC
October 2021

Analysis of poor prognostic factors of cerebral nerve after deep hypothermic circulatory arrest in patients with type A aortic dissection.

Am J Transl Res 2021 15;13(9):10599-10607. Epub 2021 Sep 15.

Department of Cardiac Surgery, Ganzhou People's Hospital Ganzhou 341000, Jiangxi Province, China.

Objective: To investigate the influences of deep hypothermic circulatory arrest (DHCA) on postoperative cranial nerve function in patients undergoing surgery for type A aortic dissection.

Methods: A total of 100 patients undergoing DHCA during the surgery for type A aortic dissection in our hospital were selected as the study subjects. After surgery, 32 patients with neurological complications were assigned to Group A, and 68 patients without neurological complications were assigned to Group B. The clinical outcomes were compared between the two groups, and the risk factors of postoperative neurological complications were analyzed by univariate and multivariate logistic regression analysis.

Results: During the surgery, patients underwent cerebral perfusion at 5 min and 10 min during DHCA had remarkably decreased cerebral oxygen saturation (rSO2) and VmMCA than those before anesthesia induction (<0.05). After recovery of CPB, rSO2 and mean velocity in middle cerebral artery (VmMCA) recovered to the preoperative levels. The correlation analysis revealed a positive correlation between rSO2 and VmMCA (<0.05). The univariate analysis suggested that the history of hypertension, hydropericardium, surgical duration, duration of cardiopulmonary bypass (CPB), aortic occlusion, ICU, and ventilator-assisted respiration, and hypoxemia significantly affected postoperative cranial nerve function (<0.05). The logistic multivariate regression analysis demonstrated that the duration of CPB and aortic occlusion and hypoxemia were independent risk factors for postoperative cranial nerve dysfunction (<0.05).

Conclusion: There were noticeable changes in hemodynamic and blood oxygen parameters in patients with type A aortic dissection undergoing DHCA during the perioperative period. The long duration of CPB and aortic occlusion and preoperative hypoxemia are the independent risk factors leading to postoperative impaired cranial nerve function.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8507019PMC
September 2021
-->