• Advances in nano research
• /
• v.12 no.2
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• Journal of Chest Surgery
• /
• v.10 no.1
• /
• pp.106-112
• /
• 1977

Transposition of the great arteries is one of the commonest forms of severe congenital heart disease and produces severe cyanosis threatening survival from the day of birth. Anatomical anomalies which the aorta arises from the infundibulum of the right ventricle and the pulmonary artery arises from the outflow tract of the left ventricle make the deranged circulation. Survival is possible only if additional anomalies are present which allow mixing of the pulmonary and systemic circulations. Preoperative diagnosis as TGA was taken on the 15 day old female via the preoperative examination and the right cordioangiography. As palliative treatment for cyanosis, Blalock-Hanlon operation was performed in this patient. The results were good as 54 mmHg changed from 27 mmHg of $PO_2$ in aorta, but sudden cardiac arrest was developed in postoperative 12 hours. In order to confirm the cause of death and the cardiac anomalies, autopsy was performed on the date of death. The diagnosis of the autopsy showed; [1] Transposition of the Great Arteries. [2] Patent Ductus Arteriosus. [3] Patent Foramen Ovale. [4] Ventricular Septal Defect, 2 Muscular Type. [5] Double Ureter, Right. [6] Artificial Atrial Septal Defect. [7] Total Collapse of the left lung and Intraparenchymal hemorrhage of right lung.

• 한국생물공학회:학술대회논문집
• /
• 2001.11a
• /
• pp.359-362
• /
• 2001

Traditionally, Cordyceps species have been used as a part of herbal medicine in Oriental countries, including Korea a for intemal health, vigorosity and to cure different diseases related to heart, lung etc. In the recent years, research on artificial fruiting of different Cordyceps species including C. militaris has been carried out in the world because of their medicinal value. Variationas well as instability occur during artificial fruiting. Instability observed in the in vitro fruiting of C. militaris is reported in the present study.

• Journal of Chest Surgery
• /
• v.35 no.12
• /
• pp.902-905
• /
• 2002

Pulmonary resection often leaves a pleural space problem that can cause prolonged air leaks. We describe a patient with lung cancer undergoing a right middle and lower lobectomy complicated by prolonged air leaks. He had a history of pulmonary tuberculosis and COPD. Artificial pneumoperitoneum was made by instillation of air via a small central vein catheter into the left lower quadrant on postoperative day(POD) 21. The air leak ceased on POD 23 and the chest tube was removed on POD 25.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.76-88
• /
• 2019

With advances in olfactory sensor technologies, the number of reports on various intelligent applications using multiple sensors (sensor arrays) are continuously increasing for fields such as medicine, environment, security, etc. For intelligent and point-of-care applications, it is not only important for the sensor technology to perform chemical or physical measurements rapidly and accurately, but it is also important for artificial intelligence technology to recognize and quantify specific chemicals or diagnose diseases such as lung cancer and diabetes. In particular, great advances in pattern recognition technologies, including deep learning algorithms, as well as sensor array technologies, are expected to enhance the potential of various types of olfactory intelligence applications, including early cancer diagnosis, drug seeking, military operations, and air pollution monitoring.

• Journal of Chest Surgery
• /
• v.21 no.1
• /
• pp.148-151
• /
• 1988

We experienced 2 years and 5 months old male patient with partial anomalous pulmonary venous return of the left lung into the coronary sinus without atrial septal defect. After incising the atrial septum and the wall between the left atrium and the coronary sinus, we made the roof of the coronary sinus and closed the artificial atrial septal defect, with using patch, then we could change the direction of the blood flow from the coronary sinus into the left atrium. The patient was discharged on the 13th postoperative day after uneventful postoperative course.

• Korean Chemical Engineering Research
• /
• v.49 no.2
• /
• pp.230-237
• /
• 2011

In this study, the characteristic of fluid flow in the new type lung assist devices has been established using computational fluid dynamics(CFD). For the modeling, the hollow fiber was ignored, and vertical types and tangential types were used for the model. Which was to analyze the flow characteristics of the fluid flow model when there exists 1 and 2 input/output ports, and when the input/output ports is located at the center of the cylinder and at the tangential direction with the cylinder wall. The modeling results showed that it was possible to eliminate no-flow region(stagnant layer) as shown in the vertical type when an inlet and an outlet were installed on the tangential direction of the cylinder as shown in the tangential type. Also, in the tangential type, vortex-type flow appeared as dominant, and it showed a complicated flow not deviated to one side. When the number of input/output was two, there was no deviated flow, and complicated flows were generated all across the tube. From the test result, it was found that input/output of flow was tangential type and complicated flows with no stagnant layer would be generated when there are two inputs/outputs, respectively.

• Mycobiology
• /
• v.51 no.2
• /
• pp.94-108
• /
• 2023

Termitomyces sp. that grow in symbiosis with fungus-farming Termites have medicinal properties. However, they are rare in nature, and their artificial culture is challenging. The expression of AXL receptor tyrosine kinase and immune checkpoint molecules favor the growth of cancer cells. The study evaluated the optimal conditions for the artificial culture of Termitomyces and their inhibitory activity on AXL and immune checkpoint molecules in lung adenocarcinoma and melanoma cell lines. The culture of 45 strains of Termitomyces was compared. Five strains with marked growth rates were selected. Four of the selected strains form a single cluster by sequence analysis. The mycelium of 4 selected strains produces more fungal mass in potato dextrose broth than in a mixed media. The bark was the most appropriate solid substrate for Termitomyces mycelia culture. The mycelium of all five selected strains showed a higher growth rate under normal CO₂ conditions. The culture broth, methanol, and ethyl acetate of one selected strain (T-120) inhibited the mRNA relative expression of AXL receptor tyrosine kinase and immune checkpoint molecules in cancer cell lines. Overall, these results suggest the potential usefulness of Termitomyces extracts as a coadjuvant therapy in malignant diseases.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.165-170
• /
• 2004

The purpose of this work was to assess and quantify the beneficial effects of long-term gas exchange, at varying frequencies, for the development of a vibrating intravascular lung assistance device (VIVLAD), for patients suffering from acute respiratory distress syndrome (ARDS). The experimental design and procedure have been applied to the construction of a new device for assessing the effectiveness of membrane vibrations. An analytical solution has been developed for the hydrodynamics of flow through a bundle of sinusoidally vibrated hollow fibers, with the intention of gaining insight into how wall vibrations might enhance the performance of the VIVLAD. As a result, the maximum oxygen transfer rate was reached at the maximum amplitude and through the transfer of vibrations to the hollow fiber membranes. The device was excited by a frequency band of 7Hz at various water flow rates, as this frequency was the 2nd mode resonance frequency of the flexible beam. 675 hollow fiber membranes were also bundled, within the blood flow, into the device.