• Korean Journal of Veterinary Service
• /
• v.22 no.2
• /
• pp.113-119
• /
• 1999

The most common cause of death is ostrich chick fading syndrome(OCFS), which is due to bacterial infection during artificial incubation and hatching. Six farmed ostrich chicks aged 3 and 10 days in Chonbuk province, were submitted to Chonbuk Livestock Development and Research Institute for necropsy, Clinically, birds showed hair loss, ocular exudate, lethargy, diarrhea, and subsequently died 3-5 days after onset of clinical signs. Grossly, umbilicus was enlarged. White-yellowish purulent nodules were scattered on the lung and the membrane of air-sac was thickened and had inflamed exudate on the surface in two chicks that died 3 days after hatching. In 10 days-old chick, intestine was shown rodding segmentally. Yolk sac was still retarded and its surface was partially hemorrahgic. The synovial fluid of the leg was yellowish. Microscopically, multifocal purulent exudates were scattered on the lung. Capillary microthrombi in the glomerulus were prominent and tubular epithelia were necrotic. Necrotic hepatocytes were scattered and intestine were congested. Microbiologically, Pseudomonas sp and/or E coli were isolated from air-sac, lung and/or liver. This case suggests that poor hygiene during artificial incubation, hatching or in the first week after hatching may cause high mortality of the ostrich chicks.

• Journal of Korea Artificial Intelligence Association
• /
• v.2 no.1
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• Journal of Biomedical Engineering Research
• /
• v.21 no.3 s.61
• /
• pp.311-320
• /
• 2000

In this paper a newly designed oxygenator module was used to perform the experiments for pressure drop and oxygen transport in order to evaluate the efficiency of the artificial lung. Also, distilled water. sodium sulfite solutions used in this experiment were evaluated for the performance of other artificial lungs. Substituted bloods have many advantages over whole blood in studying pressure drop and oxygen uptake. They are relatively inexpensive, and require fewer variables to be controlled. Furthermore, deoxygenation is not necessary when those solutions are used. In addition to these advantages. assays and interpretation of the experimental results are relatively easy. In the case of using the sodium sulfite solution having the same oxygen partial pressure as whole blood. the oxygen transfer rate of the sodium sulfite solution was basically same as that of whole blood. It was concluded in evaluating the function of artificial lungs that the sodium sulfite solution was suited for measuring oxygen transfer rate. In our module, artificial blood was flowed into the outside of hollow fiber membrane. The artificial lung created in this experiment showed that pressure drop was reduced to $1/3\~1/6$ of that compared to the inside-flow case.

• Journal of radiological science and technology
• /
• v.15 no.1
• /
• pp.99-105
• /
• 1992

Visual evaluation of rib shadow and lung marking during high voltage chest radiography. The Purpose of this study is to improvement of visual discrimination of pulmonary structures on the conventional chest radiogram. The author prepared an artificial lung using an acryl plate, 8 cm in thickness, which is nearly equivalent to human lung, and 0.6 cm thickness of an aluminum plate for an artificial rib, and 0.5 cm of an acryl plate as a pulmonary vessel as well. And they were used as objects for experimental radiograms. This study performed with gradual increasing densities of film bases in the sequences of densities of 0.6, 0.9, 1.1 and 1.3. We made two combinations of images after multiple and regular cuts, with width of 1 cm, of 4 radiograms at the above mentioned densities of film bases. One image consisted of alternative combination of radiograms taken at densities of 0.6 and 1.3, and the other did at 0.9 and 1.1. The latter image provided better visual perception of pulmonary structures than the former. Experimental radiograms were also taken with 60 kV and 120 kV respectively. After careful evaluation and comparison to images taken on varieties of different densities with combinations and kV, the author had a conclusion that it is advisable to use a high kV X-ray which makes rib shadow subtle, for better visual delineation of pulmonary structures behind ribcage, eventhough contrast of pulmonary structures are decreased at high kV radiogram.

• Biomedical Science Letters
• /
• v.20 no.3
• /
• pp.173-179
• /
• 2014

Asian sand dust is known to promote various respiratory symptoms or disorders. For the prevention of harmful health effects by Asian sand dust, the best strategy is known to avoid or reduce exposure to the Asian sand dust. Several studies have shown that Korean red ginseng (RG) has anti-inflammatory and anti-allergic effects. The study aimed to clarify the effect of Korean red ginseng intake on lung inflammation responses to artificial sand dust (ASD) similar to Asian sand dust. BALB/c mice were divided into five groups (n=12) of control (saline), ovalbumin (OVA), OVA with ASD, OVA plus RG with ASD, and OVA plus dexamethasone (DEXA) with ASD. Histopathologic evaluation of lung was conducted. Interleukin (IL)-5, IL-12, interferon (IFN)-${\gamma}$, IL-13, monocyte chemotactic protein (MCP)-1, and eotaxin within bronchoalveolar lavage (BAL) fluid were measured by ELISA. OVA+ASD group significantly increased concentrations of IL-5, IL-13, MCP-1, and eotaxin (P<0.01) compared to the control. OVA+ASD+RG group showed significant decreased levels of IL-2, IL-13, MCP-1 and eotaxin (P<0.01) compared with OVA+ASD. Between RG and DEXA treatment groups, there was no significant difference in all cytokines and chemokines. The inflammatory cells were significantly decreased in treatment groups with RG or DEXA compared to OVA+ASD group. This study suggests a beneficial effect of Korean RG administration in preventing inflammation of lung resulting from Asian sand dust.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• Journal of radiological science and technology
• /
• v.45 no.1
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

• Tuberculosis and Respiratory Diseases
• /
• v.40 no.4
• /
• pp.449-453
• /
• 1993

A 64-year-old male was admitted due to abruptly developed, severe dyspnea via local clinic. He had been a heavy smoker and alcoholic for a long time. Chest PA showed huge haziness in right upper lung field. Sputum culture for bacteriology was positive for Klebsiella pneumoniae. Immediately, appropriate antibiotics were administered and artificial ventilation was started. On 40th hospital day, simple chest roentgenogram taken due to sudden aggravated dyspnea showed marked hyperlucency in right upper lung field, suggestive of rupture of abscess cavity and resultant pneumothorax. At that time, chest tube was inserted but air leakage from the chest tube persisted. Chest CT scan taken after chest tube insertion showed the tube inserted into a thin-walled cavity in the above lesion. on 84th hospital day, right upper lobectomy with decortication was performed. Pathologically, cavittary lung abscess was diagnosed on the findings of partial re-epithelialization of ciliated columnar epithelium with severe pulmonary vascular occlusion and extensive fibrous pleural adhesions.

• Journal of Neurocritical Care
• /
• v.11 no.2
• /
• pp.63-70
• /
• 2018

Management of mechanical ventilation is essential for patients with neuro-critical illnesses who may also have impairment of airways, lungs, respiratory muscles, and respiratory drive. However, balancing the approach to mechanical ventilation in the intensive care unit (ICU) with the need to prevent additional lung and brain injury, is challenging to intensivists. Lung protective ventilation strategies should be modified and applied to neuro-critically ill patients to maintain normocapnia and proper positive end expiratory pressure in the setting of neurological closed monitoring. Understanding the various parameters and graphic waveforms of the mechanical ventilator can provide information about the respiratory target, including appropriate tidal volume, airway pressure, and synchrony between patient and ventilator, especially in patients with neurological dysfunction due to irregularity of spontaneous respiration. Several types of asynchrony occur during mechanical ventilation, including trigger, flow, and termination asynchrony. This review aims to present the basic interpretation of mechanical ventilator waveforms and utilization of waveforms in various clinical situations in the neuro-ICU.

• Journal of Sensor Science and Technology
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2023

Recently, the digital healthcare technologies including non-invasive diagnostics based on Internet of Things (IOT) are getting attention. Human exhaled breath contains a variety of volatile organic compounds (VOCs), which can provide information of malfunctions of the body and presence of a specific disease. Detection of VOCs in exhaled breath using gas sensors are easy to use, safe, and cost-effective. However, accurate diagnosis of diseases is challenging because changes in concentration of VOCs are extremely small and lots of body factors directly or indirectly influence to the conditions. To overcome the limitations, highly selective nanosensors and artificial intelligent electronic nose (E-nose) systems have been mainly researched in recent decades. This review provides brief reviews of the recent studies for diabetes and lung cancer diagnosis using nanosensors and E-nose systems.