• Journal of Digital Convergence
• /
• v.16 no.2
• /
• pp.19-26
• /
• 2018

We proposed a numerical calculation of the proportion of necrotic cells in pulmonary segmentation, pulmonary vessel segmentation lung disease site for diagnosis of lung disease from chest CT images. The first step is to separate the lungs and bronchi by applying a three-dimensional labeling technique from a chest CT image and a three-dimensional region growing method. The second step is to divide the pulmonary vessels by applying the rate of change using the first order polynomial regression, perform noise reduction, and divide the final pulmonary vessels. The third step is to find a disease prediction factor in a two-step image and calculate the proportion of necrotic cells.

• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.77-82
• /
• 2012

We carried out study to prove effectiveness as stimulating corresponding points to lung in hand to experiment applied analysis parameters for image and audio signals in this paper. To this end we collected facial image and voice before and after stimulating corresponding points to lung in hand to a male 20s 25 people. In addition, we analyzed change color, voice energy and speaking rate of right cheek area corresponding points to lung to suggest the theory of the Oriental medicine diagnosis based on data collected. As a result, after performing hand acupuncture, L value of right cheek area decreased average 2.33 and a value b value increased 0.76, 0.97 on average. In addition, size of voice energy increased average 0.42, speaking rate decreased average 0.07. In other words, effect of lung function was improved using hand acupuncture corresponding points to lung.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.373-381
• /
• 2021

In this paper, we propose a classification model based on convolutional neural network(CNN) for predicting 2-year recurrence in non-small cell lung cancer(NSCLC) patients using preoperative chest CT images. Based on the region of interest(ROI) defined as the tumor internal and external area, the input images consist of an intratumoral patch, a peritumoral patch and a peritumoral texture patch focusing on the texture information of the peritumoral patch. Each patch is trained through AlexNet pretrained on ImageNet to explore the usefulness and performance of various patches. Additionally, ensemble learning of network trained with each patch analyzes the performance of different patch combination. Compared with all results, the ensemble model with intratumoral and peritumoral patches achieved the best performance (ACC=98.28%, Sensitivity=100%, NPV=100%).

• 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.

• The Journal of Korean Medicine
• /
• v.32 no.6
• /
• pp.10-17
• /
• 2011

Background: Vibration response imaging (VRI) is a new technology that records energy generated by airflow during the respiration cycle. Analysis of lung sound using VRI may overcome the limitations of auscultation. Objectives: To set a VRI standard for healthy Koreans, we conducted a clinical assessment to evaluate breath sound images and quantification in healthy subjects and compared the findings with reported breath sound characteristics. Methods: Recordings were performed using the VRIxp. Eighty subjects took a deep breath four times during a 12-second interval while sitting upright. The quantitative aspect was analyzed using the VRI quantitative lung data (QLD) for total left lung, total right lung and for six lung regions: left upper lung (LUL), left middle lung (LML), left lower lung (LLL), right upper lung (RUL), right middle lung (RML), right lower lung (RLL). The qualitative aspect was provided through image assessments by three reviewers. Results: In all regions the left lung had significantly higher QLD than the right lung (P<0.005, paired t-test). The inter-rater agreement was 0.78. 84% of the images were found normal by the final assessment. Among the 16% (n=13) of images with abnormal final assessment, the most common flawed features were dynamic image (77%, n=10) and maximum energy frame (MEF) shape (77%, n=10). No significant differences were found between males and females for QLD but there were significant differences in qualitative aspects including dynamic images, MEF shape, and missing LLL. Conclusion: The characteristics of healthy Koreans are similar to those of Western subjects reported previously. VRI is easy to use and objective, and so is helpful to diagnose patients with respiratory diseases and to monitor the progress of diseases after medical treatments.

• Journal of radiological science and technology
• /
• v.2 no.1
• /
• pp.31-35
• /
• 1979

A thorax is consisted of a heart, great vesseles, lungs, ribs, sternum and thoracic spine etc. The quality of chest radiogram is very important in order to find out abnormality in the lung field. The image has two major characteristics; density and contrast which directly influence the diagnostic quality of the roentgenogram. It is very hard to make excellent film image in the lung field because of overlapping bones and other soft tissues. To take a good radiogram of lung field, we studied the condition of chest P-A projection in adult and obtained results as follows: 1. The average chest radiographic condition is resulted as 62KVP, 16 mAs in hospitals around Kyung Ki-Do, Korea, 2. The density of the chest 20cm in thickness, is equal to the water phantom 8cm in thickness. 3. The best quality of chest radiogram is achieved in the condition of the lung field at 100KVP, 9.6mAs by use of Grid 8:1.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1573-1582
• /
• 2011

Risk of lung cancer among lung-related diseases has gradually increased during last decades. The chest digital radiography is the primary diagnosis method for lung cancer. Diagnosing lung cancer using this method requires doctors of ripe experience. Despite their experience there are often wrong diagnoses, which decrease early diagnosis and survival rates of patients. The aim of this study was intended to establish the base on the Computer Aided Diagnosis (CAD) by analyzing Image Recognition Algorithm using Principle component Analysis (PCA) and diagnosing patient's chest X-ray image. The database obtained through this approach enables a doctor to significantly reduce misdiagnosis during the early diagnosis stage, if he or she utilizes it as the preliminary reading step. Case studies were carried out using normal organ, and organs suffering from bronchogenic carcinoma and granuloma. A normal image and unique disease images were extracted after PCA analysis, and their cross-recognition efficiency were compared each other. The result revealed that the recognition rate was much high between normal and disease images, but relatively low between two disease images. In order to increase the recognition efficiency among chest diseases the related algorithms have to be developed continuously in the future study, and such effort will establish the resolute base for CAD.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2209-2213
• /
• 2011

When taking PET/CT, the distortion of the image happens due to the movement of a lesion with respiration. In this study, the experiment was conducted to see if the change in SUV value and distortion of the image could be somewhat corrected by comparing the image which was not compensated with that of the region of lung nodule, compensated with respiration compensation Plumonary Toolkit possessed by this hospital. The records of 17 patients with Lung cancer between May and August 2008. As the result of the experiment, Max SUV value increased by from 4.08% minimum to 43.10% maximum, and the average Max SUV value of lung nodule increased from 6.07 to 7.00(12.16%). In the case of respiration compensation PET/CT, the distortion of the image improved. As there was no significance in the comparison of SCC and Adenocarcinom respectively, though there was a statistically significant level(P<0.05) before and after respiration compensation in SCC-Adenocarcinoma, there was an effect in respiration compensation regardless of Cell types. As the result of the experiment, it was found out that the distortion of standard intake coefficient value and the image was compensated Therefore, the diagnosis of lung cancer and follow up will be able to help.

• Proceedings of the KSMRM Conference
• /
• 2004.09a
• /
• pp.23-32
• /
• 2004

The chemotherapy sensitive Lewis lung carcinoma (LLC) and chemotherapy resistant Lewis lung carcinoma (CR-LLC) tumors concurrently implanted in mice, and compare these findings with histological macroscopic observations against 3D reconstruction of Fluorescence Molecular Tomography (FMT) preformed in vivo on the same animals. For the 3D image reconstruction we used 32 laser source images, a flat image and 3D surface rendering that confused for 3D Fluorescence Molecular Imaging (FMI). A minimum of ten tissue sections were analyzed per tumor for quantification of the TUNEL-positive cells, cell-associated Cy5.5-Annexin and vessel-associated Alexa Fluor-Lectin. These are useful apoptosis and angiogenesis markers, and they serve as validation experiments to data obtained in vivousing a Cy5.5-Annexin V conjugate injected intravenously in chemotherapy-treated animals carrying the tumors studied histologically. We detected higher levels of apoptosis and corresponding higher levels of Cy5.5 fluorescence in the LLC vs. the CR-LLC tumors according to tissue depth and these findings confirm that in vivo staining with the Cy5.5-Annexing conjugate correlates well with in vitro TUNEL staining and is consistent with the higher apoptotic index expected from the LLC line. There appeared to be 1.38% more apoptosis for LLC than CR-LLC. Consequently there is good correlation between the histology results and in vivo fluorescence-mediated optical imaging. In conclusion the apoptotic images of 3D FMI were validated by microscopic histological image analysis. This is a significant result for the continuous progress of fluorescence 3D imaging research.