• The Journal of the Korea Contents Association
• /
• v.18 no.1
• /
• pp.108-116
• /
• 2018

The purpose of this study was to investigate the relationship between the differences in the acoustic measurements (AVQI) and the auditory-perceptual assessments (GRBAS, CAPE-V) of the normal and vocal fold nodules. For this purpose, Total 335 voice samples were analyzed acoustically and three raters performed auditory-perceptual assessments. in the results, AVQI, G, and OS scores of the normal group were lower than those of the vocal fold nodules group. The correlations between the G scale and the OS scale were highly correlated, and the correlation between the AVQI, and auditory-perceptual results (G and OS) was also high value. The threshold values for discriminating AVQI, G, and OS between the two groups were ${\leq}4.06$, ${\leq}1$, and ${\leq}26$, respectively, and the predictive diagnostic power was 0.840, 0.860, and 0.848. In conclusion, AVQI and auditory-perceptual evaluation can improve potentiality the screening of vocal fold nodules and help to determine the diagnosis and treatment plan of voice disorders.

• Journal of the Korean Society of Radiology
• /
• v.18 no.4
• /
• pp.317-325
• /
• 2024

This study aimed to classify normal and nodule images in thyroid ultrasound images using GLCM and machine learning. The research was conducted on 600 patients who visited S Hospital in Busan and were diagnosed with thyroid nodules using thyroid ultrasound. In the thyroid ultrasound images, the ROI was set to a size of 50x50 pixels, and 21 parameters and 4 angles were used with GLCM to analyze the normal thyroid patterns and thyroid nodule patterns. The analyzed data was used to distinguish between normal and nodule diagnostic results using the SVM model and KNN model in MATLAB. As a result, the accuracy of the thyroid nodule classification rate was 94% for SVM model and 91% for the KNN model. Both models showed an accuracy of over 90%, indicating that the classification rate is excellent when using machine learning for the classification of normal thyroid and thyroid nodules. In the ROC curve, the ROC curve for the SVM model was generally higher compared to the KNN model, indicating that the SVM model has higher within-sample performance than the KNN model. Based on these results, the SVM model showed high accuracy in diagnosing thyroid nodules. This result can be used as basic data for future research as an auxiliary tool for medical diagnosis and is expected to contribute to the qualitative improvement of medical services through machine learning technology.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.37-44
• /
• 2013

In this paper, we propose the pulmonary nodule detection system based on voxel classification. The proposed system consists of three main steps. In the first step, we segment lung volume. In the second step, the lung structures are initially segmented. In the last step, we classify the nodules using voxel classification. To describe characteristics of each voxel, we extract the log-polar sampling based features. Support Vector Machine is applied to the extracted features to classify into nodules and non-nodules.

• Journal of the Korean Society of Radiology
• /
• v.11 no.4
• /
• pp.227-234
• /
• 2017

This study evaluated the usefulness of the elasticity score and strain ratio in the differential diagnosis of benign and malignant nodules in thyroid elastography. We performed a retrospective analysis based on the results of fine needle aspiration cytology. The Chi-square test and the Mann-Whitney U test were used to analyze the difference between the five degrees of elasticity score and strain ratio according to the benign and malignant thyroid nodules. ROC curve analysis was used to determine the elasticity score and the best cut-off value of the strain ratio for the prediction of malignant nodules. There was a statistically significant difference (p=0.000) between the homogeneity of the elasticity score and the difference of the strain ratio between the benign and malignant nodule groups. On the ROC curve analysis, the elasticity score and the srain ratio for predicting benign and malignant nodules were determined as AUC 0.842, 0.700, cut-off value 3, 2.49 (p=0.001). Therefore, the elasticity score and strain ratio may be useful in the differential diagnosis of thyroid nodules.

• Journal of the Korean Geographical Society
• /
• v.45 no.5
• /
• pp.628-646
• /
• 2010

The subject of this research is the small-scale trade between South Korea and China (this trade is a so-called shuttle trade.) This research attempts to find the background to the emergence of the Sino-South Korean (cross-border) small-scale trade and the role of travel routes between the two countries. This research also aims to identify the development process of the bilateral small-scale trade by studying the scale of the small-scale trade and the organization of small-scale traders. Moreover, this research tries to discover the spatial characteristics of the interregional small-scale trade by reviewing the characteristics of traded goods; process of export and import and nodes of small-scale trade. To accomplish aforementioned purposes, the author discussed the relations between small-scale traders and maritime companies. The author also studied the internal change in the small-scale trade by focusing on the reinforcement of the regulation against the small-scale trade. Lastly, the author cited the case of the Soviet Union and middle-eastern Europe, which tremendously expanded the small-scale trades in the 1980s, in order to explain the growth of the Sino-South Korean small-scale trade.

• Journal of Yeungnam Medical Science
• /
• v.23 no.2
• /
• pp.205-212
• /
• 2006

Background: Malignant pulmonary nodules account for about 30 to 40 percent of solitary pulmonary nodules (SPN). Therefore, tissue characterization of SPNs is very important. Recently, PET/CT has been widely used for tissue characterization, and has become of importance. The purpose of this study was to compare and to assess multiple factors in PET/CT comparing benign and malignant nodules. Materials and Method: Nineteen patients with SPN underwent PET/CT and biopsy. The difference of standardized uptake value 1 (SUV1), standardized uptake value 2 (SUV2) and retention index in PET/CT between malignancy and benignancy were compared by Levene's test. Result: There were twelve malignant and seven benign nodules. SUV1 and SUV2 were significantly different between malignant nodule and benign nodule (p=0.006 and 0.022), but retention index was not significantly different between malignant nodule and benign nodule (p=0.526). By receiver-operating-characteristic (ROC) analysis, the sensitivity was 66.7% and the specificity was 71.4% at a cut off value of 5.40 in SUV1. The sensitivity was 75% and the specificity was 71.4% at cut off value of 7.45 in SUV2. Conclusion: There was a statistically significant difference in SUV1 and SUV2 between benign and malignant nodules. However, the cut off value of SUV1 and SUV2 by receiver-operating-characteristic (ROC) analysis was 5.40 and 7.45 which is different from previous studies. Therefore, studies on a larger sample of patients are required for confirmation.

• Proceedings of the KOR-BRONCHOESO Conference
• /
• 1981.05a
• /
• pp.9.1-10
• /
• 1981

The clinical study of 183 cases of laryngeal mass was observed and 88 cases of vocal nodule and polyp which is confirmed histopathologically, were clinically classified into 30 cases of vocal nodule, 48 cases of localized vocal polyp, 10 cases of diffuse vocal polyp, and the following results of microscopic examination were obtained. I. The clinical study of laryngeal mass 1. Among total cases of 183, vocal nodule is 82(45%) vocal polyp 53(29%) postintubation granuloma 3(1%) laryngeal papilloma 18(10%) tuberculosis 2(1%) cancer 25(14%). 2. The sex ratio of male to female is 3:4 in vocal nodule, 1:1 in vocal polyp, 1:2 in postintubation granuloma, 3:2 in laryngeal papilloma, 11:1 in cancer. 3. The age distribution is third-fourth decade in vocal nodule, fourth-fifth decade in vocal polyp, third decade in postintubation granuloma, second and fifth decade in laryngeal tuberculosis, sixth decade in laryngeal cancer. 4. The distribution of symptoms is 5 month. -1 year in vocal nodule and polyp, less than 1 year in laryngeal papilloma and postintubation granuloma, 1 year-3 year in laryngeal tuberculosis and cancer. 5. The location of the lesion is between the anterior 1/3 and middle 1/3 in vocal nodule and polyp and papilloma, middle 1/3 and posterior 1/3 in postintubation granuloma, and is diffusely spread on the entire vocal cord in laryngeal tuberculosis and cancer. 6. The side of the lesion is bilateral in vocal nodule and papilloma and the ratio of right to left is 5:3 in vocal polyp, 2:1 in postintubation granuloma. 7. The size is 1~2mm(67%) in vocal nodule, 3~5mm(42%) in vocal polyp, 6~10mm (67%) in postintubation granuloma, 1~2mm (39%) in papilloma, more than 10mm in tuberculosis and cancer. 8. Among the symptoms, the hoarseness is in more than 90% of disease entity, the sore-throat in tuberculosis and cancer, the dyspnea in postintubation granuloma and papilloma and tuberculosis and cancer. 9. In the past history, certain relationship with smoking is noted in cancer (40%) and tuberculosis(50%) and the history of frequent attack of URI is in papilloma(33%). 10. In occupation, certain statistical significance was not noted. II. The histopathological study of vocal nodule and polyp. 1. Most polyps and nodules were covered with stratified squamous epithelium, but focal hyperkeratosis, parakeratosis, acanthosis and atrophy were rather frequently observed. Hyperkeratosis and acanthosis was most frequently seen.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.1
• /
• pp.13-19
• /
• 2012

In this paper, we propose the pulmonary nodule detection method based on hierarchical 3D block analysis. The proposed system consists of two main part. In the first part, we select the block which is need to analysis. In the second part, we analysis the selected blocks. We extract the shape based features of the object in the selected blocks. Support Vector Machine is applied to the extracted features to classify into nodules and non-nodules.

• Journal of Yeungnam Medical Science
• /
• v.12 no.2
• /
• pp.400-404
• /
• 1995

Focal nodular hyperplasia is a benign hepatic tumor mainly composed of nodules of hepatocytes and Kupffer cells separated by fibrous septa. In general, it is difficult to differentiate focal nodular hyperplasia and hepatocellular carcinoma on ultrasonography, conventional CT(computerized tomography), and angiography. But IV bolus CT is of particular value in the diagnosis of focal nodular hyperplasia because it can divide enhanced CT into early and late phase and can characterize tumor vascularity and analyze any intratumoral elements. In our case, it was seen as a hypoechoic mass lesion on ultrasonography and hyperdense mass lesion on early-phase IV bolus CT and isodense mass lesion on late-phase IV bolus CT. On angiography, hypertrophy of the feeding artery and tumor staining were well visualized. The patient underwent operation and the mass was pathologically confirmed to a focal nodular hyperplasia. We report the first case of focal nodular hyperplasia on IV bolus CT in Korea.

• The Journal of the Korea Contents Association
• /
• v.13 no.5
• /
• pp.303-310
• /
• 2013

Thyroid nodular disease is the most frequently appeared in thyroid disease. Thyroid ultrasonography offers location of nodules, size, the number, information of internal echo characteristic. Thus, it makes possible to sort high-risk nodule containing high possibility about thyroid cancer and to induct precisely when take a Fine Needle Biopsy Aspiration. On thyroid nodule, the case which is diagnosed as malignant is less than 5% but screening test is very important on ultrasound and also must be reduced unnecessary procedure. Therefore, in this study an approach for describing a region is to quantity its texture content. We applied TFA algorithm on case which has been pathologically diagnosed as papillary thyroid cancer. we obtained experiment image which set the ROI on ultrasound and cut the $50{\times}50$ pixel size, histogram equalization. Consequently, Disease recognition detection efficiency of GLavg, SKEW, UN, ENT parameter were high as 91~100%. It is suggestion about possibility on CAD which distinguishes thyroid nodule. In addition, it will be helpful to differential diagnosis of thyroid nodule. If the study on additional parameter algorithm is continuously progressed from now on, it is able to arrange practical base on CAD and it is possible to apply various disease in the thyroid US.