• Journal of Biomedical Engineering Research
• /
• v.38 no.5
• /
• pp.237-241
• /
• 2017

Early detection of the pulmonary nodule is important for diagnosis and treatment of lung cancer. Recently, CT has been used as a screening tool for lung nodule detection. And, it has been reported that computer aided detection(CAD) systems can improve the accuracy of the radiologist in detection nodules on CT scan. The previous study has been proposed a method using Convolutional Neural Network(CNN) in Lung CAD system. But the proposed model has a limitation in accuracy due to its sparse layer structure. Therefore, we propose a Deep Convolutional Neural Network to overcome this limitation. The model proposed in this work is consist of 14 layers including 8 convolutional layers and 4 fully connected layers. The CNN model is trained and tested with 61,404 regions-of-interest (ROIs) patches of lung image including 39,760 nodules and 21,644 non-nodules extracted from the Lung Image Database Consortium(LIDC) dataset. We could obtain the classification accuracy of 91.79% with the CNN model presented in this work. To prevent overfitting, we trained the model with Augmented Dataset and regularization term in the cost function. With L1, L2 regularization at Training process, we obtained 92.39%, 92.52% of accuracy respectively. And we obtained 93.52% with data augmentation. In conclusion, we could obtain the accuracy of 93.75% with L2 Regularization and Data Augmentation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.1881-1886
• /
• 2016

Background: CA125 is very helpful in treatment monitoring and detection of epithelial ovarian cancer (EOC) recurrence. However there is controversy as to its accuracy and optimal usage. What is the impact of the CA125 levels before primary surgery treatment to the survival of patients? This study aimed to detect any association of preoperative serum levels with prognosis and survival in EOC patients. Materials and Methods: Our cohort comprised EOC patients in Dr. Sardjito Hospital, Yogyakarta, Indonesia, who complied with follow up. To explore the effect of preoperative CA125 levels and other variables on survival Cox's regression models were applied. Results: A total of 90 cases of EOC who had surgery were available for follow up. The level of CA125 proved to be a prognostic factor for overall survival of EOC patients, with an adjusted HR of 4.10 (p = 0.03). Adjuvant chemotherapy was another prognostic factor, 1 - 2 cycles having an adjusted HR of 0.17 (p = 0.04) and 3 - 8 cycles HR 0.39 (p = 0.06). Other factors such as age of patients adjusted HR 1.54 (p = 0.32), moderate differentiation (adjusted HR 1.61, p = 0.51) poor differentiation (adjusted HR 3.41, p = 0.15), and stage of disease (adjusted HR 1.98,p=0.27) were statistically not significant. However, this might have been because the power of the study was low. Conclusions: Preoperative level of CA125 is a prognostic factor for overall survival in EOC patients. The best cut-off for prognostic classification of CA125 serum level is 70 U/ml.

• Journal of radiological science and technology
• /
• v.42 no.1
• /
• pp.9-17
• /
• 2019

Although digital mammography is a representative method for breast cancer detection. It has a limitation in detecting and classifying breast tumor due to superimposed structures. Machine learning, which is a part of artificial intelligence fields, is a method for analysing a large amount of data using complex algorithms, recognizing patterns and making prediction. In this study, we proposed a technique to improve the diagnostic accuracy of energy-selective mammography by training data using the machine learning algorithm and using dual-energy measurements. A dual-energy images obtained from a photon-counting detector were used for the input data of machine learning algorithms, and we analyzed the accuracy of predicted tumor thickness for verifying the machine learning algorithms. The results showed that the classification accuracy of tumor thickness was above 95% and was improved with an increase of imput data. Therefore, we expect that the diagnostic accuracy of energy-selective mammography can be improved by using machine learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.307-310
• /
• 2021

In the recent years, studies using Computer-Aided Diagnostics(CAD) have been actively conducted, such as signal and image processing technology using breast ultrasound images, automatic image optimization technology, and automatic detection and classification of breast masses. As computer diagnostic technology is developed, it is expected that early detection of cancer will proceed accurately and quickly, reducing health insurance and test ice for patients, and eliminating anxiety about biopsy. In this paper, a quantitative analysis of tumors was conducted in ultrasound images using a gray level co-occurrence matrix(GLCM) to experiment with the possibility of use for computer assistance diagnosis.

• Korean Journal of Remote Sensing
• /
• v.28 no.1
• /
• pp.129-143
• /
• 2012

This paper demonstrates the effectiveness of advanced spatial modeling techniques for environmental monitoring and impact assessment through a case study of Chernobyl nuclear accident occurred in 1986. Land-cover types changed after the accident are analysed by a post classification comparison method using bi-temporal Landsat TM data acquired in 1986 and 1992 near the accident site. Spatial modeling including various kriging algorithms are also applied to analyze the relationships between Cesium concentrations in soil and thyroid cancer incidence rates in Belarus, which was greatly damaged by the accident. The change detection results clearly showed the decrease of croplands and the increase of abandoned lands, and concrete structures were newly built around the nuclear plant to prevent the spread of radioactive contamination. In Belarus, high Cesium concentrations were observed in southern areas with high thyroid cancer risk estimated by Poisson kriging. Geographically weighted regression, which could account for geographic variations of independent variables including Cesium concentrations and distances from the Chernobyl nuclear power plant, was applied to extract the relationships between the independent variables and the thyroid cancer risk. The estimated risk values showed a correlation coefficient value of 0.98 with respect to the thyroid cancer risk values, which implied that the thyroid cancer risk in Belarus was affected by the accident. In conclusion, it is expected that advanced spatial modeling techniques applied in this study would be useful for environmental impact assessment and public health research.

• Journal of Gastric Cancer
• /
• v.9 no.4
• /
• pp.167-171
• /
• 2009

Purpose: This study was done to determine the usefulness of serum pepsinogen (PG) levels as a screening method for gastric cancer, and to assess the relationships between serum PG and clinicopathologic factors of gastric adenocarcinoma. Materials and Methods: Serum PG concentrations were measured in 94 subjects who were classified into (a) a control group (50 subjects) without abnormal endoscopic finding on a health checkup, or (b) a gastric cancer group (44 subjects) who had surgery at Daegu Catholic University Hospital between Nov. 2008 and May 2009. Receiver operator characteristic curves were utilized to select the most suitable test. Using different cutoff points, sensitivity and specificity were calculated. We compared preoperative serum PG levels with several clinicopathologic findings for patients with gastric adenocarcinoma. Results: The Serum PG I：II ratio was the most useful as a screening test. The sensitivity and specificity of PG screening for gastric cancer were, respectively, 81.8% and 82%. The cut off point correlated with the type of intestinal cancer (Lauren classification; P=0.003), tumor stage (P=0.001), and gastric adenocarcinoma with peritumoral chronic atrophic gastritis (P=0.036). Conclusion: Serum PG levels were found to be a potentially useful screening test and to correlate with clinicopathologic factors in gastric cancer patients. But, in order to use serum PG found in a health checkup for gastric cancer as a clinical application a large scale study is recommended.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.3
• /
• pp.1327-1331
• /
• 2014

Background: Electrical impedance tomography (EIT) is a new non-invasive, mobile screening method which does not use ionizing radiation to the human breast; allows conducting quantitative assessment of the images besides the visual interpretation. The aim of this study was to correlate the quantitative assessment and visual interpretation of breast electrical impedance tomographs and associated factors. Materials and Methods: One hundred and fifty mammography patients above 40 years and undergoing EIT were chosen using convenient sampling. Visual interpretation of the images was carried out by a radiologist with minimum of three years experience using the breast imaging - electrical impedance (BI-EIM) classification for detection of abnormalities. A set of thirty blinded EIT images were reinterpreted to determine the intra-rater reliability using kappa. Quantitative assessment was by comparison of the breast average electric conductivity with the norm and correlations with visual interpretation of the images were determined using Chi-square. One-way ANOVA was used to compare the mean electrical conductivity between groups and t-test was used for comparisons with pre-existing Caucasians statistics. Independent t-tests were applied to compare the mean electrical conductivity of women with factors like exogenous hormone use and family history of breast cancer. Results: The mean electrical conductivity of Malaysian women was significantly lower than that of Caucasians (p<0.05). Quantitative assessment of electrical impedance tomography was significantly related with visual interpretation of images of the breast (p<0.05). Conclusions: Quantitative assessment of electrical impedance tomography images was significantly related with visual interpretation.

• BMB Reports
• /
• v.37 no.6
• /
• pp.671-675
• /
• 2004

The expression and clinicopathological significance of Quox-1 gene was studied in oral squamous cell carcinoma (OSCC). Immunocytochemistry and western blot analysis were used to examine the different expressions of Quox-1 protein in 114 OSCC specimens, 34 oral epithelial dysplasia specimens, and 16 normal oral mucosa specimens. RT-PCR and virtual Northern Blot were also used to examine the expression of Quox-1 mRNA. It was found that Quox-1 was not expressed in normal epithelium. However, as dysplastic lesions progressed Quox-1 expression increased (p < 0.01), and Quox-1 expression was not significantly different between severe dysplasia and highly differentiated OSCCs (p > 0.05). As the degree of differentiation decreased, Quox-1 positivity increased in OSCC (p < 0.01), and the rate of Quox-1 (81.58%) positivity in OSCC was higher than that in normal oral mucosa (p < 0.01). Our findings imply that the positive expression of Quox-1 is correlated with the histological classification of OSCCs. Thus, the expression of Quox-1 in OSCC may serve as a significant predicting factor of proliferative status and malignant degree, and it may also be a biological detection marker of oral mucosas initial cancer and of OSCC.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.6
• /
• pp.2523-2527
• /
• 2014

Background: Serum thyroglobulin detection plays an essential role during the follow-up of thyroid cancer patients treated with total/near total thyroidectomy and radioiodine ablation. The aim of this retrospective study was to evaluate the relationship between stimulated serum thyroglobulin (Tg) level at the time of high dose $^{131}I$ ablation and risk of recurrence, using a three-level classification in patients with differentiated thyroid cancer (DTC) according to the ATA guidelines. Also we investigated the relationship between postoperative stimulated Tg at the time of ablation and DxWBS results at 8-10 months thereafter. Materials and Methods: Patients with radioiodine accumulation were regarded as scan positive (scan+). If there was no relevant pathological radioiodine accumulation or minimal local accumulation in the thyroid bed region, this were regarded as scan negative (scan-) at the time of DxWBS. We classified patients in 3 groups as low, intermediate and high risk group for assessment of risk of recurrence according to the revised ATA guidelines. Also, we divided patients into 3 groups based on the stimulated serum Tg levels at the time of $^{131}I$ ablation therapy. Groups 1-3 consisted of patients who had Tg levels of ${\leq}2ng/ml$, 2-10 ng/ml, and ${\geq}10ng/ml$, respectively. Results: A total of 221 consecutive patients were included. In the high risk group according to the ATA guideline, while 45.5% of demonstrated Scan(+) Tg(+), 27.3% of patients demonstrated Scan(-) Tg(-); in the intermediate group, the figures were 2.3% and 90.0% while in the low risk group, they were 0.6% and 96.4%. In 9 of 11 patients with metastases (81.8%), stimulated serum Tg level at the time of radioiodine ablation therapy was over 10, however in 1 patient (9.1%) it was <2ng/mL and in one patient it was 2-10ng/mL (p=0.005). Aggressive subtypes of DTC were found in 8 of 221 patients and serum Tg levels were ${\leq}2ng/ml$ in 4 of these 8. Conclusions: We conclude that TSH-stimulated serum thyroglobulin level at the time of ablation may not determine risk of recurrence. Therefore, DxWBS should be performed at 8-12 months after ablation therapy.

• Journal of Environmental Health Sciences
• /
• v.43 no.6
• /
• pp.532-544
• /
• 2017

Objectives: Because the amount of medical waste (i.e., health-care waste) generated in Korea is rapidly increasing and social concern against its safety is widespread, a number of issues related with medical wastes are being discussed. The purpose of this study is to compare diverse medical waste management systems worldwide and propose future directions of a medical waste management system in Korea. Methods: Literature review was conducted mainly on the WHO, and developed countries such as the European Union (Germany, Belgium and UK), Japan and the United States. For these countries, the data with respect to their systems for medical waste management ranging from the definition of medical waste to the whole processes of collection, transportation and disposal were summarized and compared. Results: The terminology and classification of medical wastes were not consistent for WHO recommendation, EU, Japan, US and Korea. Comparison of the collection, storage, transportation and disposal of medical waste showed that Korea had rather stronger regulations for medical waste management compared to developed countries including Belgium (Flanders region), Germany, Japan and the US. Considering that developed countries adopt rather flexible disposal system especially for general medical wastes which pose lower possibility of infection, Korean government could consider diversifying disposal methods other than incineration. It may also be very important to try to reduce the amount of medical wastes and enough capacity for off-site incineration are secured. Conclusion: Our study of international comparisons suggests that it is necessary to continue to identify advantages and disadvantages of the current medical waste management systems and establish more effective one in Korea.