• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.607-609
• /
• 2002

본 논문은 흉부 전산화단층촬영 영상에서 폐 영역을 자동으로 분할하는 알고리즘과 폐결절을 자동으로 검출하는 알고리즘에 관한 연구 내용을 담고 있다. 폐 분할 알고리즘은 gray-level thresholding과 morphologic 영상 처리기법을 이용하였고, 폐결절 자동 검출 알고리즘은 추출된 결절 후보의 size, compactness, mean of gray level 값을 분석하여 혈관과 결절을 구분하였다. 개발한 폐결절 자동 검출 시스템은 실험한 영상에 포함된 폐결절 117개 중 55%인 64개를 검출하였고, 3.4 False Positive/section이었다.

• Journal of Korean Medical Science
• /
• v.33 no.53
• /
• pp.342.1-342.6
• /
• 2018

We validated the diagnostic performance of a previously developed blood-based 7-protein biomarker panel, $AptoDetect^{TM}$-Lung (Aptamer Sciences Inc., Pohang, Korea) using modified aptamer-based proteomic technology for lung cancer detection. Non-small cell lung cancer (NSCLC), 200 patients and benign nodule controls, 200 participants were enrolled. In a high-risk population corresponding to ${\geq}55years$ of age and ${\geq}30pack-years$, the diagnostic performance was improved, showing 73.3% sensitivity and 90.5% specificity with an area under the curve of 0.88. $AptoDetect^{TM}$-Lung (Aptamer Sciences Inc.) offers the best validated performance to discriminate NSCLC from benign nodule controls in a high-risk population and could play a complementary role in lung cancer screening.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.6
• /
• pp.32-38
• /
• 2009

An FMEA for the waterjet-lifter of a DSNM is performed to prevent the occurrence of device failure. A waterjet-lifter raises and transports manganese nodules from the deep-sea floor up to a somewhat elevated place, from which a pin-scraper transports the lifted nodules to the inner space of the DSNM. A concept design for a device using the axiomatic design methodology is shown as the mapping between the functional domain and physical domain. The FMEA for a DSNM is introduced briefly and the rating criteria of severity, occurrence, and detection for the DSNM are defined. The FMEA of the functional requirements of a DSNM device is accomplished. Three kinds of failure modes, as well as their effects and causes, are predicted. Current design control methods for detecting potential failures, such as physical or computational experiments, design confirmation, and mathematical calculation, are described and the recommended actions for several significant causes are suggested.

• The Korean Journal of Nuclear Medicine
• /
• v.20 no.1
• /
• pp.53-58
• /
• 1986

Thyroid scans using $Na^{131}I\;and\;^{99m}TcO_4^-$ in two (anterior and anterior oblique) projections were done simultaneously in 50 patients with single palpable nodule and in euthyroid state(nodular nontoxic goiter) and 20 normal subjects to evaluate the imaging ability of each radionuclide and the necessity of oblique view. In detection of a nodule as a cold or cool area, $^{99m}TcO_4^-$ was slightly superior to $^{131}I$(82 % to 78% with anterior view alone, 92% to 84% when oblique view is added in detectability), with addition of an oblique view, 5 more cold or cool area in $^{99m}Tc$ scan and 3 more $^{131}I$ scan were detected. In normal subjects $^{99m}TcO_4^-$ scan was significantly superior to $^{131}I$ scan(90% to 70%) in getting normal pattern of tracer uptake in the glands. For routine imaging study of the thyroid, $^{99m}Tc$ pertechnetate scan with multiple projection is considered to be a preferable method.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.729-737
• /
• 2020

Screening with low-dose spiral computed tomography (LDCT) has been shown to reduce lung cancer mortality by about 20% when compared to standard chest radiography. One of the problems arising from screening programs is that large amounts of CT image data must be interpreted by radiologists. To solve this problem, automated detection of pulmonary nodules is necessary; however, this is a challenging task because of the high number of false positive results. Here we demonstrate detection of pulmonary nodules using six off-the-shelf convolutional neural network (CNN) models after modification of the input/output layers and end-to-end training based on publicly databases for comparative evaluation. We used the well-known CNN models, LeNet-5, VGG-16, GoogLeNet Inception V3, ResNet-152, DensNet-201, and NASNet. Most of the CNN models provided superior results to those of obtained using customized CNN models. It is more desirable to modify the proven off-the-shelf network model than to customize the network model to detect the pulmonary nodules.

• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.10039-10043
• /
• 2014

Background: In Pakistan thyroid cancer is responsible for 1.2% cases of all malignant tumors. Ultrasonography (US) is helpful in detecting cancerous thyroid nodules on basis of different features like echogenicity, margins, microcalcifications, size, shape and abnormal neck lymph nodes. We therefore aimed to calculate diagnostic accuracy of ultrasound in detection of carcinoma in thyroid nodules taking fine needle aspiration cytology as the reference standard. Materials and Methods: A cross-sectional analytical study was designed to prospectively collect data from December 2010 till December 2012 from the Department of Radiology in Aga Khan University Hospital, Karachi, Pakistan. A total of 100 patients of both genders were enrolled after informed consent via applying non-probability consecutive sampling technique. Patients referred to Radiology department of Aga Khan University to perform thyroid ultrasound followed by fine-needle aspiration cytology of thyroid nodules were included. They were excluded if proven for thyroid malignancy or if their US or FNAC was conducted outside our institution. Results: The subjects comprised 76 (76%) females and 24 males. Mean age was $41.8{\pm}SD$ 12.3 years. Sensitivity and specificity with 95%CI of ultrasound in differentiating malignant thyroid nodule from benign thyroid nodule calculated to be 91.7% (95%CI, 0.72-0.98) and 78.94% (0.68-0.87) respectively. Reported positive predictive value and negative PV were 57.9% (0.41-0.73) and 96.8% (0.88-0.99) and overall accuracy was 82%. Likelihood ratio (LR) positive was computed to be 4.3 and LR negative was 0.1. Conclusions: Ultrasonography has a high diagnostic accuracy in detecting malignancy in thyroid nodules on the basis of features like echogenicity, margins, micro calcifications and shape.

• Journal of Periodontal and Implant Science
• /
• v.41 no.4
• /
• pp.167-175
• /
• 2011

Purpose: Periodontal ligament (PDL) cell differentiation into osteoblasts is important in bone formation. Bone formation is a complex biological process and involves several tightly regulated gene expression patterns of bone-related proteins. The expression patterns of bone related proteins are regulated in a temporal manner both in vivo and in vitro. The aim of this study was to observe the gene expression profile in PDL cell proliferation, differentiation, and mineralization in vitro. Methods: PDL cells were grown until confluence, which were then designated as day 0, and nodule formation was induced by the addition of 50 ${\mu}g$/mL ascorbic acid, 10 mM ${\beta}$-glycerophosphate, and 100 nM dexamethasone to the medium. The dishes were stained with Alizarin Red S on days 1, 7, 14, and 21. Real-time polymerase chain reaction was performed for the detection of various genes on days 0, 1, 7, 14, and 21. Results: On day 0 with a confluent monolayer, in the active proliferative stage, c-myc gene expression was observed at its maximal level. On day 7 with a multilayer, alkaline phosphatase, bone morphogenetic protein (BMP)-2, and BMP-4 gene expression had increased and this was followed by maximal expression of osteocalcin on day 14 with the initiation of nodule mineralization. In relationship to apoptosis, c-fos gene expression peaked on day 21 and was characterized by the post-mineralization stage. Here, various genes were regulated in a temporal manner during PDL fibroblast proliferation, extracellular matrix maturation, and mineralization. The gene expression pattern was similar. Conclusions: We can speculate that the gene expression pattern occurs during PDL cell proliferation, differentiation, and mineralization. On the basis of these results, it might be possible to understand the various factors that influence PDL cell proliferation, extracellular matrix maturation, and mineralization with regard to gene expression patterns.

• Tuberculosis and Respiratory Diseases
• /
• v.58 no.2
• /
• pp.111-119
• /
• 2005

The introduction of high-resolution CT (HRCT) in recent years has improved the ability of radiologists to detect and characterize the diffuse infiltrative lung disease (DILD). The detection and diagnosis of diffuse lung disease using HRCT are based on the recognition of specific abnormal findings. In this article, pattern recognition of HRCT findings is reviewed in the differential diagnosis of diffuse infiltrative lung disease. In general, HRCT findings of lung disease can be classified into four categories based on their appearances. These categories consist of (1) nodules and nodular opacities, (2) linear and reticular opacities, (3) increased lung opacity, and (4) decreased lung opacity, including cystic lesions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.247-249
• /
• 2003

일반적으로 방사선 의사들(radialogists)이 폐 결절(pulmonary nodule)을 탐지하는 데는 실제적으로 30% 의 실패율을 가진다고 알려져 있다. 만약 자동화된 시스템이 흉부 영상에서 의심스런 결절들의 위치들을 방사선 의사에게 알려줄 수 있다면 잘못 판단되는 결절들의 수를 잠재적으로 줄일 수 있다. 그리하여 기존의 시스템들은 처리가 어려운 X 선 영상을 좀 더 다루기 쉬운 상태로 바꿔주기 위하여 원래의 영상에 수축(erosion)과 확장(dilation)을 연이어서 행하는 형태학적 필터링(morphological filtering) 처리를 행한다. 그런 다음 결절의 특징을 가려낼 수 있는 추출 기술들을 나름대로 행한다. 그러나, 이 형태학적 필터링 처리는 상당한 처리 시간을 필요로 한다. 이에 본 논문은 형태학적 필터링 처리를 행하지 않고 원래의 흉부 X 선 영상으로부터 직접 결절의 의심지역들을 추출한 후 두가지 특징 추출기술들을 적용시킨다. 그리하여 본 시스템은 결절의 정확한 판독이 어려운 폐의 X 선 영상에 적용되어 false-positive 들을 효과적으로 줄임으로써 보다 효율적인 폐 결절의 추출를 가능하게 하였다.