• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.1
• /
• pp.31-35
• /
• 2010

This paper presents the development of automatic defect detection program using 3D computed tomography image of small solid rocker motor. We applied the neighbor pixel comparison algorithm with beam hardening correction for the recognition of defect. We made the artificial defect specimen in order to decide a standard CT value of defect. The program was tested with 150 small solid rocket motors and it could detect the disbond, crack, foreign material and void. The program showed more reliable and faster results than human inspector's interpretation.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.331-337
• /
• 2005

'Supplement 23:DICOM SR' announced on April 2000 made possible co-relations between the clinical reports and human body parts by standardizing the exchange of clinical information. DICOM SR uses its own coding schemes and values to represent information, which convey hierarchically structured content items. This paper analyzes radiology reports produced in HIS(Hospital Information System) and categorizes content structures into three parts such as, finding, conclusion, and recommendation, and implements a system which can be used by clinicians. Digital X-ray images and their reports have been managed separately. Since the report made by DICOM SR can refer to images, the integrated information of reports and images is possible.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.317-319
• /
• 2021

최근 코로나 19가 장기화하면서, 비대면서비스로 대체되고 있는 한편, 의료분야에도 서비스 패러다임이 변화되고 있다. 특히, 국내의 법 제도적으로 묶여 있는 원격 의료서비스의 적용이 가능하고 상급종합병원에서는 비대면 진료서비스를 도입하고 있다. 본 논문에서 제안하는 비대면 원격판독시스템은 모바일 의료영상진단기기를 기반으로 의료사각지대에 있는 환자들의 영상촬영과 이에 대한 판독 서비스를 제공하기 위한 시스템이다. 제안한 시스템은 의료환경에 적용하기 위해 환자의 개인정보를 보호하고, 원격으로 환자의 영상 데이터를 판독하기 위한 시스템과 그 처리 과정을 보인다. 그리고 끝으로 구축된 시스템의 수행 결과를 보인다.

• The Korean Journal of Nuclear Medicine
• /
• v.28 no.3
• /
• pp.317-325
• /
• 1994

The accuracy of dipyridamole stress/rest $^{99m}Tc$-MIBI myocardial imaging for detection of ischemia depends on reproducible image interpretation. To evaluate the reproducibility of visual assessment, agreement in interpretation among two independent observers, blind-ed to clinical data, was evaluated in SPECT images of 131 patients (94 males, 38 females; mean age $58{\pm}7yr$) with suspected coronary artery disease who underwent both dipyridamole stress/rest $^{99m}Tc$-MIBI myocardial SPECT and coronary angiography. The left ventricle was divided into twenty-nine segments in stress and rest SPECT images and each segment was visually graded according to a five-point scale (segmental score : 0=normal, 1=equivocal, 2=mild decrease, 3=severe decrease and 4=absent uptake). Overall concordance of segmental scoring between the two observers was 80%. The Pear-son's correlation coefficient (r) of the segmental scores for stress and rest images were 0.67 and 0.65, respectively, while the difference in score between the two images showed a correlation of 0.45 (all p<0.001). Agreement between two observers in final SPECT diagnosis as absence or presence of disease was 93%. The degree of agreement in segmental scoring showed no difference between patients with or without agreement as to the presence of disease. Therefore it appeared that cases with inconcordant diagnosis between the 2 observers were mainly due to a difference in individual threshold for interpretating the significance of a particular decreased uptake area rather than to a difference in perceiving the degree of the hypoactivity Thus, establishment of individual optimum thresholds in visual interpretation of myocardial SPECT may be helpful to improve reproducibility and accuracy of scan diagnosis.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.20 no.2
• /
• pp.265-276
• /
• 1990

The purpose of this experiment was to evaluate radiographic interpretation, of various sized 60 periapical and 60 cancellous lesions in 10 mandibular sections of 5 dogs according to kVp (65, 70, 75, 80 and 85 kVp). The results were as follows; The change of kilovoltage within 65kVp-85kVp range did not have influence on the radiographic interpretation of the same-sized bony defects at the constant radiographic density (p> 0.05). When the bony defects were less than the size of No.2 round bur, radiographic interpretation of bony defects prepared with No.2 round bur was easier than those prepared with No. 1 round bur at 80-85kVp in periapical region (p<0.05). However, in cancellous bone, this radiographic interpretation was easier at 65-75kVp (p<0.05). There were significant differences in the radiographic interpretation between the defects confined only to the cancellous, bone and the defects involved in the compact bone (p<0.05). However there were no significant differences between the defects confined only to the cancellous bone and the defects involved in junctional area of cancellous and compact bone (p>0.05). From the results of densitometric analysis, there was a difference in densitometric measurements at the same radiographic interpretation scores, and aluminum equivalent differences of 0.15-1.66㎜ thickness were needed for radiographic interpretation.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.346-351
• /
• 2014

Accurate blood typing tests are essential for safe blood transfusion. Recently many automated test equipments have been introduced to reduce errors and increase the efficiency of the test. However, those equipments being high in price, it is difficult to introduce automated test equipment for every hospital. In this study, we developed a reader for blood typing using column agglutination test. In the process, the results, read out by the image processing, are stored and reaffirmed. To evaluate the reader, 148 samples for ABO and RhD blood typing tests and 154 samples for unexpected antibody test were used. The positive and negative intensity of the reading and the reading of the reaction were 100% in agreement with the result of traditional manual method. If additional verification is completed, this reader can be efficiently and economically used in small-and medium-sized hospitals.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2004.11a
• /
• pp.246.1-246.1
• /
• 2004

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.2
• /
• pp.109-116
• /
• 2005

Purpose : To determine the usefulness of additional Mn-DPDP MRI for preoperative evaluation of the patients with colorectal cancers by comparison of dual-phase CT scan, Mn-DPDP enhanced MRI and combination of CT and MRI. Materials and Methods : Fifty-three colorectal cancer patients with 92 metastatic nodules underwent dualphase (arterial and portal) helical CT scan and Mn-DPDP MRI prior to surgery. The indication of MRI was presence or suspected of having metastatic lesions at CT scan and/or increased serum carcinoembryonic antigen (CEA) levels (10 ng/mL or more). The diagnosis was established by the combination of findings at surgery, intraoperative ultrasonography, and histopathologic examination. Two radiologists interpreted CT, MRI, and combination of CT-MRI at discrete sessions and evaluated each lesion for location, size, and intrinsic characteristics. The lesions were divided into three groups according to their diameter; 1cm<, 1-2 cm, and >2 cm. Diagnostic accuracy was evaluated using the alternative-free response receiver operating characteristic method. Detection and false positive rate were also evaluated. Results : In the lesions smaller than 1 cm, detection rate of combined CT-MRI was superior to CT or MRI alone (82%, p=0.036). The mean accuracy (Az values) of combined CT and MRI was significantly higher than that of CT in the lesions smaller than 2 cm (1 cm<, p=0.034; 1-2 cm, p=0.045). However, there was no significant difference between MRI and combined CT-MRI. The false positive rate of CT was higher than those of combined CT-MR in the lesions smaller than 1 cm (28%, p=0.023). Conclusion : Additional MRI using Mn-DPDP besides routine CT scan was helpful in differentiating the hepatic lesions (<2 cm) and could improve detection of the small hepatic metastases (<1 cm) from colorectal carcinoma.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.3
• /
• pp.52-61
• /
• 2020

This study developed a legibility distance(LD) model for three colors used in VMS according to luminance under foggy conditions through experiments. For this, a simulated environment was created, and LD values of red, green, and yellow color were collected by increasing the luminance. From the test results, the LDs for red at luminance levels of 2,000 cd/㎡ and 20,000 cd/㎡ and a visibility distance of 10m were 10.2m and 18.8m, respectively, which was an improvement of 84%. The LD was improved by 34% and 17% at a visibility distance of 20 m and 30 m, respectively. For green, the LD was improved by 69%, 63%, and 19% at visibility distance of 10m, 20m, 30m, respectively. For yellow, the LD was improved by 100%, 47%, and 36% at visibility distance of 10m, 20m, 30m, respectively. The LD models for three colors were developed by using two independent variables, luminance value and visibility distance. The adjusted coefficients of the red, green, and yellow model equations were calculated as 0.982, 0.978, and 0.915, respectively, and the explanatory power of all models was very high.