• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.679-684
• /
• 2023

Venous puncture is widely used to obtain blood samples for pathological examination. Because the invasive venipuncture method using a needle is repeatedly performed, the pain suffered by the patient increases, so our research team pre-developed a miniaturized near-infrared (NIR) imaging system in advance. To improve the image quality of the acquired NIR images, this study aims to model the non-local means (NLM) algorithm, which is well known to be efficient in noise reduction, and analyze its applicability in the system. The developed NIR imaging system is based on the principle that infrared rays pass through dichroic and long-pass filters and are detected by a CMOS sensor module. The proposed NLM algorithm is modeled based on the principle of replacing the pixel from which noise is to be removed with a value that reflects the distances between surrounding pixels. After acquiring an NIR image with a central wavelength of 850 nm, the NLM algorithm was applied to segment the final vein area through histogram equalization. As a result, the coefficient of variation of the NIR image of the vein using the NLM algorithm was 0.247 on average, which was an excellent result compared to conventional filtering methods. In addition, the dice similarity coefficient value of the NLM algorithm was improved by 62.91 and 9.40%, respectively, compared to the median filter and total variation methods. In conclusion, we demonstrated that the NLM algorithm can acquire accurate segmentation of veins acquired with a NIR imaging system.

• Journal of Information Management
• /
• v.40 no.2
• /
• pp.95-115
• /
• 2009

Author resolution is to disambiguate same-name author occurrences into real individuals. For this, pair-wise author similarities are computed for author name entities, and then clustering is performed. So far, many studies have employed hierarchical clustering techniques for author disambiguation. However, various hierarchical clustering methods have not been sufficiently investigated. This study covers an empirical evaluation and analysis of hierarchical clustering applied to Korean author resolution, using multiple distance functions such as Dice coefficient, Cosine similarity, Euclidean distance, Jaccard coefficient, Pearson correlation coefficient.

• Korean Journal of Radiology
• /
• v.24 no.3
• /
• pp.235-246
• /
• 2023

Objective: It is difficult to predict the treatment response of tissue after stereotactic radiosurgery (SRS) because radiation necrosis (RN) and tumor recurrence can coexist. Our study aimed to predict tumor recurrence, including the recurrence site, after SRS of brain metastasis by performing a longitudinal tumor habitat analysis. Materials and Methods: Two consecutive multiparametric MRI examinations were performed for 83 adults (mean age, 59.0 years; range, 27-82 years; 44 male and 39 female) with 103 SRS-treated brain metastases. Tumor habitats based on contrast-enhanced T1- and T2-weighted images (structural habitats) and those based on the apparent diffusion coefficient (ADC) and cerebral blood volume (CBV) images (physiological habitats) were defined using k-means voxel-wise clustering. The reference standard was based on the pathology or Response Assessment in Neuro-Oncologycriteria for brain metastases (RANO-BM). The association between parameters of single-time or longitudinal tumor habitat and the time to recurrence and the site of recurrence were evaluated using the Cox proportional hazards regression analysis and Dice similarity coefficient, respectively. Results: The mean interval between the two MRI examinations was 99 days. The longitudinal analysis showed that an increase in the hypovascular cellular habitat (low ADC and low CBV) was associated with the risk of recurrence (hazard ratio [HR], 2.68; 95% confidence interval [CI], 1.46-4.91; P = 0.001). During the single-time analysis, a solid low-enhancing habitat (low T2 and low contrast-enhanced T1 signal) was associated with the risk of recurrence (HR, 1.54; 95% CI, 1.01-2.35; P = 0.045). A hypovascular cellular habitat was indicative of the future recurrence site (Dice similarity coefficient = 0.423). Conclusion: After SRS of brain metastases, an increased hypovascular cellular habitat observed using a longitudinal MRI analysis was associated with the risk of recurrence (i.e., treatment resistance) and was indicative of recurrence site. A tumor habitat analysis may help guide future treatments for patients with brain metastases.

• Annals of Surgical Treatment and Research
• /
• v.95 no.6
• /
• pp.297-302
• /
• 2018

Purpose: Increased robotic surgery is attended by increased reports of complications, largely due to limited operative view and lack of tactile sense. These kinds of obstacles, which seldom occur in open surgery, are challenging for beginner surgeons. To enhance robotic surgery safety, we created an augmented reality (AR) model of the organs around the thyroid glands, and tested the AR model applicability in robotic thyroidectomy. Methods: We created AR images of the thyroid gland, common carotid arteries, trachea, and esophagus using preoperative CT images of a thyroid carcinoma patient. For a preliminary test, we overlaid the AR images on a 3-dimensional printed model at five different angles and evaluated its accuracy using Dice similarity coefficient. We then overlaid the AR images on the real-time operative images during robotic thyroidectomy. Results: The Dice similarity coefficients ranged from 0.984 to 0.9908, and the mean of the five different angles was 0.987. During the entire process of robotic thyroidectomy, the AR images were successfully overlaid on the real-time operative images using manual registration. Conclusion: We successfully demonstrated the use of AR on the operative field during robotic thyroidectomy. Although there are currently limitations, the use of AR in robotic surgery will become more practical as the technology advances and may contribute to the enhancement of surgical safety.

• Journal of Microbiology and Biotechnology
• /
• v.20 no.9
• /
• pp.1266-1275
• /
• 2010

Isozyme and protein electrophoresis data from mycelial extracts of 27 isolates of Trichoderma harzianum, 10 isolates of T. aureoviride, and 10 isolates of T. longibrachiatum from Southern Peninsular Malaysia were investigated. The eight enzyme and a single protein pattern systems were analyzed. Three isozyme and total protein patterns were shown to be useful for the detection of three Trichoderma species. The isozyme and protein data were analyzed using the Nei and Li Dice similarity coefficient for pairwise comparison between individual isolates, species isolate group, and for generating a distance matrix. The UPGMA cluster analysis showed a higher degree of relationship between T. harzianum and T. aureoviride than to T. longibrachiatum. These results suggested that the T. harzianum isolates had high levels of genetic variation compared with the other isolates of Trichoderma species.

• Journal of Plant Biotechnology
• /
• v.33 no.2
• /
• pp.139-145
• /
• 2006

The present study is the first report of molecular variations in different accessions of Rauvolfia tetraphylla L.f, a medicinally important plant collected from seven locations of Andhra Pradesh, India. Molecular analysis was carried out using RAPD markers. Out of the 40 primers screened from OPA and OPC Kts, a total of 205 scorable polymorphic markers out of 397 total markers were generated. Polymorphism of 51.6% was found with 3 unique markers. Levels of genetic diversity within accessions i.e., the genetic distance ranged from 0.816-0.932. Cluster analysis based on Dice coefficient showed two major groups indicating that mostly in cross-pollinated plants, high levels of differentiation among accessions exists independent of geographical distance. Hence the results of the present study can be seen as a starting point for future researches on the population and evolutionary genetics of this species. Understanding such variation would also facilitate their use in various conservational management practices, rootstock breeding and hybridisation programmes.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.657-659
• /
• 2019

본 논문에서는 피부 이미지에서 건선 병변만을 가장 효과적으로 분할 할 수 있는 분할기법 선별을 목표로 한다. Interactive graph cuts (IGC)와 Level set method (LSM)를 사용하여 건선 영역을 분할한 후 Jaccard Index (JI)와 Dice Similarity Coefficient (DSC)을 사용하여 건선 영역에 효과적인 분할 방법을 제안한다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.10
• /
• pp.213-220
• /
• 2024

Retinal vessel analysis plays a vital role in the detection of some diseases. For example, diabetic retinopathy which may lead to blindness is one of the most common diseases that cause retinal blood vessel structure to change. However, doctors usually take a lot of time and money to collect and label training sets. Thus, automated vessel segmentation as the first step toward computer-aided analysis of fundus remains an active research avenue. We propose an automated Retinal vessel segmentation method based on the GAN network. Traditional image segmentation networks are unsupervised, and GAN is a new semi-supervised network due to adding a Discriminator. By training the discriminator network, we can capture the quality of the generator's output and drive it closer to the true image features. In our experiment, we use DRIVE dataset for training and testing. The final segmentation effect is represented by the Dice coefficient. Experimental results show that the GAN network can effectively improve the edge effect of image segmentation. Compared with the traditional U-net network, GAN shows about 1.55% higher segmentation accuracy.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.424-426
• /
• 2024

인공지능 기술이 급속도로 발전하고 있음에도 암환자의 방사선 치료 계획시 종양 경계를 임상의가 여전히 수동으로 설정하고 있다. 본 연구에서는 2 차원 및 3 차원 의료영상에서 종양 및 정상 조직을 자동으로 분할하고 시각화 해주는 소프트웨어 도구를 소개하고자 한다. 개발된 소프트웨어는 사용자의 개입을 최소화하고, 분할하고자 하는 관심 영역에 따라 파라미터 설정을 달리할 수 있다. 오픈 소프트웨어 3DSlicer 와 종양의 활성, 괴사, 부종 영역에 대한 분할 정확성을 DSC(Dice similarity coefficient)로 평가했으며, 비슷하거나 더 우수한 결과를 보였다. 특히, 초기 컨투어 설정부터 최종 분할 마스크 획득까지 처리 시간이 약 36.3% 더 빠른 결과를 보였다. 개발된 의료영상 분할 소프트웨어는 종양 및 정상 조직 분할을 용이하게 하여, 인공지능 지도 학습에 필요로 하는 라벨링 작업을 지원할 수 있을 것으로 사료된다.

• Journal of Life Science
• /
• v.15 no.2 s.69
• /
• pp.161-168
• /
• 2005

In this study, we did the molecular typing of 39 environmental Legionella pneumophila serogroup 1 isolates collected from 2001-2003 in Busan using the pulsed-filed gel electrophoresis (PFGE). PFGE of SfiI fragments were divided into 10 pulsotypes $(A\~J)$, corresponding to $<65\%$ similarity and a subtype within each pulsotype was characterized by $>84\%$ similarity. The major cluster was pulsotype E $(46.2\%)$, which included 18 isolates and was divided into 4 subtypes $(E1\~E4)$. PFGE of NotI fragments were divided into 8 pulsotypes $(a\~h)$, corresponding to $<60\%$ similarity and a subtype within each pulsotype was characterized by $100\%$ similarity. The major cluster was pulsotype f $(38.5\%)$, which included 15 isolates. The ATCC type strain L. pneumophila serogroup 1 was identified as a different molecular pulsotype compare to the Busan isolates. It is possible that L. pneumophila serogroup 1 isolated in Busan with specific DNA pattern is comparable with those isolation in other cities in Korea.