• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.139-146
• /
• 2023

Osteoporosis is a disease in which the risk of bone fractures increases due to a decrease in bone density caused by aging. Osteoporosis is diagnosed by measuring bone density in the total hip, femoral neck, and lumbar spine. To accurately measure bone density in the lumbar spine, the vertebral region must be segmented from the lumbar X-ray image. Deep learning-based automatic spinal segmentation methods can provide fast and precise information about the vertebral region. In this study, we used 695 lumbar spine images as training and test datasets for a deep learning segmentation model. We proposed a lumbar automatic segmentation model, CM-Net, which combines the center point of the spine and the modified U-Net network. As a result, the average Dice Similarity Coefficient(DSC) was 0.974, precision was 0.916, recall was 0.906, accuracy was 0.998, and Area under the Precision-Recall Curve (AUPRC) was 0.912. This study demonstrates a high-performance automatic segmentation model for lumbar X-ray images, which overcomes noise such as spinal fractures and implants. Furthermore, we can perform accurate measurement of bone density on lumbar X-ray images using an automatic segmentation methodology for the spine, which can prevent the risk of compression fractures at an early stage and improve the accuracy and efficiency of osteoporosis diagnosis.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.474-476
• /
• 2021

신경 교세포에서 발생하는 가장 흔한 뇌 악성종양인 교모세포종은 조기 진단 및 치료계획 수립이 중요하다. 주로 조영제를 통해 촬영된 T1CE 영상을 통해 암의 진단이 이뤄지는데, 최근 가돌리늄 기반 조영제 주입의 위험이 보고되고 있다. 의료영상에서 새로운 영상을 합성하는 GAN 모델과 영역분할에 대한 심층신경망 모델에 대한 연구가 활발히 진행되고 있다. 본 연구에서는 교모세포종 환자의 T1CE 영상의 생성과 암의 영역분할을 동시에 학습하는 하나의 모델을 제안한다. 제안된 모델의 성능은 평균 제곱오차, 최대신호대잡음비 등의 유사성 측정을 통해 평가되어 0.002, 55dB의 평균 결과 값을 보여준다.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.303-314
• /
• 2023

This study aimed to assess the practical feasibility of advanced deformable image registration (DIR) algorithms in radiotherapy by employing two distinct datasets. The first dataset included 14 4D lung CT scans and 31 head and neck CT scans. In the 4D lung CT dataset, we employed the DIR algorithm to register organs at risk and tumors based on respiratory phases. The second dataset comprised pre-, mid-, and post-treatment CT images of the head and neck region, along with organ at risk and tumor delineations. These images underwent registration using the DIR algorithm, and Dice similarity coefficients (DSCs) were compared. In the 4D lung CT dataset, registration accuracy was evaluated for the spinal cord, lung, lung nodules, esophagus, and tumors. The average DSCs for the non-learning-based SyN and NiftyReg algorithms were 0.92±0.07 and 0.88±0.09, respectively. Deep learning methods, namely Voxelmorph, Cyclemorph, and Transmorph, achieved average DSCs of 0.90±0.07, 0.91±0.04, and 0.89±0.05, respectively. For the head and neck CT dataset, the average DSCs for SyN and NiftyReg were 0.82±0.04 and 0.79±0.05, respectively, while Voxelmorph, Cyclemorph, and Transmorph showed average DSCs of 0.80±0.08, 0.78±0.11, and 0.78±0.09, respectively. Additionally, the deep learning DIR algorithms demonstrated faster transformation times compared to other models, including commercial and conventional mathematical algorithms (Voxelmorph: 0.36 sec/images, Cyclemorph: 0.3 sec/images, Transmorph: 5.1 sec/images, SyN: 140 sec/images, NiftyReg: 40.2 sec/images). In conclusion, this study highlights the varying clinical applicability of deep learning-based DIR methods in different anatomical regions. While challenges were encountered in head and neck CT registrations, 4D lung CT registrations exhibited favorable results, indicating the potential for clinical implementation. Further research and development in DIR algorithms tailored to specific anatomical regions are warranted to improve the overall clinical utility of these methods.

• 한국컴퓨터그래픽스학회논문지
• /
• 제30권1호
• /
• pp.11-17
• /
• 2024

폐암은 크기가 다양하고 유사한 밝기값을 갖는 주변 구조물이 존재하기 때문에 흉부 CT 영상에서 폐암을 정확하게 분할하는 것이 어렵다. 이러한 문제를 해결하기 위해 본 논문에서는 심층 감독을 포함하고 UNet3+를 백본으로 사용하는 폐암 분할 네트워크를 제안한다. 또한, 픽셀 기반, 영역 기반 및 형태 기반의 3가지 구성 요소로 이루어진 하이브리드 병변 초점 손실함수를 제안한다. 이를 통해 배경에 비해 작은 영역을 차지하는 폐암 부분에 집중하고, 불명확한 경계를 처리하는데 도움이 되는 형태 정보를 고려할 수 있다. 제안 방법을 UNet 및 UNet3+와 비교 실험을 통해 검증하였고, 제안 방법은 모든 폐암 크기에서 DSC 측면에서 가장 우수한 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• Korean Circulation Journal
• /
• 제54권1호
• /
• pp.30-39
• /
• 2024

Background and Objectives: Intravascular ultrasound (IVUS) evaluation of coronary artery morphology is based on the lumen and vessel segmentation. This study aimed to develop an automatic segmentation algorithm and validate the performances for measuring quantitative IVUS parameters. Methods: A total of 1,063 patients were randomly assigned, with a ratio of 4:1 to the training and test sets. The independent data set of 111 IVUS pullbacks was obtained to assess the vessel-level performance. The lumen and external elastic membrane (EEM) boundaries were labeled manually in every IVUS frame with a 0.2-mm interval. The Efficient-UNet was utilized for the automatic segmentation of IVUS images. Results: At the frame-level, Efficient-UNet showed a high dice similarity coefficient (DSC, 0.93±0.05) and Jaccard index (JI, 0.87±0.08) for lumen segmentation, and demonstrated a high DSC (0.97±0.03) and JI (0.94±0.04) for EEM segmentation. At the vessel-level, there were close correlations between model-derived vs. experts-measured IVUS parameters; minimal lumen image area (r=0.92), EEM area (r=0.88), lumen volume (r=0.99) and plaque volume (r=0.95). The agreement between model-derived vs. expert-measured minimal lumen area was similarly excellent compared to the experts' agreement. The model-based lumen and EEM segmentation for a 20-mm lesion segment required 13.2 seconds, whereas manual segmentation with a 0.2-mm interval by an expert took 187.5 minutes on average. Conclusions: The deep learning models can accurately and quickly delineate vascular geometry. The artificial intelligence-based methodology may support clinicians' decision-making by real-time application in the catheterization laboratory.

• Bulletin of the Korean Chemical Society
• /
• 제23권11호
• /
• pp.1531-1540
• /
• 2002

With the invention of the inlaying technique for celadon in the latter half of the 12th century, the Koryo potters reached a new height of artistic and scientific achievement in ceramics chemical technology. Inlaid celadon shards, collected in 1991 during the surface investigation of Kangjin kilns found on the southwestern shore of South Korea, were imbedded in epoxy resin and polished for cross-section examination. Backscattered electron images were taken with an electron microprobe equipped with an energy dispersive spectrometer. The spectrometer was also used to determine the composition of micro-areas. Porcelain stone, weathered rock of quartz, mica, and feldspar composition were found to be the raw material for the body and important components in the glaze and white inlay. The close similarity between glaze and black inlay in the microstructure suggests that the glaze material was modified by adding clay with high iron content, such as biotite, for use as black inlay. The deep soft translucent quality of celadon glaze is brought about by its microstructure of bubbles, remnant and devitrified minerals, and the schlieren effect.

• 전기전자학회논문지
• /
• 제24권2호
• /
• pp.514-522
• /
• 2020

Continuous Learning 환경에서 인공 신경망의 학습이 진행됨에 따라 이전에 학습했던 데이터의 정보를 잊는 Catastrophic Forgetting 현상이 있다. 서로 다른 Domain을 갖는 데이터 사이에서 쉽게 발생한다. 이 현상을 제어하기 위해 신경망의 출력 분포를 통해 이전에 학습된 데이터와 새로 학습할 데이터들의 관계를 측정하는 방법과 이 측정값을 사용하여 Catastrophic Forgetting 현상을 완화하는 방법을 제시한다. 평가를 위해 MNIST, EMNIST 데이터를 사용하였고 실험 결과, 이전 데이터에 대한 정확도가 평균적으로 약 22.37% 향상되었다.

• 지식경영연구
• /
• 제8권1호
• /
• pp.15-28
• /
• 2007

In the age where the Internet changes everything, even the earth has become flat. The boarders between nations, locations, times, and industries are not meaningful, and no single company can do the whole process well. Therefore, various types of 'Value network' and 'Relation web' emerge for moving first and learning fast. Both the relationship maturity model (RMM) proposed and the partnership management initiatives at SKT demonstrate that the concept is important, and that the final goal can be reached only through a series of critical outcome at each phase. In particular, recognizing as core infrastructures various online/offline channels, deep trust, and rich communications is an important finding for a successful relationship management. Also, related literatures suggest the following key factors to be influential in more than two phases: professionalism including expertise, similarity, channel infrastructure, trustful/trustworthy, and absorptive capacity. Based on these findings, future efforts need to be put on the research & development of related measurement and management tools. It is hoped that more dance with their partners through these efforts.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.