• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1019-1022
• /
• 2019

최근의 영상 처리 분야는 딥러닝 기법들의 성능이 입증됨에 따라 다양한 분야에서 이와 같은 기법들을 활용해 영상에 대한 분류, 분석, 검출 등을 수행하려는 시도가 활발하다. 그중에서도 의료 진단 보조 역할을 할 수 있는 의료 영상 분석 소프트웨어에 대한 기대가 증가하고 있는데, 본 연구에서는 캡슐내시경 영상에 주목하였다. 캡슐내시경은 주로 소장 촬영을 목표로 하며 식도부터 대장까지 약 8~10시간 동안 촬영된다. 이로 인해 CT, MR, X-ray와 같은 다른 의료 영상과 다르게 하나의 데이터 셋이 10~15만 장의 이미지를 갖는다. 일반적으로 캡슐내시경 영상을 판독하는 순서는 위장관 교차점(Z-Line, 유문판, 회맹판)을 기준으로 위장관 랜드마크(식도, 위, 소장, 대장)를 구분한 뒤, 각 랜드마크 별로 병변 정보를 찾아내는 방식이다. 그러나 워낙 방대한 영상 데이터를 가지기 때문에 의사 혹은 의료 전문가가 영상을 판독하는데 많은 시간과 노력이 소모되고 있다. 본 논문의 목적은 캡슐내시경 영상의 판독에서 모든 환자에 대해 공통으로 수행되고, 판독하는 데 많은 시간을 차지하는 위장관 랜드마크를 찾는 것에 있다. 이를 위해, 위장관 랜드마크를 식별할 수 있는 CNN 학습 모델을 설계하였으며, 더욱 효과적인 학습을 위해 전처리 과정으로 학습에 방해가 되는 학습 노이즈 영상들을 제거하고 위장관 랜드마크 별 특징 분석을 진행하였다. 총 8명의 환자 데이터를 가지고 학습된 모델에 대해 평가 및 검증을 진행하였는데, 무작위로 환자 데이터를 샘플링하여 학습한 모델을 평가한 결과, 평균 정확도가 95% 가 확인되었으며 개별 환자별로 교차 검증 방식을 진행한 결과 평균 정확도 67% 가 확인되었다.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.2
• /
• pp.131-136
• /
• 2013

Purpose: Quantitative comparative evaluation of the difference in eye lens absorbed dose when measured by MVCT and kV-CBCT, though such a dose was not included in the original IMRT treatment plan for the nasopharyngeal cancer patient. Materials and Methods: We used CT (Lightspeed Ultra 16, General Electric, USA) against an Anderson rando phantom (Alderson Research Laboratories Inc, USA) and established the plan for tomotherapy treatment (Tomotherapy, Inc, USA) and linear accelerator treatment (Pinnacle 8.0, Philips Medicle System) for the achieved CT images on the same condition with the nasopharyngeal cancer patient treatment plan. Then, align the ther-moluminescence dosimeter (TLD100 Harshaw, USA) with the eye lens, shot the lens with Tomotherapy MVCT under 3 conditions (Fine, Normal, and Coarse), and shot both lenses with kV-CBCT under 2 conditions (Low Dose Head and Standard Dose Head) 3 times each. Results: When we analyzed the eye lens absorbed dose according to MVCT and kV-CBCT images by using both Tomotherapy and Pinacle 8.0, we achieved the following result; According to Tomotherapy MVCT, RT 0.8257 cGy in the Coarse mode, LT 0.8137 cGy, RT 1.089 cGy and LT 1.188 cGy in the Normal mode, and RT 2.154 cGy and LT 2.082 cGy in the Fine mode. According to Pinacle 8.0 kV-CBCT, RT 0.2875 cGy and LT 0.1676 cGy in the Standard Dose mode and RT 0.1648 cGy and LT 0.1212 cGy in the Low-Dose mode. In short, the MVCT result was significantly different from that of kV-CBCT, up to 20 times. Conclusion: We think kV-CBCT is more effective for reducing the amount of radiation which a patient is receiving during intensity modulated radiation treatment for other purposes than treatment than MVCT, when we consider the absorbed dose only from the viewpoint of image-guided radiation therapy. Besides, we understood the amount of radiation is too sensitive to the shooting condition, even when we use the same equipment.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.32 no.1
• /
• pp.60-69
• /
• 2016

Purpose: The objective of this study was to compare the accuracy of digital models from 3 dimentional (3D) optical scanner and cone beam computed tomography (CBCT). Materials and Methods: We obtained digital models from 11 pairs of stone casts using a 3D optical scanner and a CBCT, and compared the accuracy of the models. Results: The error range of average positive distance was 0.059 - 0.117 mm and negative distance was 0.066 - 0.146 mm. Statistically (P < 0.05), average positive distance was larger than $70{\mu}m$ and shorter than $100{\mu}m$, and that of negative distance was larger than $100{\mu}m$ and shorter than $120{\mu}m$. Conclusion: We concluded that the accuracy of digital models generated from CBCT is not appropriate to make final prostheses. However, it may be acceptable for provisional restorations and orthodontic diagnoses with respect to the accuracy of the digitalization.

• The korean journal of orthodontics
• /
• v.40 no.2
• /
• pp.66-76
• /
• 2010

Objective: Obstructive sleep apnea (OSA) is a common disorder which is characterized by a recurrence of entire or partial collapse of the pharyngeal airway during sleep. A given tidal volume must traverse the soft tissue tube structure of the upper airway, so the tendency for airway obstruction is influenced by the geometries of the duct and characteristics of the airflow in respect to fluid dynamics. Methods: Individualized 3D FEA models were reconstructed from pretreatment computerized tomogram images of three patients with obstructive sleep apnea. 3D computational fluid dynamics analysis was used to observe the effect of airway geometry on the flow velocity, negative pressure and pressure drop in the upper airway at an inspiration flow rate of 170, 200, and 230 ml/s per nostril. Results: In all 3 models, large airflow velocity and negative pressure were observed around the section of minimum area (SMA), the region which narrows around the velopharynx and oropharynx. The bigger the Out-A (outlet area)/ SMA-A (SMA area) ratio, the greater was the change in airflow velocity and negative pressure. Conclusions: Pressure drop meaning the difference between highest pressure at nostril and lowest pressure at SMA, is a good indicator for upper airway resistance which increased more as the airflow volume was increased.

• The Journal of Korean Society for Radiation Therapy
• /
• v.19 no.1
• /
• pp.43-49
• /
• 2007

Purpose: The aim of this study was the clinical implementation of IGRT using KV CBCT for setup correction in radiation therapy. Materials and Methods: We selected 9 patients (3 patient for each region; head, body, pelvis)and acquired 135 CBCT images with CLINAC iX (Varian medical system, USA). During the scan, the required time was measured. We analyzed the result in 3 direction; vertical, longitudinal, lateral. Results: The mean setup errors at the couch position of vertical, lateral, and longitudinal direction were 0.07, 0.12, and 0.1 cm in the head region, 0.3, 0.26, and 0.22 cm in the body region, 0.21, 0.18, and 0.15 cm in the pelvis region respectively. The mean time required for CBCT was $6{\sim}7$ minute. Conclusion: The CBCT on the LINAC provides the capacity for soft tissue imaging in the treatment position and real time monitoring during treatment delivery. With presented workflow, the setup correction within reasonable time for more accurate radiation therapy is possible. And it's image can be very useful for adaptive radiation therapy(ART) in the future with improved image quality.

• Journal of the Korean Academy of Esthetic Dentistry
• /
• v.27 no.2
• /
• pp.82-96
• /
• 2018

3D printing is a process of producing 3d object from a digital file in STL format by joining, bonding, sintering or polymerizing small volume elements by layer. The various type of 3d printing is classified according to the additive manufacturing strategies. Among the types of 3D printer, SLA(StereoLithography Apparatus) and DLP(Digital Light Processing) 3D printer which use polymerization by light source are widely used in dental office. In the previous study, a full-arch scale 3d printed model is less precise than a conventional stone model. However, in scale of quadrant arch, a 3d printed model is significantly precise than a five-axis milled model. Using $3^{rd}$ Party dental CAD program, full denture, provisional crowns and diagnostic wax-up model are fabricated by 3d printer in dental office. In Orthodontics, based on virtual setup model, indirect bracket bonding tray can be generated by 3d printer. And thermoforming clear aligner can be fabricated on the 3d printed model. 3D printed individual drilling guide enable the clinician to place the dental implant on the proper position. The development of layer additive technology enhance the quality of 3d printing object and shorten the operating time of 3D printing. In the near future, traditional dental laboratory process such as casting, denture curing will be replaced by digital 3D printing.

• The Journal of Korean Society for Radiation Therapy
• /
• v.26 no.1
• /
• pp.91-98
• /
• 2014

Purpose : To compare the dosimetry for the left breast cancer treatment between three dimensional conformal radiation radiotherapy (3D-CRT) and Hybrid planning and to estimate usefulness of Hybrid planning Materials and Methods : Five patients with left breast cancer were included in the study. They were planned using several different radiotherapy techniques including: 1)open rectangular field, 2)tangential wedge-based field 3)field in field, 4)hybrid planning(energy, wedge combine). For each patient planning was using Light Speed RT-16 CT and PINNACLE planning system-ver.9.2. Hybrid plan was made using same system and using the same targets and optimization goals. We comparing the Homogeneity Index(HI), normal organs at the does-volume histogram(DVH) Results : In all plans, the Homogeneity Index(HI) of Hybrid planning was significantly better than other. Dose comparison of HI= 2D-RT:38.32, TW:38.32, FIF:29.22, HYBRID:30.57. 2D-RT, TW, FIF Hybrid$V_{75_-lung}$=112.33, 125.14, 121.3, 123.78. $V_{50_-lung}$=155.43, 159.62, 157.96, 159.06. $V_{25_-lung}$=199.86, 200.22, 198.65, 200.31. $V_{50_-heart}$=26.07, 27.1, 26.85, 27.17 $V_{30_-heart}$=33.71, 34.37, 34.15, 34.65 Conclusion : In summary, 3D-CRT, Hybrid planning techniques were found to have acceptableCTV coverage in our study. However the Hybrid planning increased radiation dose exposure to normal tissue. If you apply for treatment of inhomogeneity areas like lung, For best results will be achieved.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.21 no.1
• /
• pp.15-22
• /
• 2017

Purpose During Brain SPECT study, critical factor for proper study with $^{99m}Tc-ECD$ or $^{99m}Tc-HMPAO$ is one of the important causes to patent's movement. It causes both improper diagnosis and examination failure. In this study, we evaluated the effect of Dynamic Continuous Mode Acquisition compared to Step and Shoot Mode to raise efficacy and reject the data set with movement, as well as, be reconstructed in certain criteria. Materials and Methods Deluxe Jaszczak phantom and Hoffman 3D Brain phantom were used to find proper standard data set and exact time. Step and Shoot Mode and Dynamic Continuous Mode Acquisition were performed with SymbiaT16. Firstly, Deluxe Jaszczak phantom was filled with $Na^{99m}TcO_4$ 370 MBq and obtained in 60 minutes to check spatial resolution compared with Step and Shoot Mode and Dynamic Continuous Mode. The second, the Hoffman 3D Phantom filled with $Na^{99m}TcO_4$ 74 MBq was acquired for 15 Frame/minutes to evaluate visual assessment and quantification. Finally, in the Deluxe Jaszczak phantom, Spheres and Rods were measured by MI Apps program as well as, checking counts with the frontal lobe, temporal lobe, occipital lobe, cerebellum and hypothalamus parts was performed in the Hoffman 3D Brain Phantom. Results In Brain SPECT Study, using Dynamic Continuous Mode rather than current Step and Shoot Mode, we can do the reading using the 20 to 50 % of the acquired image, and during the test if the patient moves, we can remove unneeded image to reduce the rate of restudy and reinjection. Conclusion Dynamic Continuous Mode in Brain study condition enhances effects compared to Step and Shoot Mode. And also is powerful method to reduce reacquisition rate caused by patient movement. The findings further indicate that it suggest rejection limit to maintain clinical value with certain reconstruction factors compared with Tomo data set. Further examination to improve spatial resolution, SPECT/CT should be the answer for that.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.881-887
• /
• 2023

This study aims to analyze the development and current trends of AI-based medical imaging devices commercialized in South Korea. As of September 30, 2023, there were a total of 186 AI-based medical devices licensed, certified, and reported to the Korean Ministry of Food and Drug Safety, of which 138 were related to imaging. The study comprehensively examined the yearly approval trends, equipment types, application areas, and key functions from 2018 to 2023. The study found that the number of AI medical devices started from four products in 2018 and grew steadily until 2023, with a sharp increase after 2020. This can be attributed to the interaction between the advancement of AI technology and the increasing demand in the medical field. By equipment, AI medical devices were developed in the order of CT, X-ray, and MR, which reflects the characteristics and clinical importance of the images of each equipment. This study found that the development of AI medical devices for specific areas such as the thorax, cranial nerves, and musculoskeletal system is active, and the main functions are medical image analysis, detection and diagnosis assistance, and image transmission. These results suggest that AI's pattern recognition and data analysis capabilities are playing an important role in the medical imaging field. In addition, this study examined the number of Korean products that have received international certifications, particularly the US FDA and European CE. The results show that many products have been certified by both organizations, indicating that Korean AI medical devices are in line with international standards and are competitive in the global market. By analyzing the impact of AI technology on medical imaging and its potential for development, this study provides important implications for future research and development directions. However, challenges such as regulatory aspects, data quality and accessibility, and clinical validity are also pointed out, requiring continued research and improvement on these issues.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.2
• /
• pp.167-173
• /
• 2013

Purpose: This study is to evaluate the efficacy of the CBCT and EXACTRAC the image on the spine stereotactic body radiation treatment. Materials and Methods: The study compared the accuracy of the dose distribution for changes in the real QA phantom for The shape of the body of the phantom was performed. Novalis treatment artificially set up at the center and to the right, on the Plan 1 mm, 2 mm, 3 mm in front 1 mm, 2 mm, 3 mm and upwards 1 mm, 2 mm, 3 mm and $0.5^{\circ}$ by moving side to side Exactrac error correction and error values of CBCT and plan changes on the dose distribution were recorded and analyzed. Results: Cubic Phantom of the experimental error, the error correction Exactrac X-ray 6D Translation in the direction of the 0.18 mm, Rotation direction was $0.07^{\circ}$. Translation in the direction of the 3D CBCT 0.15 mm Rotation direction was $0.04^{\circ}$. DVH dose distribution using the results of the AP evaluate the change in the direction of change was greatest when moving. Conclusion: ExacTrac image-guided radiation therapy with a common easy and fast to get pictures from all angles, from the advantage of CBCT showed a potential alternative. But every accurate information compared with CT treatment planning and treatment of patients with more accurate than the CBCT ExacTrac the location provided. Changes in the dose distribution in the experiment results show that the treatment of spinal SBRT set up some image correction due to errors at the target and enter the spinal cord dose showed that significant differences appear.