• Radiation Oncology Journal
• /
• v.25 no.1
• /
• pp.54-61
• /
• 2007

[ $\underline{Purpose}$ ]: The purpose of this study is to develop a practical method for determining accurate marker positions for prostate cancer radiotherapy using CT images and kV x-ray images obtained from the use of the on- board imager (OBI). $\underline{Materials\;and\;Methods}$: Three gold seed markers were implanted into the reference position inside a prostate gland by a urologist. Multiple digital image processing techniques were used to determine seed marker position and the center-of-mass (COM) technique was employed to determine a representative reference seed marker position. A setup discrepancy can be estimated by comparing a computed $COM_{OBI}$ with the reference $COM_{CT}$. A proposed algorithm was applied to a seed phantom and to four prostate cancer patients with seed implants treated in our clinic. $\underline{Results}$: In the phantom study, the calculated $COM_{CT}$ and $COM_{OBI}$ agreed with $COM_{actual}$ within a millimeter. The algorithm also could localize each seed marker correctly and calculated $COM_{CT}$ and $COM_{OBI}$ for all CT and kV x-ray image sets, respectively. Discrepancies of setup errors between 2D-2D matching results using the OBI application and results using the proposed algorithm were less than one millimeter for each axis. The setup error of each patient was in the range of $0.1{\pm}2.7{\sim}1.8{\pm}6.6\;mm$ in the AP direction, $0.8{\pm}1.6{\sim}2.0{\pm}2.7\;mm$ in the SI direction and $-0.9{\pm}1.5{\sim}2.8{\pm}3.0\;mm$ in the lateral direction, even though the setup error was quite patient dependent. $\underline{Conclusion}$: As it took less than 10 seconds to evaluate a setup discrepancy, it can be helpful to reduce the setup correction time while minimizing subjective factors that may be user dependent. However, the on-line correction process should be integrated into the treatment machine control system for a more reliable procedure.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.155-163
• /
• 2019

This paper proposes a new methodology to recognize cracks on asphalt road surfaces using the image data obtained with drones. The target section was Yuseong-daero, the main highway of Daejeon. Furthermore, two object detection algorithms, such as Tiny-YOLO-V2 and Faster-RCNN, were used to recognize cracks on road surfaces, classify the crack types, and compare the experimental results. As a result, mean average precision of Faster-RCNN and Tiny-YOLO-V2 was 71% and 33%, respectively. The Faster-RCNN algorithm, 2Stage Detection, showed better performance in identifying and separating road surface cracks than the Yolo algorithm, 1Stage Detection. In the future, it will be possible to prepare a plan for building an infrastructure asset-management system using drones and AI crack detection systems. An efficient and economical road-maintenance decision-support system will be established and an operating environment will be produced.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.10-17
• /
• 2017

This study is the first attempt to raise face recognition ability through machine learning algorithm and apply to CRM's information gathering, analysis and application. In other words, through face recognition of VIP customer in distribution field, we can proceed more prompt and subdivided customized services. The interest in machine learning, which is used to implement artificial intelligence, has increased, and it has become an age to automate it by using machine learning beyond the way that a person directly models an object recognition process. Among them, Deep Learning is evaluated as an advanced technology that shows amazing performance in various fields, and is applied to various fields of image recognition. Face recognition, which is widely used in real life, has been developed to recognize criminals' faces and catch criminals. In this study, two image analysis models, TF-SLIM and Inception-V3, which are likely to be used for criminal face recognition, were selected, analyzed, and implemented. As an evaluation criterion, the image recognition model was evaluated based on the accuracy of the face recognition program which is already being commercialized. In this experiment, it was evaluated that the recognition accuracy was good when the accuracy of the image classification was more than 90%. A limit of our study which is a way to raise face recognition is left as a further research subjects.

• Korean Journal of Digital Imaging in Medicine
• /
• v.12 no.2
• /
• pp.113-117
• /
• 2010

This research attempts to qualitatively evaluate the intensity change by radiopharmaceuticals and obtain computed tomography using phantom injected with various nuclide. Cylindrical phantom is used for comparing and analysing the effect on diagnosis image during radiopharmaceuticals inspection. Inside of the phantom, water is injected and computed tomography image is scanned. During nuclear medicine invitro, frequently used radiopharmaceuticals, $^{99m}TcO_4$ 20 mCi and $^{18}F$ 14 mCi, is diluted in the water phantom and scanned in the same method. Traverse image obtained by CT scan is divided into six traverse image in the same slice of each scanned image. CT-number(HU) value of 10 measuring point is measured in 2 cm interval based on the center of the phantom. Measured HU value, based on the water phantom, is compared with the image after injecting $^{99m}TcO_4$ and $^{18}F$. Average scale of water is 2.8~1.6 HU, $^{99m}TcO_4$ is 3.0~1.6 HU and $^{18}F$ is 1.2~0 HU. Average of water is $2.3{\pm}0.17$ HU, $^{99m}TcO_4$ is $2.2{\pm}0.85$ HU and F-18 is $0.7{\pm}0.95$ HU. Based on water, reduced value of about 0.1 HU and about 0.5 HU is acquired from $^{99m}TcO_4$ and F-18. Radionuclide used in nuclear medicine inspection utilizes 100~200 KeV energy and obtains image through scintillation camera and PET-CT utilizes 511 KeV positron annihilation energy to obtain image. What we learned from this research is that gamma rays from these energies used in CT scan for diagnosis purpose or radioactive therapy plan can change the intensity of the image. The nuclear medicine inspection for reducing the effect of emitted gamma ray diagnosis image should be obtained after a period of time considering half-life which would be reduced distortion or changed in image.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.273-276
• /
• 2001

The origin of image-slicking in metal-insulator-metal type thin-film-diode(TFD) LCDs is the asymmetric current-voltage(I-V) characteristic of TFD element. we developed that MIM-LCDs have reduced-image-sticking and perfect symmetry characteristic. One-Time Post-Annealing (OPTA) heat treatment process was introduced to reduce the asymmetry and shift of the I-V characteristics, respectively. OPTA means that the whole layers of lower metal, insulator, and uuper metal are annealed at one time. The treatment temperatures and fabricated process of TFD element were under foot. Also, this low temperature fabricated process allows the application of plastic substrates.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.398-400
• /
• 2019

Faced with the increasing demand for image recognition on mobile devices, how to run convolutional neural network (CNN) models on mobile devices with limited computing power and limited storage resources encourages people to study efficient model design. In recent years, many effective architectures have been proposed, such as mobilenet_v1, mobilenet_v2 and PeleeNet. However, in the process of feature selection, all these models neglect some information of shallow features, which reduces the capture of shallow feature location and semantics. In this study, we propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFA-10 data set increased by 4.0%.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.47-54
• /
• 1998

With the increasing popularity of the use of large-volume image database in various application, it becomes imperative to build an efficient and fast retrieval system to browse through the entire database. We present a new method for a content-based image retrieval by using a variable block size and block matching algorithm. Proposed approach is reflecting image features that exploit visual cues such as color and space allocation of image and is getting the fast retrieval time by automatical convergence of retrieval times which adapt to wanting similarity value. We have implemented this technique and tested it for a database of approximately 150 images. The test shows that a 1.9 times fast retrieval time compare to J & V algorithm at the image retrieval efficiency 0.65 and that a 1.83 times fast retrieval time compare to predefined fixed block size.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.2
• /
• pp.179-186
• /
• 2016

Purpose : To figure out if the treatment plan for rectum, bladder and prostate that have a lot of interfraction errors satisfies dosimetric limits without adaptive plan by analyzing MR image. Materials and Methods : This study was based on 5 prostate cancer patients who had IMRT(total dose: 70Gy) Using ViewRay MRIdian System(ViewRay, ViewRay Inc., Cleveland, OH, USA) The treatment plans were made on the same CT images to compare with the plan quality according to adaptive plan, and the Eclipse(Ver 10.0.42, Varian, USA) was used. After registrate the 5 treatment MR images to the CT images for treatment plan to analyze the interfraction changes of organ, we measured the dose volume histogram and the changes of the absolute volume for each organ by appling the first treatment plan to each image. Over 5 fractions, the total dose for PTV was $V_{36.25}$ Gy $${\geq_-}$$ 95%. To confirm that the prescription dose satisfies the SBRT dose limit for prostate, we measured $V_{100%}$, $V_{95%}$, $V_{90%}$ for CTV and $V_{100%}$, $V_{90%}$, $V_{80%}$ $V_{50%}$ of rectum and bladder. Results : All dose average value of CTV, rectum and bladder satisfied dose limit, but there was a case that exceeded dose limit more than one after analyzing the each image of treatment. After measuring the changes of absolute volume comparing the MR image of the first treatment plan with the one of the interfraction treatment, the difference values were maximum 1.72 times at rectum and maximum 2.0 times at bladder. In case of rectum, the expected values were planned under the dose limit, on average, $V_{100%}=0.32%$, $V_{90%}=3.33%$, $V_{80%}=7.71%$, $V_{50%}=23.55%$ in the first treatment plan. In case of rectum, the average of absolute volume in first plan was 117.9 cc. However, the average of really treated volume was 79.2 cc. In case of CTV, the 100% prescription dose area didn't satisfy even though the margin for PTV was 5 mm because of the variation of rectal and bladder volume. Conclusion : There was no case that the value from average of five fractions is over the dosimetric limits. However, dosimetric errors of rectum and bladder in each fraction was significant. Therefore, the precise delivery is needed in case of prostate SBRT. The real-time tracking and adaptive plan is necessary to meet the precision delivery.

• Journal of Radiation Protection and Research
• /
• v.35 no.2
• /
• pp.69-76
• /
• 2010

Prototype double-scattering Compton camera, which consists of three gamma-ray detectors, that is, two double-sided silicon strip detectors (DSSDs) as scatterer detectors and a NaI(Tl) scintillation detector as an absorber detector, could provide high imaging resolution with a compact system. In the present study, the energy resolution and the timing resolution of component detectors were measured, and the parameters affecting the energy resolution of the DSSD were examined in terms of equivalent noise charge (ENC). The energy resolutions of the DSSD-1 and DSSD-2 were, in average, $25.2keV{\pm}0.8keV$ FWHM and $31.8keV{\pm}4.6keV$ FWHM at the 59.5 keV peak of $^{241}Am$, respectively. The timing resolutions of the DSSD and NaI(Tl) scintillation detector were 57.25 ns FWHM and 7.98 ns FWHM, respectively. In addition, the Compton image was obtained for a point-like $^{137}Cs$ gamma source with double-scattering Compton camera. From the present experiment, the imaging resolution of 8.4 mm FWHM (angular resolution of $8.1^{\circ}$ FWHM), and the imaging sensitivity of $1.5{\times}10^{-7}$ (intrinsic efficiency of $1.9{\times}10^{-6}$) were obtained.

• Journal of radiological science and technology
• /
• v.39 no.1
• /
• pp.43-49
• /
• 2016

In this study, equivalent dose and LET (Linear Energy Transfer) calibration of CR-39 SSNTD (Solid State Nuclear Track Detector) were performed using 400 MeV/u C heavy ions in HIMAC (Heavy Ion Medical Accelerator in Chiba) for high LET radiation therapy. The irradiated CR-39 SSNDTs were etched according the etching condition of JAXA (Japan Aerospace Exploration Agency). And the etched SSNTDs were analyzed by using Image J. Determined frequency mean dose (${\bar{y_D}}$)and dose-mean lineal energy (${\bar{y_F}}$)of 400 MeV/u C are about 8.5keV/mm and 10.1 keV/mm, respectively by using the CR-39 SSNTD. This value is very similar to the results calculated by GEANT4 Monte Carlo simulation and measured with TEPC (Tissue Equivalent Proportional Counter) active radiation detector. We could determine the equivalent dose and LET calibration factors of CR-39. And we confirmed that the CR-39 SSNTD was useful for high LET radiation dosimetry in hadron radiotherapy.