• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.349-355
• /
• 2012

Information technology improves convenience, safety, and performance of automobiles. Recently, a lot of algorithms are studied to provide safety and environment information for driving, and lane detection algorithm is one of them. In this paper, we propose a lane detection algorithm that reduces the amount of calculation by reducing region of interest (ROI) after preprocessing. The proposed algorithm reduces the area of ROI a lot by determining the candidate regions near lane boundaries as V-ROI so that the amount of calculation is reduced. In addition, the amount of calculation can be maintained almost the same regardless of the resolutions of the input images by compressing the images since the lane detection algorithm does not require high resolution. The proposed algorithm is implemented using C++ and OpenCV library and is verified to work at 30 fps for realtime operation.

• Progress in Medical Physics
• /
• v.27 no.1
• /
• pp.1-7
• /
• 2016

In this work, we considered a compressed-sensing (CS)-based image deblurring scheme with a total-variation (TV) regularization penalty for improving image characteristics in digital tomosynthesis (DTS). We implemented the proposed image deblurring algorithm and performed a systematic simulation to demonstrate its viability. We also performed an experiment by using a table-top setup which consists of an x-ray tube operated at $90kV_p$, 6 mAs and a CMOS-type flat-panel detector having a $198-{\mu}m$ pixel resolution. In the both simulation and experiment, 51 projection images were taken with a tomographic angle range of ${\theta}=60^{\circ}$ and an angle step of ${\Delta}{\theta}=1.2^{\circ}$ and then deblurred by using the proposed deblurring algorithm before performing the common filtered-backprojection (FBP)-based DTS reconstruction. According to our results, the image sharpness of the recovered x-ray images and the reconstructed DTS images were significantly improved and the cross-plane spatial resolution in DTS was also improved by a factor of about 1.4. Thus the proposed deblurring scheme appears to be effective for the blurring problems in both conventional radiography and DTS and is applicable to improve the present image characteristics.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.523-530
• /
• 2019

The purpose of this study was to obtain the K-edge images using a spectral CT system based on a photon-counting detector and implement the 3D fusion imaging using the conventional and spectral CT images. Also, we evaluated the clinical feasibility of the 3D fusion images though the quantitative analysis of image quality. A spectral CT system based on a CdTe photon-counting detector was used to obtain K-edge images. A pork phantom was manufactured with the six tubes including diluted iodine and gadolinium solutions. The K-edge images were obtained by the low-energy thresholds of 35 and 52 keV for iodine and gadolinium imaging with the X-ray spectrum, which was generated at a tube voltage of 100 kVp with a tube current of $500{\mu}A$. We implemented 3D fusion imaging by combining the iodine and gadolinium K-edge images with the conventional CT images. The results showed that the CNRs of the 3D fusion images were 6.76-14.9 times higher than those of the conventional CT images. Also, the 3D fusion images was able to provide the maps of target materials. Therefore, the technique proposed in this study can improve the quality of CT images and the diagnostic efficiency through the additional information of target materials.

• Journal of the Korean Society of Radiology
• /
• v.17 no.7
• /
• pp.1157-1164
• /
• 2023

This study measures the additional dose for each treatment area using kV X-ray based OBI (On-Board Imager) and CBCT (Cone-Beam CT), which have excellent spatial resolution and contrast, and evaluates the adequacy and stability of radiation management aspects of IGRT. The subjects of the experiment were examined with OBI and CBCT attached to a linear accelerator (Clinac IX), and ring-shaped Halcyon CBCT under imaging conditions for each treatment area, and the dose at the center was measured using an ion chamber. OBI single fraction dose was measured as 0.77 mGy in the head area, 3.04 mGy in the chest area, and 7.19 mGy in the pelvic area. The absorbed doses from the two devices, Clinac IX CBCT and Halcyon CBCT, were measured to be similar in the pelvic area, at 70.04 mGy and 70.45 mGy. and in chest CBCT, the Clinac IX absorbed dose (70.05 mGy) was higher than the Halcyon absorbed dose (21.01 mGy). The absorbed dose to the head area was also higher than that of Clinac IX (9.08 mGy) and Halcyon (5.44 mGy). In kV X-ray-based IGRT, additional radiation exposure due to photoelectric absorption may affect the overall volume of the treatment area, and caution is required.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.397-400
• /
• 2000

초음파 영상의 3차원 구성은 기존의 2차원 영상에서는 얻을 수 없었던 결함의 깊이, 방향성 등의 정보를 획득할 수 있기 때문에 최근에 이에 대한 관심이 고조되고 있다. 본 연구에서는 SAM(Scanning Acoustic Micro-scope)의 각 스펙트럼(angular spectrum) 접근법을 사용하여 물체에서의 3차원 영상 구현 이론에 대해서 연구하였다. 이러한 방법은 초음파 트랜스듀서를 디포커싱 시키면서 얻어진 2차원영상 정보를 이용하여 3차원으로 구성하는 방법이다. 실험에서는 알루미늄 원형 시료를 사용하였고, V(z)이론을 이용하여 산란된 신호에서의 영상을 구현하는 데 초점을 두었다. 모의 실험을 통하여 피사체 중심에 대해서 $70^\circ$ 범위 내에서 반사형 초음파 현미경으로 영상을 얻어낼 수 있음을 확인하였다. 중심주파수가 5MHz이고 대역폭이 $35\%$인 트랜스듀서를 사용하여 원형 시료의 중심부에서의 영상을 얻어내었다

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.264-267
• /
• 2015

본 논문에서는 개선된 고속의 Back Projection 기법과 에지맵 보간을 이용한 단일영상 기반의 초해상도(super resolution) 영상을 생성하는 알고리즘을 제안한다. 본 논문에서 제안하는 알고리즘은 영상의 색채 왜곡을 방지하기 위해 RGB 컬러 도메인에서 HSV 컬러 도메인으로 변경하여 밝기정보인 V만 이용한다. 먼저 잡음제거와 속도 향상을 위해 개선된 고속 back projection을 이용해 영상을 확대 재구성한다. 이와 함께 LoG(laplacian of gaussian) 필터링을 이용하여 에지 맵을 추출한다. 에지의 정보와 back projection의 결과를 이용하여 고해상도 영상을 재구성한다. 제안하는 알고리즘을 이용하여 복원한 영상은 부자연스러운 인공물을 효과적으로 제거하고, blur현상을 줄여 에지 정보를 보정하고 강조해준다. 또한 실험을 통해 제안하는 알고리즘이 기존의 보간법과 전통적인 back projection 결과보다 주관적인 화질이 우수하고 객관적으로 우수한 성능을 나타내는 것을 입증한다.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.193-195
• /
• 2018

홍채코드는 홍채의 정보를 이진코드로 표현함으로써 홍채정보를 보호하는 방법이다. 이러한 방법은 현재 홍채인식 시스템에서 표준으로 채택된 기술이다. 본 논문에서는 1-D 가버 필터를 사용하여 홍채 코드로부터 역공학적 방법을 사용하여 홍채영상을 복원하고, 복원된 홍채 영상과 기존의 홍채영상의 인식 결과를 통해 홍채 인식에 대한 취약성을 연구한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.177-178
• /
• 2015

디지털방사선영상시스템의 영상 품질을 비교하기 위해 영상의 정량적인 분해능을 나타내는 변조전달함수(MTF), 노이즈 특성을 나타내는 잡음력 스펙트럼(NPS)을 이용하여 영상 품질평가를 하였다. IEC61267 선질을 사용하여 IEC62220-1에서 제시하는 기하학적인 조건과 실제 임상에서 사용되어지는 기하학적인 조건을 사용하여 그리드 및 부가필터, 임상선량을 이용하여 edge 팬텀을 사용하여 MTF, NPS값을 측정하였다. 그리드사용 유 무, 부가필터사용 유 무, kV, 임상선량(mAs), 영상검출기까지의 거리에 따른 MTF 결과는 임상조건 100cm, 180cm과 IEC62220-1 기하학적인 조건 150cm에서 MTF 공간주파수 측정값은 비슷하게 나타났으며, 오히려 임상조건 100cm에서 공간주파수가 높게 나타나는 경우도 있었다. NPS 결과는 선량(mAs)이 증가함에 따라 감소함을 나타내었다. IEC61267 선질을 이용한 영상품질평가에서는 IEC62220-1기하학적인 조건을 이용한 품질평가보다 임상조건 기하학적인 조건을 사용한 영상의 품질이 좋았다. 본 논문의 영상특성 평가 연구 결과들을 바탕으로 향후 IEC 표준의 영상평가에서 제시하는 평가방법보다는 임상 조건을 적용한 영상특성 평가방법을 적용한다면 실제 임상의 디지털방사선영상시스템의 영상품질을 적절하게 유지할 수 있을 것으로 사료된다.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.387-394
• /
• 2022

120 kVp FBP reconstruction image standard by using raw data after scanning by changing tube voltage among the NECK CT protocols that are broad applied in clinical practice using a human phantom including thyroid gland The usefulness of the DLIR reconstruction technique was investigated. As a result, CTDIvol decreased when the DLIR reconstruction technique was applied, and in particular, the image quality obtained under the same standard scanning conditions at a lower dose for ASIR-V and DLIR reconstruction was reached than when FBP was applied at the same kVp In addition, as a result of SNR and CNR analysis, the DLIR reconstructed image was analyzed with high SNR and CNR values, and SSIM analysis, the SSIM index of the 100 kVp, DLIR reconstructed image was measured to be close to 1, and it was analyzed that the similarity of the reconstructed image to the original image was high (p>0.05). If the results of this study are used to supplement clinical image evaluation and further develop an algorithm applicable to various anatomical structures, it is thought that it will be useful for clinical application as it is possible to maintain the image quality while lowering the examination dose.