본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색
결과 내 검색 동의어 포함
결과 내 검색 동의어 포함

-

초록보기

CT 촬영 시 방사선량을 줄이면 피폭 위험성을 낮출 수 있으나, 영상 해상도가 크게 저하 될 뿐 아니라 잡음(noise) 발생으로 인해 진단의 효용성이 떨어진다. 따라서, CT 영상에서의 잡음제거는 영상복원 분야에 있어 매우 중요하고 필수적인 처리 과정이다. 영상 영역에서 잡음과 원래 신호를 분리하여 잡음만을 제거하는 것은 한계가 있다. 본 논문에서는 웨이블릿 변환 기반 GAN 모델 즉, WT-GAN(wavelet transform-based GAN) 모델을 이용하여 CT 영상에서 효과적으로 잡음 제거하고자 한다. 여기서 사용된 GAN 모델은 U-Net 구조의 생성자와 PatchGAN 구조의 판별자를 통해 잡음제거 영상을 생성한다. 본 논문에서 제안된 WT-GAN 모델의 성능 평가를 위해 다양한 잡음, 즉, 가우시안 잡음(Gaussian noise), 포아송 잡음 (Poisson noise) 그리고 스펙클 잡음 (speckle noise)에 의해 훼손된 CT 영상을 대상으로 실험하였다. 성능 실험 결과, WT-GAN 모델은 전통적인 필터 즉, BM3D 필터뿐만 아니라 기존의 딥러닝 모델인 DnCNN, CDAE 모형 그리고 U-Net GAN 모형보다 정성적이고, 정량적인 척도 즉, PSNR (Peak Signal-to-Noise Ratio) 그리고 SSIM (Structural Similarity Index Measure) 면에서 우수한 결과를 보였다.

Reducing the radiation dose during CT scanning can lower the risk of radiation exposure, but not only does the image resolution significantly deteriorate, but the effectiveness of diagnosis is reduced due to the generation of noise. Therefore, noise removal from CT images is a very important and essential processing process in the image restoration. Until now, there are limitations in removing only the noise by separating the noise and the original signal in the image area. In this paper, we aim to effectively remove noise from CT images using the wavelet transform-based GAN model, that is, the WT-GAN model in the frequency domain. The GAN model used here generates images with noise removed through a U-Net structured generator and a PatchGAN structured discriminator. To evaluate the performance of the WT-GAN model proposed in this paper, experiments were conducted on CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. As a result of the performance experiment, the WT-GAN model is better than the traditional filter, that is, the BM3D filter, as well as the existing deep learning models, such as DnCNN, CDAE model, and U-Net GAN model, in qualitative and quantitative measures, that is, PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) showed excellent results.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
Cluster-based similarity calculation of IT assets : method of attacker's next targets detection Dongsung Kim, Seon-Gyoung Shon, Dan Dongseong Kim, Huy-Kang Kim p. 1-10

(A) study on predicting credit ratings of Korean companies using TabNet Hyeokjin Choi, Gyeongho Jung, Hyunchul Ahn p. 11-20

(An) efficient CT image denoising using WT-GAN model Hae Chan Jeong, Dong Hoon Lim p. 21-29

(A) design and implementation of generative AI-based advertising image production service application Chang Hee Ok, Hyun Sung Lee, Min Soo Jeong, Yu Jin Jeong, Ji An Choi, Young-Bok Cho, Won Joo Lee p. 31-38

Implementation of a wearable device for monitoring the health status of the elderly living alone Ji-Hoon Lee, Gyung-Hwan Kim, Myeong-Chul Park p. 39-46

(A) prototype design for a real-time VR game with hand tracking using affordance elements Yu-Won Jeong p. 47-53

(The) effects of live commerce's experience economy factors on consumer's flow, attitude, and purchase intention Na-eun Jung, Hyung-Seok Lee p. 55-66

Implementation of a crowding measurement system based on high frequency signal Myoungbeom Chung p. 67-74

(A) study of the relationship between consumption value, advertising acceptance attitude and purchase intention according to MBTI personality type : focusing on the consumption of digital products by MZ generation Jae-Woo Lee, Chang-Bae Ko p. 75-83

(A) research on the design and implementation of LED display-based light gun systems Byong-Kwon Lee p. 85-91

Privacy-preserving collection and analysis of medical microdata Jong Wook Kim p. 93-100

Effects of walking activity monitoring and feedback using wearable device on body composition and metabolic syndrome risk factors in middle-aged women Chan-Yang Kim, Woo-Young Park p. 101-110

Development and verification of muscle strength effectiveness based on Fitsig® (EMG prototype) Changjin Ji, Yong-hyun Byun, Sangho Kim p. 111-121

(A) chest compression CPR study performed on a main stretcher : comparative study between C-step and over the belly Gyu-Sik Shim, Song-Yi Han p. 123-129

(A) study on the impact of rural older adults residence type and social activity participation on health-promoting behaviors : a gender perspective Hyoun-Woo Choi, Joo-Lee Son, Yoon-Ji Choi, Jung-Shin Choi p. 131-142

(A) study on the current status and improvement plans for e-Learning utilization using the Delphi technique : focusing on scuba diving education Sung-Soo Park p. 143-153

Development of an unsupervised learning-based ESG evaluation process for Korean public institutions without label annotation Do Hyeok Yoo, SuJin Bak p. 155-164

Based on the analysis of entrepreneurship support policy information, establishment of customized entrepreneurship promotion model for sports major Byung-Kwan Lee p. 165-175

Enhancing music recommendation systems through emotion recognition and user behavior analysis Qi Zhang p. 177-187

(A) study of subjectivity about virtual fashion Su-Joung Cha p. 189-202

(A) study on the development of a problem bank in an automated assessment module for data visualization based on public data HakNeung Go, Sangsu Jeong, Youngjun Lee p. 203-211

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차