Journal of Digital Contents Society (디지털콘텐츠학회 논문지)

Digital Contents Society (한국디지털콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

A GPU-based Filter Algorithm for Noise Improvement in Realtime Ultrasound Images

실시간 초음파 영상에서 노이즈 개선을 위한 GPU 기반의 필터 알고리즘

  • Cho, Young-Bok (Department of Computer & Information Security, Daejeon University) ;
  • Woo, Sung-Hee (Department of Medical IT Engineering, Korea National University of Transportation)
  • 조영복 (대전대학교 정보보안학과) ;
  • 우성희 (한국교통대학교 의료IT공학과)
  • Received : 2018.05.20
  • Accepted : 2018.06.25
  • Published : 2018.06.30
⟨ Previous Next ⟩

Abstract

The ultrasound image uses ultrasonic pulses to receive the reflected waves and construct an image necessary for diagnosis. At this time, when the signal becomes weak, noise is generated and a slight difference in brightness occurs. In addition, fluctuation of image due to breathing phenomenon, which is the characteristic of ultrasound image, and change of motion in real time occurs. Such a noise is difficult to recognize and diagnose visually in the analysis process. In this paper, morphological features are automatically extracted by using image processing technique on ultrasound acquired images. In this paper, we implemented a GPU - based fast filter using a cloud big data processing platform for image processing. In applying the GPU - based high - performance filter, the algorithm was run with performance 4.7 times faster than CPU - based and the PSNR was 37.2dB, which is very similar to the original.

초음파 영상은 초음파 펄스를 이용해 반사파를 수신하여 진단에 필요한 영상을 구성하는데 신호가 약해 질 경우, 잡음이 발생하여 미세한 명암도 차이가 발생한다. 또한 초음파 영상의 특성인 호흡에 의한 흔들림 현상과 실시간으로 변화하는 움직임에서 영상의 밝기 변화가 발생한다. 이와 같은 노이즈로 인해 임상적 병변을 육안으로 판단하고 진단하는데 어려움이 있다. 본 논문에서는 초음파 획득한 이미지에 영상처리 기법을 이용하여 형태학적 특징을 자동 추출한다. 이 논문에서는 영상처리를 위해 클라우드 빅데이터 처리 플랫폼을 활용해 GPU기반의 빠른 필터를 구현하였다. GPU 기반의 고성능 필터의 적용시 CPU 기반보다 4.7배 빠른 성능으로 알고리즘이 동작되었고 PSNR이 37.2dB로 원본과 매우 유사함을 확인하였다.

Keywords

Acknowledgement

Supported by : 한국교통대학교

References

  1. O'Connell, D., D. H. Thomas, T.H. Dou, E. Aliotta, J. H. Lewis, J.M. Lamb, P. Lee and D. A Low, "Adaptive weighted median filtering for reduced blurring when fusing co-registered fast helical CT images", 2017, Available: http://iopscience.iop.org/article/10.1088/2057-1976/aa889d/meta
  2. K. Z. Abd-Elmoniem, A. M. Youssef, and Y. M. Kadah, "Real-Time Speckle Reduction and Coherence Enhancement in Ultrasound Imaging via Nonlinear Anisotropic Diffusion", 2002, Available: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.725.7281&rep=rep1&type=pdf
  3. D. Ghosh, D. Nandi, P. Ghosal, and A. Kumar, "A Novel Speckle Reducing Scan Conversion in Ultrasound Imaging System", 2017, Available: https://link.springer.com/chapter/10.1007/978-981-10-3373-5_34 .
  4. Cho, Young-Bok,Woo, Sung-Hee and Lee, Sang-Ho, "The Big Data Analysis and Medical Quality Management for Wellness," The Journal of Korea Society of Computer and Information , vol.19, no.12, p.101-109, December 2014 https://doi.org/10.9708/jksci.2014.19.12.101
  5. Hong, Dong-Hee, and Park, Mi-Soon, "Analysis of HealthcareConvergence on Bacterial Contamination of Radiological Equipment in Emergency Rooms of General Hospitals", 2017, Available: https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiOrteServHistIFrame.kci?sereArticleSearchBean.artiId=ART002194655&sereArticleSearchBean.orteFileId=KCI_FI002194655
  6. Kalavathi Palanisamy, M Abinaya. and Boopathiraja S, "Removal of Speckle Noise in Ultrasound Images using Spatial Filters.", 2017, Avalable: https://www.researchgate.net/profile/Kalavathi_Palanisamy3/publication/313056268_Removal_of_Speckle_Noise_in_Ultrasound_Images_using_Spatial_Filters/links/588f030a92851cef1363be1e/Removal-of-Speckle-Noise-in-Ultrasound-Images-using-Spatial-Filters.pdf?origin=publication_detail
  7. McDonald ES, McCarthy AM, Weinstein SP Schnall MD and Conant EF, "Conant EF. BI-RADS category 3 comparison: probably benign category after recall from screening before and after implementation of digital breast tomosynthesis", 2017, Available: https://doi:10.1148/radiol.2017162837
  8. Cho, Young-Bok, Kim, Min-Kang and Woo, Sung-Hee, "High-speed CUDA Algorithm for GPU -based feature extraction in Iris", International Information Institute (Tokyo). Information, vol.21, no.1, pp. 239-248, Jan 2018.
  9. Paek, Jaeg-Yung and Seo, Yeong-Geon, "Extracting the Slope and Compensating the Image Using Edges and Image Segmentation in Real World Image", Journal of DCS, Vol. 17, No. 5, p.441, Oct 2016 https://doi.org/10.9728/dcs.2016.17.5.441
  10. Suryadibrata Alethea and Kim Kwang-Baek,"Ganglion Cyst Region Extraction from Ultrasound Images Using Possibilistic C-Means Clustering Method", Journal of Information and Communication Convergence Engineering(JICCE), vol. 15. no. 1, p. 49, March 2017, Available: http://www.kpubs.org/article/articleDownload.kpubs?downType=pdf&articleANo=E1ICAW_2017_v15n1_49 https://doi.org/10.6109/JICCE.2017.15.1.49
  11. Lee, Min-Chul, Kotaro Inoue, and Cho, Myungjin, "Three-Dimensional Automatic Target Recognition System Based on Optical Integral Imaging Reconstruction", Journal of Information and Communication Convergence Engineering(JICCE), vol. 14, no. 1, p51, March, 2016, Available https://www.researchgate.net/publication/301236933_Three-Dimensional_Automatic_Target_Recognition_System_Based_on_Optical_Integral_Imaging_Reconstruction https://doi.org/10.6109/jicce.2016.14.1.051

Cited by

  1. Keras based CNN Model for Disease Extraction in Ultrasound Image vol.19, pp.10, 2018, https://doi.org/10.9728/dcs.2018.19.10.1975
  2. Image Processing of Lesion in Iris Image Using OpenCV vol.19, pp.11, 2018, https://doi.org/10.9728/dcs.2018.19.11.2035