Hierarchical Non-Rigid Registration by Bodily Tissue-based Segmentation : Application to the Visible Human Cross-sectional Color Images and CT Legs Images

조직 기반 계층적 non-rigid 정합: Visible Human 컬러 단면 영상과 CT 다리 영상에 적용

  • Kim, Gye-Hyun (School Electronic Engineering, Soongsil Univ.) ;
  • Lee, Ho (School Electronic Engineering, Soongsil Univ.) ;
  • Kim, Dong-Sung (School Electronic Engineering, Soongsil Univ.) ;
  • Kang, Heung-Sik (School of Medicine, Seoul National University)
  • 김계현 (숭실대학교 정보통신전자 공학부) ;
  • 이호 (숭실대학교 정보통신전자 공학부) ;
  • 김동성 (숭실대학교 정보통신전자 공학부) ;
  • 강흥식 (서울대학교 의과대학)
  • Published : 2003.08.01

Abstract

Non-rigid registration between different modality images with shape deformation can be used to diagnosis and study for inter-patient image registration, longitudinal intra-patient registration, and registration between a patient image and an atlas image. This paper proposes a hierarchical registration method using bodily tissue based segmentation for registration between color images and CT images of the Visible Human leg areas. The cross-sectional color images and the axial CT images are segmented into three distinctive bodily tissue regions, respectively: fat, muscle, and bone. Each region is separately registered hierarchically. Bounding boxes containing bodily tissue regions in different modalities are initially registered. Then, boundaries of the regions are globally registered within range of searching space. Local boundary segments of the regions are further registered for non-rigid registration of the sampled boundary points. Non-rigid registration parameters for the un-sampled points are interpolated linearly. Such hierarchical approach enables the method to register images efficiently. Moreover, registration of visibly distinct bodily tissue regions provides accurate and robust result in region boundaries and inside the regions.

해부학적 구조의 변형이 존재하는 두 영상을 정합하기 위하여 연구되는 non-rigid 정합 방법은 환자간의 정합 환자와 표준영상간의 정합, 동일환자에서 변형을 갖는 부위의 정합 등 이용한 진단 및 연구에 사용되어 현재 많은 연구가 진행되고 있는 분야이다. 본 논문에서는 서로 형태와 색상 특성이 다른 Visible Human 컬러 영상파 CT 영상의 다리 부위를 정합하기 위하여 해부 영상에서 두드러진 차이를 보이는 뼈, 근육, 지방 조직을 분할하고 분할된 각 조직의 경계 단위를 계층적인 정합을 하는 조직 기반 성합 방법을 제안하였다. 제안한 조직 기반의 정합은 색상 특성이 두드러지게 변하는 경계 부위를 정확히 정합하므로 기존의 특징점을 이용한 정합 방법에 비하여 강력하고 정확한 결과를 얻음을 실험을 통하여 검증하였다. 또한 계층적인 정합은 분할된 조직의 바운딩 박스(bounding box) 정합. 전역 Rigid 정합과 지역 non-rigid 정합, 정합 보간(interpolation)을 순차적으로 실행하여 효율적인 계산 시간을 제공하였다.

Keywords

References

  1. Medical Image Analysis v.1 no.4 Segmentation of the Visible Human for High-Quality Volume-Based Visualization T.Schiemann;U.Tiede;K.H.Hohne https://doi.org/10.1016/S1361-8415(97)85001-3
  2. Workshop of IPIU v.1 Registration of Visible Human cross-sectional images and normal CT images using segmentation based on material characteristics H.Lee;D.Kim
  3. Medical Image Analysis v.2 no.1 A survey of medical image registration J.B.A Maintz;M.A.Viergever https://doi.org/10.1016/S1361-8415(01)80026-8
  4. Computer Vision, Virtual Reality and Robotics in Medicine 3D multi-modality medical image registration using feature space clustering A.Collignon;D.Vandermeulen;P.Suetens;G.Marchal
  5. IEEE Transaction on Medical Imaging v.16 no.2 Multimodality Image Registration by maximization of Mutual Information F.Maes;A.Collignon;G.Marchal;P.Suetens https://doi.org/10.1109/42.563664
  6. IEEE Transaction on Medical Imaging v.19 no.8 Image Registration by Maximization of Combined Mutual Information and Gradient Information J.P.W.Pluim;J.B.A.Maintz;M.A.Viergever https://doi.org/10.1109/42.876307
  7. IEEE International Symposium on Biomedical Imaging Non-rigid registration of medical images: purpose and methods, a short survey B.M.Dawant
  8. IEEE Workshop on Applications of Computer Vision Integrated Approaches to Non-rigid Registration in Medical Images Y.Wang
  9. IEEE Transaction on Image Processing v.4 no.7 Automatic Taget Segmentation by Locally Adaptive Image Thresholding W.Lie https://doi.org/10.1109/83.392347
  10. Digital Image Processing R.G.Gonzalez;R.E.Woods
  11. IEEE Transactions on Medical Imaging v.16 no.5 A methodology for evaluation of boundary detection algorithm on medical images C.Vikram;Y.M.Kim https://doi.org/10.1109/42.640755