Determining histology-MRI slice correspondences for defining MRI-based disease signatures of prostate cancer

Gaoyu Xiao, B. Nicolas Bloch, Jonathan Chappelow, Elizabeth M. Genega, Neil M. Rofsky, Robert E. Lenkinski, John Tomaszewski, Michael D. Feldman, Mark Rosen, Anant Madabhushi

Research output: Contribution to journalArticle

47 Scopus citations

Abstract

Mapping the spatial disease extent in a certain anatomical organ/tissue from histology images to radiological images is important in defining the disease signature in the radiological images. One such scenario is in the context of men with prostate cancer who have had pre-operative magnetic resonance imaging (MRI) before radical prostatectomy. For these cases, the prostate cancer extent from ex vivo whole-mount histology is to be mapped to in vivo MRI. The need for determining radiology-image-based disease signatures is important for (a) training radiologist residents and (b) for constructing an MRI-based computer aided diagnosis (CAD) system for disease detection in vivo. However, a prerequisite for this data mapping is the determination of slice correspondences (i.e. indices of each pair of corresponding image slices) between histological and magnetic resonance images. The explicit determination of such slice correspondences is especially indispensable when an accurate 3D reconstruction of the histological volume cannot be achieved because of (a) the limited tissue slices with unknown inter-slice spacing, and (b) obvious histological image artifacts (tissue loss or distortion). In the clinic practice, the histology-MRI slice correspondences are often determined visually by experienced radiologists and pathologists working in unison, but this procedure is laborious and time-consuming. We present an iterative method to automatically determine slice correspondence between images from histology and MRI via a group-wise comparison scheme, followed by 2D and 3D registration. The image slice correspondences obtained using our method were compared with the ground truth correspondences determined via consensus of multiple experts over a total of 23 patient studies. In most instances, the results of our method were very close to the results obtained via visual inspection by these experts.

Original languageEnglish (US)
Pages (from-to)568-578
Number of pages11
JournalComputerized Medical Imaging and Graphics
Volume35
Issue number7-8
DOIs
StatePublished - Oct 1 2011

Keywords

  • Histology
  • MRI
  • Prostate cancer
  • Slice correspondences

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Determining histology-MRI slice correspondences for defining MRI-based disease signatures of prostate cancer'. Together they form a unique fingerprint.

  • Cite this

    Xiao, G., Bloch, B. N., Chappelow, J., Genega, E. M., Rofsky, N. M., Lenkinski, R. E., Tomaszewski, J., Feldman, M. D., Rosen, M., & Madabhushi, A. (2011). Determining histology-MRI slice correspondences for defining MRI-based disease signatures of prostate cancer. Computerized Medical Imaging and Graphics, 35(7-8), 568-578. https://doi.org/10.1016/j.compmedimag.2010.12.003