A general framework for the segmentation of follicular lymphoma virtual slides

Comput Med Imaging Graph. 2012 Sep;36(6):442-51. doi: 10.1016/j.compmedimag.2012.05.003. Epub 2012 Jun 18.

Abstract

Follicular lymphoma (FL) is one of the most common types of non-Hodgkin's lmphomas in the world. Diagnosis of FL is based on morphological and immunohistochemical characteristics found on tissue sections. Our project's aim is to develop computer-aided analysis tools on virtual slide images (VSI) of lymphoid tissues with the purpose of improving the FL grading performed in malignant follicles. In this paper, we focus on the first step of our work, an automated system for detecting follicles in VSI of lymphoid tissues. To mimic the human expert process, the system works on low-resolution CD20 images and maps the follicle boundaries on high-resolution H&E images.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Biopsy / methods*
  • Humans
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Lymphoma, Follicular / pathology*
  • Microscopy / methods*
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Sensitivity and Specificity
  • User-Computer Interface*