Fast GPU-based segmentation of H&E stained squamous epithelium from multi-gigapixel tiled virtual slides

Benjamin Bryant, Hamed Sari-Sarraf, Mitchell Wachtel, Rodney Long, Sameer Antani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


The processing of multi-gigapixel virtual histology slides presents a computationally intensive and time consuming task. Common tiled TIFF slide formats, such as those used by Aperio [1], contain inherent header information that can be used to rapidly locate tissue regions for cervical intraepithelial neoplasia (CIN) diagnosis. Tiles used in these formats are individually compressed subsections of the virtual slide, whose compression ratio varies based on their individual content. This paper discusses a method that exploits this information to rapidly identify regions of interest in an iterative process to locate epithelial tissue. These regions are decompressed using a multi-core CPU, from which a Compute Unified Device Architecture (CUDA) enabled GPU rapidly generates features and Support Vector Machine (SVM) decisions. SVM classifier results are used in a post-processing scheme to remove apparently spurious misclassifications. The mean overall execution time when using a high-end desktop PC, together with a GTX 560 GPU, is roughly 3 seconds per gigapixel, while maintaining the area under an ROC curve above 0.9 when classifying squamous epithelium versus other tissues.

Original languageEnglish
Title of host publicationMedical Imaging 2013
Subtitle of host publicationDigital Pathology
StatePublished - 2013
EventSPIE Medical Imaging Symposium 2013: Digital Pathology - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 11 2013

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceSPIE Medical Imaging Symposium 2013: Digital Pathology
Country/TerritoryUnited States
CityLake Buena Vista, FL


  • CIN
  • CUDA
  • GPU
  • SVM
  • Segmentation


Dive into the research topics of 'Fast GPU-based segmentation of H&E stained squamous epithelium from multi-gigapixel tiled virtual slides'. Together they form a unique fingerprint.

Cite this