A Minimum Spanning Forest-Based Method for Noninvasive Cancer Detection with Hyperspectral Imaging

Robert Pike, Guolan Lu, Dongsheng Wang, Zhuo Georgia Chen, Baowei Fei

Research output: Contribution to journalArticlepeer-review

80 Scopus citations


Goal: The purpose of this paper is to develop a classification method that combines both spectral and spatial information for distinguishing cancer from healthy tissue on hyperspectral images in an animal model. Methods: An automated algorithm based on a minimum spanning forest (MSF) and optimal band selection has been proposed to classify healthy and cancerous tissue on hyperspectral images. A support vector machine classifier is trained to create a pixel-wise classification probability map of cancerous and healthy tissue. This map is then used to identify markers that are used to compute mutual information for a range of bands in the hyperspectral image and thus select the optimal bands. An MSF is finally grown to segment the image using spatial and spectral information. Conclusion: The MSF based method with automatically selected bands proved to be accurate in determining the tumor boundary on hyperspectral images. Significance: Hyperspectral imaging combined with the proposed classification technique has the potential to provide a noninvasive tool for cancer detection.

Original languageEnglish (US)
Article number7202847
Pages (from-to)653-663
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Issue number3
StatePublished - Mar 2016
Externally publishedYes


  • Hyperspectral imaging
  • image classification
  • minimum spanning forest
  • mutual information
  • noninvasive cancer detection
  • support vector machine

ASJC Scopus subject areas

  • Biomedical Engineering


Dive into the research topics of 'A Minimum Spanning Forest-Based Method for Noninvasive Cancer Detection with Hyperspectral Imaging'. Together they form a unique fingerprint.

Cite this