Small Blob Identification in Medical Images Using Regional Features From Optimum Scale

Min Zhang, Teresa Wu, Kevin M. Bennett

Research output: Contribution to journalArticlepeer-review

54 Scopus citations


Recent advances in medical imaging technology have greatly enhanced imaging-based diagnosis which requires computational effective and accurate algorithms to process the images (e.g., measure the objects) for quantitative assessment. In this research, we are interested in one type of imaging objects: small blobs. Examples of small blob objects are cells in histopathology images, glomeruli in MR images, etc. This problem is particularly challenging because the small blobs often have inhomogeneous intensity distribution and an indistinct boundary against the background. Yet, in general, these blobs have similar sizes. Motivated by this finding, we propose a novel detector termed Hessian-based Laplacian of Gaussian (HLoG) using scale space theory as the foundation. Like most imaging detectors, an image is first smoothed via LoG. Hessian analysis is then launched to identify the single optimal scale on which a presegmentation is conducted. The advantage of the Hessian process is that it is capable of delineating the blobs. As a result, regional features can be retrieved. These features enable an unsupervised clustering algorithm for postpruning which should be more robust and sensitive than the traditional threshold-based postpruning commonly used in most imaging detectors. To test the performance of the proposed HLoG, two sets of 2-D grey medical images are studied. HLoG is compared against three state-of-the-art detectors: generalized LoG, Radial-Symmetry and LoG using precision, recall, and F-score metrics. We observe that HLoG statistically outperforms the compared detectors.

Original languageEnglish (US)
Article number6910292
Pages (from-to)1051-1062
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
Issue number4
StatePublished - Apr 1 2015


  • Blob detection
  • Hessian analysis
  • Laplacian of Gaussian (LoG)
  • Scale space
  • Unsupervised learning

ASJC Scopus subject areas

  • Biomedical Engineering


Dive into the research topics of 'Small Blob Identification in Medical Images Using Regional Features From Optimum Scale'. Together they form a unique fingerprint.

Cite this