Segmentation of rodent brains from MRI based on a novel statistical structure prediction method

  • Authors:

  • Jinghao Zhou;Sukmoon Chang;Shaoting Zhang;George Pappas;Michael Michaelides;Foteini Delis;Nora Volkow;Panayotis Thanos;Dimitris Metaxas

  • Affiliations:

  • Radiation Oncology, The Cancer Institute of New Jersey, UMDNJ-Robert Wood Johnson Medical School, New Brunswick and CBIM, Rutgers, The State University of New Jersey, Piscataway, NJ;CBIM, Rutgers, The State University of New Jersey, Piscataway, NJ and Computer Science, Capital College, Penn State University, Middletown, PA;CBIM, Rutgers, The State University of New Jersey, Piscataway, NJ;Behavior Neuropharmacology and Neuroimaging Lab, Medical Department, Brookhaven National Laboratory, Upton, NY;Behavior Neuropharmacology and Neuroimaging Lab, Medical Department, Brookhaven National Laboratory, Upton, NY;Behavior Neuropharmacology and Neuroimaging Lab, Medical Department, Brookhaven National Laboratory, Upton, NY;Behavior Neuropharmacology and Neuroimaging Lab, Medical Department, Brookhaven National Laboratory, Upton, NY;Behavior Neuropharmacology and Neuroimaging Lab, Medical Department, Brookhaven National Laboratory, Upton, NY;CBIM, Rutgers, The State University of New Jersey, Piscataway, NJ

  • Venue:
  • ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Functional segmentation of brain images is important in understating the relationships between anatomy and mental diseases in brains. Volumetric analysis of various brain structures such as the cerebellum plays a critical role in studying the structural changes in brain regions as a function of development, trauma, or neurodegeneration. Although various segmentation methods in clinical studies have been proposed, most of them require a priori knowledge about the locations of the structures of interest, preventing the fully automatic segmentation. In this paper, we present a novel method for detecting and locating the brain structures of interest that can be used for the fully automatic functional segmentation of 2D rodent brain MR images. The presented method focuses on detecting the topological changes of brain structures based on a novel area ratio criteria. The mean successful rate of the detection method shows 89.4% accuracy compared to the expert-identified ground truth.