Yang Hu

Rochester Institute of Technology, Rochester, New York, United States

Are you Yang Hu?

Claim your profile

Publications (4)0.2 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a framework that efficiently employs intensity, gradient, and textural features for three-dimensional (3-D) segmentation of medical (MRI/CT) volumes. Our methodology commences by determining the magnitude of intensity variations across the input volume using a 3-D gradient detection scheme. The resultant gradient volume is utilized in a dynamic volume growing/formation process that is initiated in voxel locations with small gradient magnitudes and is concluded at sites with large gradient magnitudes, yielding a map comprising an initial set of partitions (or subvolumes). This partition map is combined with an entropy-based texture descriptor along with intensity and gradient attributes in a multivariate analysis-based volume merging procedure that fuses subvolumes with similar characteristics to yield a final/refined segmentation output. Additionally, a semiautomated version of the aforestated algorithm that allows a user to interactively segment a desired subvolume of interest as opposed to the entire volume is also discussed. Our approach was tested on several MRI and CT datasets and the results show favorable performance in comparison to the state-of-the-art ITK-SNAP technique.
    No preview · Article · May 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: A significant increase in the availability of high resolution hyperspectral images has led to the need for developing pertinent techniques in image analysis, such as classification. Hyperspectral images that are correlated spatially and spectrally provide ample information across the bands to benefit this purpose. Conditional Random Fields (CRFs) are discriminative models that carry several advantages over conventional techniques: no requirement of the independence assumption for observations, flexibility in defining local and pairwise potentials, and an independence between the modules of feature selection and parameter leaning. In this paper we present a framework for classifying remotely sensed imagery based on CRFs. We apply a Support Vector Machine (SVM) classifier to raw remotely sensed imagery data in order to generate more meaningful feature potentials to the CRFs model. This approach produces promising results when tested with publicly available AVIRIS Indian Pine imagery.
    No preview · Article · Feb 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: CT (Computed tomography) is a widely employed imaging modality in the medical field. Normally, a volume of CT scans is prescribed by a doctor when a specific region of the body (typically neck to groin) is suspected of being abnormal. The doctors are required to make professional diagnoses based upon the obtained datasets. In this paper, we propose an automatic registration algorithm that helps healthcare personnel to automatically align corresponding scans from 'Study' to 'Atlas'. The proposed algorithm is capable of aligning both 'Atlas' and 'Study' into the same resolution through 3D interpolation. After retrieving the scanned slice volume in the 'Study' and the corresponding volume in the original 'Atlas' dataset, a 3D cross correlation method is used to identify and register various body parts.
    No preview · Article · Feb 2012 · Proceedings of SPIE - The International Society for Optical Engineering
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a novel gradient driven methodology for three dimensional (3-D) segmentation of Computed Tomographic (CT) imagery. Our approach begins interactively where-in a user marks a set of voxels within the cross-section of a Sub-Volume Of Interest (SVOI), using a single slice of the CT volume. Subsequently, a 3-D gradient detection scheme is utilized to determine the radiodensity variations across the volume. The resultant gradient information is employed in an iterative volume growing procedure, which is initiated at voxels with small gradient magnitudes adjoining the user-selected voxels and culminates at voxels with large gradient magnitudes, to arrive at the final 3-D segmentation result of the SVOI. The aforementioned method was tested on multiple studies and the results show favorable performance against a state-of-the-art technique.
    No preview · Conference Paper · Jan 2011