By Topic

IEE Colloquium on Image Processing in Medicine

19 Apr 1991

Filter Results

Displaying Results 1 - 9 of 9
  • Symmetry-based networks for medical object description

    Publication Year: 1991, Page(s):2/1 - 213
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (476 KB)

    A technique is presented for describing objects by assigning them object-based coordinates using a shape invariant scheme based on their symmetries. A partial implementation of this scheme has resulted in several robust image analysis systems dealing with foetal ultra-sound, cervical cells and tracking moving cells in time-lapse images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation for 3-D display [of medical images]

    Publication Year: 1991, Page(s):8/1 - 8/7
    Cited by:  Patents (5)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (308 KB)

    The authors' work is concerned with the role of segmentation in preparing CT or MR datasets for 3-D display. Some widely used segmentation techniques-including spatial editing, tone scale transformations, and connectivity-based approaches-are first reviewed, and a novel data tagging scheme (permitting display-time selection of the output of any of the above techniques) is then presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Processing techniques for speckle reduction in medical ultrasound images

    Publication Year: 1991, Page(s):6/1 - 6/4
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (216 KB)

    With the advent of the new generation of DSP (Digital Signal Processing) technology more sophisticated methods for speckle reduction, such as the phase acknowledging techniques, are now feasible on a real time basis. There are a number of advantageous features associated with these methods: correction processing is localised; overall image resolution is retained; performance is robust to noise; no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards interactive vision edge-region integration in MRI

    Publication Year: 1991, Page(s):1/1 - 1/2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (96 KB)

    It is pragmatic to look for ways in which the knowledge of an expert can interact with data driven processes and such high level knowledge as can be represented usefully in a system. Central problems such as image segmentation do not go away but systems can be judged somewhat differently, not as successes or failures, but on the basis of the amount of work that they save a human expert. This argum... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deconvolution of pulse-echo images

    Publication Year: 1991, Page(s):3/1 - 3/4
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (164 KB)

    In order to improve the capability of resolving boundaries and small details, an approach to remove or partially remove the influence of the pulse must be used. An algorithm consisting of a Kalman filter and a reflection estimator is described. For one-dimensional deconvolution the pulse estimator gives all the necessary parameters for performing the algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEE Colloquium on `Image Processing in Medicine' (Digest No.084)

    Publication Year: 1991
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (12 KB)

    The following topics were dealt with: MRI edge-region integration; symmetry-based networks for object description; pulse-echo image deconvolution; segmentation; neural networks; speckle reduction in ultrasound images; imaging absorption of infrared light in brain; 3D display View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Imaging absorption of infra-red light in the brain

    Publication Year: 1991, Page(s):7/1 - 7/2
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (104 KB)

    The task of reconstructing an image from the intensity of the transmitted light detected on the surface of the body is quite formidable because the photons undergo very many scattering events such that the overall model of their propagation is best described as a diffusion process. Recently it has become popular to use very short (<20 picosecond) pulses as input sources and measure the transmit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation via image structure [in medical imaging]

    Publication Year: 1991, Page(s):4/1 - 4/3
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (192 KB)

    The author describes a segmentation technique which satisfies the criteria for good segmentations in that it (i) can produce T-junctions, (ii) each section of edge has an associated confidence and (iii) requires no user-intervention or domain-dependent constants. Initial results with the technique appear to indicate that the segmentations produced compare well with the expectations of an inexpert ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of MR images using neural nets

    Publication Year: 1991, Page(s):5/1 - 5/4
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (120 KB)

    A two tier system for MR image segmentation is proposed. The first stage involves probabilistically classifying the pixels of the input image based on second order grey level statistics obtained from the co-occurrence matrix. These probabilities then form the input to a multilayer perceptron, allowing contextual constraints to be applied to local areas of the image improving the spatial coherence ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.