Optimal Threshold Selection for Tomogram Segmentation by Projection Distance Minimization

  title={Optimal Threshold Selection for Tomogram Segmentation by Projection Distance Minimization},
  author={Kees Joost Batenburg and Jan Sijbers},
  journal={IEEE Transactions on Medical Imaging},
Grey value thresholding is a segmentation technique commonly applied to tomographic image reconstructions. Many procedures have been proposed to optimally select the grey value thresholds based on the tomogram data only (e.g., using the image histogram). In this paper, a projection distance minimization (PDM) method is presented that uses the tomographic projection data to determine optimal thresholds. These thresholds are computed by minimizing the distance between the forward projection of… 

Figures from this paper

Optimal Threshold Selection for Segmentation of Dense Homogeneous Objects in Tomographic Reconstructions
A new threshold estimation approach, segmentation inconsistency minimization, that exploits the available projection data to determine the optimal global threshold is proposed and results in more accurate segmentations, compared to alternative threshold selection methods.
Threshold Selection using Segmentation Inconsistency Minimization Technique in Tomographic Reconstructions Ms .
Tomographic reconstructions are often segmented to extract valuable quantitative information. In this paper, we consider the problem of segmenting a dense object of constant density within a
An EIT image segmentation method based on projection distance minimization
An image segmentation method based on projection distance minimization (PDM) was proposed, which can determine the optimal threshold from the initial EIT image by minimizing the distance between the computed projection of the segmented image and the measured projection data.
Visualizing the segmentation error of a tomogram using the residual projection error
A way to visualize the segmentation error, based on the residual projection error, which is the difference between the recorded data and the forward projection of the segmented tomogram, is introduced.
Effect of Image Size on Threshold Selection for Segmentation of Dense Homogeneous Objects in Tomographic Reconstructions
Accurate image segmentation is required for obtaining correct localization, shape, size of tomographic image objects, but it is difficult to obtain, in particular if one needs to segment objects that
A Data Consistent Variational Segmentation Approach Suitable for Real-time Tomography
This article proposes a segmentation method for tomographic volumes composed of few materials that combines existing high-quality variational segmentation frameworks with the data consistency approach used in tomography and discrete tomography.
The proposed method tries to develop thresholding concept and K-means algorithm to obtain high performance and efficiency of mammographic images taken from Mammographic Image Analysis Society digital mammogram database.
This work focuses on segmentation that combines neural network with Watershed algorithm modified to use automatic optimal threshold selection algorithm, and Experimental results prove that the proposed method is efficient in segmenting medical images.


Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images
A sequence of morphological operations is used to smooth the irregular boundary along the mediastinum in order to obtain results consistent with these obtained by manual analysis, in which only the most central pulmonary arteries are excluded from the lung region.
Thresholding technique for accurate analysis of density and geometry in QCT, pQCT and microCT images.
  • T. Hangartner
  • Physics
    Journal of musculoskeletal & neuronal interactions
  • 2007
The aim of this communication is to highlight the influence of threshold selection on various bone parameters and recommend appropriate thresholds for geometry and density parameters.
Automatic threshold selection based on histogram modes and a discriminant criterion
A fully automatic thresholding method via histogram modal decomposition by data-dependent-systems methodology is presented, in which the histogram of an image is parametrically modeled by the power spectrum of an autoregressive model to provide vital information about histogram clusters.
Efficient Multilevel Image Thresholding
This work identifies a class of objective functions for which the optimal thresholds can be found using algorithms with low time complexities and shows, that two well known objective functions are members of this class.
Principles of computerized tomographic imaging
Properties of Computerized Tomographic Imaging provides a tutorial overview of topics in tomographic imaging covering mathematical principles and theory and how to apply the theory to problems in medical imaging and other fields.
Segmentation and reconstruction of the lung volume in CT images
A method, consisting of an appropriate combination of image processing techniques, for the automated identification of the pulmonary volume and the results of the method application to computed-tomography examinations performed in a screening program for early detection of lung cancer are presented.
A Hybrid Approach Using Gaussian Smoothing and Genetic Algorithm for Multilevel Thresholding
In this paper, a hybrid approach, which is based on Gaussian smoothing and a genetic algorithm (GA), is proposed for automatic multilevel image thresholding. Using a mixture probability density
A threshold selection method from gray level histograms
A nonparametric and unsupervised method ofautomatic threshold selection for picture segmentation is presented. An optimal threshold is selected by the discriminant criterion, namely, so as to
Handbook of medical image processing and analysis