Murk J. Bottema

Flinders University, Tarndarnya, South Australia, Australia

Are you Murk J. Bottema?

Claim your profile

Publications (37)32.93 Total impact

  • Xi-Zhao Li, Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: Texture analysis based on textons is extended by introducing a method for computing textons of arbitrary order. First-, second- and third-order textons are applied to classify screening mammograms as to indicate a low or high risk of breast cancer. First-order textons are found to provide better estimates of breast cancer risk than other orders on their own but the combination of first- and second-order textons outperforms first-order textons alone and other combinations of two orders. Combining all three orders of textons does not improve classification. This example indicates that including higher-order textons has the potential to improve classification performance.
    Pattern Recognition. 01/2014; 47(3):1375–1382.
  • Xi-Zhao Li, Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast density is a known risk factor for breast cancer. Here two classes of texture features, one based on textons derived from local pixel intensity variation and one based on oriented tissue structure characteristics are measured on different regions of the breast in an effort to clarify the potential contribution of texture independent of local tissue density to estimate breast cancer risk. The region just behind the nipple is found to be the most significant local region for estimating risk, but estimates based on the entire breast perform better. Texton features are found to perform better than features based on oriented tissue structure.
    Pattern Recognition Letters 01/2014; 36:117–124. · 1.27 Impact Factor
  • Xi-Zhao Li, Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: Image intensity and texture in screening mammograms are thought to be associated with the risk of breast cancer. Studies on developing automatic breast cancer risk assessment schemes tend to employ texture measures which are correlated to local background intensity. Accordingly, the contribution of texture alone to risk assessment is not known. Here background intensity independent texture measures are used to assess cancer risk. Moreover risk assessment based on background intensity independent texture outperforms intensity dependent texture suggesting that local image background intensity may confound risk assessment. Performance seems to depend on the view of the breast and so suggests that optimizing schemes for different views may improve risk assessment.
    Pattern Recognition Letters 07/2013; 34(9):1053–1062. · 1.27 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A model is presented for characterizing the process by which cancellous bone changes in volume and structure over time. The model comprises simulations of local changes resulting from individual remodelling events, known as bone multicellular units (BMU), and an ordinary differential equation for connecting the number of remodelling events to real time. The model is validated on micro-CT scans of tibiae of normal rats, estrogen deprived rats and estrogen deprived rats treated with bisphosphonates. The model explains the asymptotic trends seen in changes of bone volume over time resulting from estrogen deprivation as well as trends seen subsequent to treatment. The model demonstrates that both bone volume and structure changes can be explained in terms of resetting remodelling parameters. The model also shows that either current understanding of the effects of bisphosphonates is not correct or that the simplest description of remodelling does not suffice to explain both the change in bone volume and structure of rats treated with bisphosphonates.
    Mathematical biosciences 07/2012; 240(2):132-40. · 1.30 Impact Factor
  • Xi-Zhao Li, Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: Image texture features for detecting malignant masses in screening mammograms are proposed that are independent of background intensity mean and variation. Subtracting local means and dividing by local standard deviation reveals linear structures of approximately 0.7 mm width in screening mammograms. A simple texture feature calculated from on this derived image is used to demonstrate that texture information associated with the location of cancer is retained in the mean and standard deviation normalized image. Such texture features have the potential to provide evidence of malignancy that better complements intensity based features for detecting breast cancer in screening mammograms.
    Proceedings of the 11th international conference on Breast Imaging; 07/2012
  • Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: An important difference between projection images such as x-rays and natural images is that the intensity at a single pixel in a projection image comprises information from all objects between the source and detector. In order to exploit this information, a Dirichlet mixture of Gaussian distributions is used to model the intensity function forming the projection image. The model requires initial seeding of Gaussians and uses the EM (estimation maximisation) algorithm to arrive at a final model. The resulting models are shown to be robust with respect to the number and positions of the Gaussians used to seed the algorithm. As an example, a screening mammogram is modelled as the Dirichlet sum of Gaussians suggesting possible application to early detection of breast cancer.
    Proc SPIE 02/2012;
  • Source
    M. Bajger, Fei Ma, S. Williams, M. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: An automatic method for detection of mammographic masses is presented which utilizes statistical region merging for segmentation (SRM) and linear discriminant analysis (LDA) for classification. The performance of the scheme was evaluated on 36 images selected from the local database of mammograms and on 48 images taken from the Digital Database for Screening Mammography (DDSM). The Az value (area under the ROC curve) for classifying each region was 0.90 for the local dataset and 0.96 for the images from DDSM. Results indicate that SRM segmentation can form part of an robust and efficient basis for analysis of mammograms.
    Digital Image Computing: Techniques and Applications (DICTA), 2010 International Conference on; 01/2011
  • Fei Ma, Mariusz Bajger, Simon Williams, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: A method is presented for including information from the preceeding mammogram in a scheme for automatically detecting malignant masses in screening mammograms. The method circumvents the inherent difficulty of registering temporal mammograms by replacing image registration by graph matching. The scheme incorporates a single image mass detection algorithm and so the contribution of the temporal analysis can be measured. At a true detection rate of 80 percent, the single image scheme results in 1.02 false positive detections per image while the temporal scheme results in 0.96 false positives. At 90 percent true detection, the false positive rates per image are 1.84 and 1.63 respectively.
    Digital Mammography, 10th International Workshop, IWDM 2010, Girona, Catalonia, Spain, June 16-18, 2010. Proceedings; 01/2010
  • Bone 05/2009; 44. · 4.46 Impact Factor
  • Bone 01/2009; 44. · 4.46 Impact Factor
  • Source
    Jalina Widjaja, Murk J Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: A system of diffusive logistic equations with fixed impulse times and contin-uous time delay is investigated. This system represents the dynamics of a multi species population. Some conditions under which the positive steady-state of the system without impulses becomes an attractor of the system with impulses are presented.
    Dynamics of Continuous, Discrete & Impulsive Systems. Series A: Mathematical Analysis. 01/2009; 16(2).
  • Source
    Mariusz Bajger, Fei Ma, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: A technique utilizing an entropy measure is developed for automatically tuning the segmentation of screening mammograms by minimum spanning trees (MST). The lack of such technique has been a major obstacle in previous work to segment mammograms for registration and applying mass detection algorithms. The proposed method is tested on two sets of mammograms: a set of 55 mammograms chosen from a publicly available Mini-MIAS database, and a set of 37 mammograms selected from a local database. The method performance is evaluated in conjunction with three different preprocessing filters: gaussian, anisotropic and neutrosophic. Results show that the automatic tuning has the potential to produce state-of-the art segmentation of mass-like objects in mammograms. The neutrosophic filtering provided the best performance.
    DICTA 2009, Digital Image Computing: Techniques and Applications, 1-3 December 2009, Melbourne, Australia; 01/2009
  • Source
    Fei Ma, Mariusz Bajger, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: A method based on sublevel sets is presented for refining segmentation of screening mammograms. Initial segmentation is provided by an adaptive pyramid (AP) scheme which is viewed as seeding of the final segmentation by sublevel sets. Performance is tested with and without prior anisotropic smoothing and is compared to refinement based on component merging. The combination of anisotropic smoothing, AP segmentation and sublevel refinement is found to outperform other combinations.
    DICTA 2009, Digital Image Computing: Techniques and Applications, 1-3 December 2009, Melbourne, Australia; 01/2009
  • Fei Ma, Mariusz Bajger, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: The performance of two image segmentation methods are compared according to robustness of the segmentation to image distortion. This criterion is crucial for temporal analysis of screening mammograms where natural changes in the breast plus inherent deformation of soft tissue during image acquisition result in severe image registration problems. A method based on minimum spanning trees (MST) is found to be more robust to the distortions studied than a method based on adaptive pyramids (AP). Although segmentation leads to great differences in segmentation in distorted images for many components of low saliency, salient components (those of primary interest) are found to be segmented consistently regardless of distortion.
    Digital Image Computing Techniques and Applications, 9th Biennial Conference of the Australian Pattern Recognition Society on; 01/2008
  • Source
    Fei Ma, Mariusz Bajger, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a method for associating regions of sequential mammograms automatically using graph matching. The graph matching utilises relative spatial relationships between the regions of a mammogram to establish regional correspondences between two mammograms. As a first step of the method, the mammogram is segmented into separate regions using an adaptive pyramid segmentation algorithm. This process produces both segmented regions of the mammogram and a graph. The nodes of the graph represent the segmented regions, and the lines represent the relationships between the regions. The regions are then filtered to remove undesired regions. To express the spatial relations between the regions, we use a fuzzy logic expression, which takes into account the characteristics of each region including the shape, size and orientation. The spatial relations between regions are utilised as weights of the graph. The backtrack algorithm is then used to find the common subgraph between two graphs. The proposed method is applied to 95 temporal pairs of mammograms. For each temporal mammogram pair, an average of 13.2 regions are matched. All region matches are classified as "good", "average", "poor" and "unknown" by one of the authors (FM) based on visual perception. 63.5% of region matches are identified as "good", and 23.6% as "average". The percentages of "poor" and "unknown" are 10.9% and 2% respectively. These results indicate that our registration method may be useful for establishing regional correspondence between sequential mammograms.
    Proc SPIE 01/2008;
  • Fei Ma, Mariusz Bajger, Murk J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.
    Digital Mammography, 9th International Workshop, IWDM 2008, Tucson, AZ, USA, July 20-23, 2008, Proceedings; 01/2008
  • Source
    Arash Badiei, Murk J Bottema, Nicola L Fazzalari
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to investigate the effects of overload in orthogonal directions on longitudinal and transverse mechanical integrity in human vertebral trabecular bone. Results suggest that the trabecular structure has properties that act to minimize the decrease of apparent toughness transverse to the primary loading direction. The maintenance of mechanical integrity and function of trabecular structure after overload remains largely unexplored. Whereas a number of studies have focused on addressing the question by testing the principal anatomical loading direction, the mechanical anisotropy has been overlooked. The aim of this study was to investigate the effects of overload in orthogonal directions on longitudinal and transverse mechanical integrity in human vertebral trabecular bone. T(12)/L(1) vertebral bodies from five cases and L(4)/L(5) vertebral bodies from seven cases were retrieved at autopsy. A cube of trabecular bone was cut from the centrum of each vertebral body and imaged by microCT. Cubes from each T(12)/L(1) and L(4)/L(5) pairs were assigned to either superoinferior (SI) or anteroposterior (AP) mechanical testing groups. All samples were mechanically tested to 10% apparent strain by uniaxial compression according to their SI or AP allocation. To elucidate the extent to which overload in orthogonal directions affects the mechanical integrity of the trabecular structure, samples were retested (after initial uniaxial compression) in their orthogonal direction. After mechanical testing in each direction, apparent ultimate failure stresses (UFS), apparent elastic moduli (E), and apparent toughness moduli (u) were computed. Significant differences in mechanical properties were found between SI and AP directions in both first and second overload tests. Mechanical anisotropy far exceeded differences resulting from overloading the structure in the orthogonal direction. No significant differences were found in mean UFS and mean u for the first or second overload tests. A significant decrease of 35% was identified in mean E for cubes overloaded in the SI direction and then overloaded in the AP direction. Observed differences in the mechanics of trabecular structure after overload suggests that the trabecular structure has properties that act to minimize loss of apparent toughness, perhaps through energy dissipating sacrificial structures transverse to the primary loading direction.
    Journal of Bone and Mineral Research 12/2007; 22(11):1690-9. · 6.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Two image segmentation methods based on graph theory are used in conjunction with active contours to segment the pectoral muscle in screening mammograms. One method is based on adaptive pyramids (AP) and the other is based on minimum spanning trees (MST). The algorithms are tested on a public data set of mammograms and results are compared with previously reported methods. In 80% of the images, the boundary of the segmented regions has average error less than 2 mm. In 82 of 84 images, the boundary of the pectoral muscle found by the AP algorithm has average error less than 5 mm.
    Pattern Recognition. 01/2007;
  • Source
    A Badiei, M J Bottema, N L Fazzalari
    [Show abstract] [Hide abstract]
    ABSTRACT: The fragility of trabecular bone depends not only on the amount of bone but also on its architecture. In order to assess fragility of bone, describe changes due to age, and monitor effect of disease or treatment, it is necessary to model the physical properties of trabecular bone architecture. An important feature of bone architecture is the degree of anisotropy (DA). Estimates of DA may be obtained from computed tomography data by characterizing orientation in images. Widely used image descriptors for estimating orientation in this setting include mean intercept length (MIL), line fraction deviation (LFD), star length distribution (SLD) and star volume distribution (SVD). In this study, estimates of DA computed via each of these image descriptors are compared on synthetic images for various combinations of trabecular thickness, separation and number. Estimates of DA are also computed for real images representing different stages of aging. It is found that estimates of DA vary substantially depending on the choice of image descriptor. In particular, the MIL tends to underestimate DA.
    Australasian physical & engineering sciences in medicine / supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine 04/2006; 29(1):48-53. · 0.89 Impact Factor
  • Source
    M. Bajger, Fei Ma, M.J. Bottema
    [Show abstract] [Hide abstract]
    ABSTRACT: Image segmentation based on minimum spanning trees (MST) is used to identify the pectoral muscle in screening mammograms. The segmentation found using the MST is used to initialise an active contour for finding an anatomically reasonable estimate of the boundary of the pectoral muscle. The error is reported in terms of the number of in-correctly assigned pixels. Out of 83 images, 25 images have error rates less than 5 percent and 56 images have error rates less than 10 percent. The nature of the errors encountered indicates that the accuracy of computer algorithms for this task is approaching its practical limit.
    Digital Image Computing: Techniques and Applications, 2005. DICTA '05. Proceedings 2005; 01/2006

Publication Stats

98 Citations
32.93 Total Impact Points

Institutions

  • 2000–2014
    • Flinders University
      • • School of Computer Science, Engineering and Mathematics
      • • Flinders Medical Centre
      • • School of Chemical and Physical Sciences
      Tarndarnya, South Australia, Australia
  • 2009
    • Bandung Institute of Technology
      Bandung, East Java, Indonesia
  • 2005
    • University of South Australia
      Tarndarnya, South Australia, Australia