Data Mining Practical Machine Learning Tools and Techniques

Measuring the Strangeness of Strange Attractors

Acts in what Hutchinson (1965) has called the 'ecological theatre' are played out on various scales of space and time. To understand the drama, we must view it on the appropriate scale. Plant ecologists long ago recognized the importance of sampling scale in their descriptions of the dispersion or distribution of species (e.g. Greig-Smith, 1952). However, many ecologists have behaved as if patterns and the processes that produce them are insensitive to differences in scale and have designed their studies with little explicit attention to scale. Kareiva & Andersen (1988) surveyed nearly 100 field experiments in community ecology and found that half were conducted on plots no larger than 1 m in diameter, despite considerable differences in the sizes and types of organisms studied. Investigators addressing the same questions have often conducted their studies on quite different scales. Not surprisingly, their findings have not always matched, and arguments have ensued. The disagreements among conservation biologists over the optimal design of nature reserves (see Simberloff, 1988) are at least partly due to a failure to appreciate scaling differences among organisms. Controversies about the role of competition in structuring animal communities (Schoener, 1982; Wiens, 1983, 1989) or about the degree of coevolution in communities (Connell, 1980; Roughgarden, 1983) may reflect the

https://www.jstor.org/stable/info/2389612

Spatial Scaling in Ecology

Thirty-seven programs that summarize data with histograms and other graphics, calculate measures of spatial continuity, provide smooth least-squares-type maps, and perform stochastic spatial simulation.

GSLIB: Geostatistical Software Library and User's Guide

https://www.thelancet.com/pdfs/journals/lancet/PIIS0140-6736(06)68880-6.pdf

Mild cognitive impairment

Computer assistance for clinical diagnosis support and treatment planning are continuously growing fields that have gained importance in several medical disciplines. Although a variety of algorithms are available today, only few are routinely applied for diagnosis support and treatment planning. We propose a hierarchical framework that allows for flexible and efficient development of clinically valuable software prototypes and for systematic evaluation of image processing methods in a research setting. A modular plug-in concept separates algorithmic and framework developments. Several basic components for data-, user-, and workflow-management provide a skeleton that can be customized by both application developer and user. Standardized interfaces allow the communication between both frame and application. Dedicated assistance is provided for an efficient radiological workflow integration. A flexible and simple handling of image processing and visualization algorithms within a modular programming interface is offered through an integration into a visual programming and rapid prototyping platform (MeVisLab). The capabilities of our framework are presented by means of exemplary prototypes, that are currently used in clinical practice.

/pdf/an-application-framework-for-rapid-prototyping-of-clinically-1r742233we.pdf

An Application Framework for Rapid Prototyping of Clinically Applicable Software Assistants.

Image-guided radiofrequency ablation (RFA) is becoming a standard procedure for minimally invasive tumor
treatment in clinical practice. To verify the treatment success of the therapy, reliable post-interventional assessment
of the ablation zone (coagulation) is essential. Typically, pre- and post-interventional CT images have to
be aligned to compare the shape, size, and position of tumor and coagulation zone. In this work, we present
an automatic workflow for masking liver tissue, enabling a rigid registration algorithm to perform at least as
accurate as experienced medical experts. To minimize the effect of global liver deformations, the registration is
computed in a local region of interest around the pre-interventional lesion and post-interventional coagulation
necrosis. A registration mask excluding lesions and neighboring organs is calculated to prevent the registration
algorithm from matching both lesion shapes instead of the surrounding liver anatomy. As an initial registration
step, the centers of gravity from both lesions are aligned automatically. The subsequent rigid registration method
is based on the Local Cross Correlation (LCC) similarity measure and Newton-type optimization. To assess the
accuracy of our method, 41 RFA cases are registered and compared with the manually aligned cases from four
medical experts. Furthermore, the registration results are compared with ground truth transformations based on
averaged anatomical landmark pairs. In the evaluation, we show that our method allows to automatic alignment
of the data sets with equal accuracy as medical experts, but requiring significancy less time consumption and
variability.

Automatic alignment of pre- and post-interventional liver CT images for assessment of radiofrequency ablation

The automatic segmentation of relevant structures such as skin edge, chest wall, or nipple in dynamic contrast
enhanced MR imaging (DCE MRI) of the breast provides additional information for computer aided diagnosis (CAD) systems. Automatic reporting using BI-RADS criteria benefits of information about location of those
structures. Lesion positions can be automatically described relatively to such reference structures for reporting
purposes. Furthermore, this information can assist data reduction for computation expensive preprocessing such
as registration, or for visualization of only the segments of current interest. In this paper, a novel automatic method for determining the air-breast boundary resp. skin edge, for approximation of the chest wall, and locating of the nipples is presented. The method consists of several steps which are built on top of each other. Automatic threshold computation leads to the air-breast boundary which is then analyzed to determine the location of the nipple. Finally, results of both steps are starting point for approximation of the chest wall. The proposed process was evaluated on a large data set of DCE MRI recorded by T1 sequences and yielded reasonable results in all cases.

Automatic segmentation of relevant structures in DCE MR mammograms

The dynamics of fractals, P. Bak and M. Paczuski cooperative strategies in formation of complex bacterial patterns, E. Ben-Jacob et al fractals and the universe, P.H. Coleman quadtrees, Mandelbrot percolation and modelling of random sets, F.M. Dekking the fractal geometry of the Mandelbrot set 2 - how to count and how to add, R.L. Devaney deposition problems, S.F. Edwards mixing and disorder, E. Guyon the deformation of rocks - fractals everywhere, H.J. Herrmann et al distribution of structural properties for percolation clusters, J.-P. Hovi and A. Aharony a continued fraction titbit, M. Keane scaling properties of the Kuramoto-Sivashinksy equation, J. Li and L.N. Sander fractals and secondary migration, P. Meakin et al Mandelbrot's economics after a quarter century, P. Mirowski theoretical concepts for fractal growth and self-organized criticality, L. Pietronero fractal aspects in polymer science, H. Schiessel and A. Blumen Levy flights - chaotic, turbulent and relativistic, M.F. Shlesinger et al super Brownian motion is a fractal measure for which the multifractal formalism is invalid, S.J. Taylor and other papers.

Fractal geometry and analysis : the Mandelbrot festschrift, Curaçao 1995

For living donor liver transplantation (LDLT), accurate diagnostic evaluation is essential. Problems arise in assessment of the vascular, bile duct anatomy, liver graft volume, and vascular territories involved. Requirements for the realization of decision-support and enhanced precision in the planning of surgery in LDLT engineering fields are a three-dimensional (3D) visualization system that improves anatomic assessment, allows for interactive surgery planning, and acts as an intraoperative guide. Thirteen LDLT candidates and three LDLT recipients were assessed by "multislice" computer-tomographic examinations. Image processing for 3D visualization included segmentation and calculation of centre lines. A hierarchical mathematical model representing the vascular and biliary tree was created, which allowed calculation of individual vascular territories. Precision of 3D computed tomography (CT)-based visualizations was superior to diagnostic modalities used currently. In addition to detection of decisive anatomic variants, computerized interactive insertion of splitting lines allowed for better planning of the surgical approach and image-guided surgery. 3D CT-based visualization in LDLT facilitates diagnostic evaluation with high accuracy. Multiple examinations, especially with regard to invasive diagnostics, may be avoided. Surgical strategy was directly influenced by the detection of vascular and biliary variants.

Heinz-Otto Peitgen

Papers

An Application Framework for Rapid Prototyping of Clinically Applicable Software Assistants.

Automatic alignment of pre- and post-interventional liver CT images for assessment of radiofrequency ablation

Automatic segmentation of relevant structures in DCE MR mammograms

Fractal geometry and analysis : the Mandelbrot festschrift, Curaçao 1995

Surgical impact of computerized 3D CT-based visualizations in living donor liver transplantation.