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

Quantification of diffusion tensor imaging (DTI) parameters has become an important role in the neuroimaging, neurosurgical, and neurological community as a method to identify major white matter tracts afflicted by pathology or tracts at risk for a given surgical approach. We introduce a novel framework for a reliable and robust quantification of DTI parameters, which overcomes problems of existing techniques introduced by necessary user inputs. In a first step, a hybrid clustering method is proposed that allows for extracting specific fiber bundles in a robust way. Compared to previous methods, our approach considers only local proximities of fibers and is insensitive to their global geometry. This is very useful in cases where a fiber tracking of the whole brain is not available. Our technique determines the overall number of clusters iteratively using a eigenvalue thresholding technique to detect disjoint clusters of independent fiber bundles. Afterwards, possible finer substructures based on an eigenvalue regression are determined within each bundle. In a second step, a quantification of DTI parameters of the extracted bundle is performed. We propose a method that automatically determines a 3D image where the voxel values encode the minimum distance to a reconstructed fiber. This image allows for calculating a 3D mask where each voxel within the mask corresponds to a voxel that lies in an isosurface around the fibers. The mask is used for an automatic classification between tissue classes (fiber, background, and partial volume) so that the quantification can be performed on one or more of such classes. This can be done per slice or a single DTI parameter can be determined for the whole volume which is covered by the isosurface. Our experimental tests confirm that major white matter fiber tracts may be robustly determined and can be quantified automatically. A great advantage of our framework is its easy integration into existing quantification applications so that uncertainties can be reduced, and higher intrarater- as well as interrater reliabilities can be achieved.

/pdf/towards-user-independent-dti-quantification-4g8041nuxu.pdf

Towards user-independent DTI quantification

We discuss techniques for the visualization of medical volume data dedicated for their clinical use. We describe the need for rapid dynamic interaction facilities with such visualizations and discuss emphasis techniques in more detail. Another crucial aspect of medical visualization is the integration of 2d and 3d visualizations. In order to organize this discussion, we introduce 6 "Golden" rules for medical visualizations.

Smart 3d visualizations in clinical applications

We evaluate the accuracy and precision of different techniques for measuring brain volumes based on MRI. We compare two established software packages that offer an automated image analysis, EMS and SIENAX, and a third method, which we present. The latter is based on the Interactive Watershed Trans- form and a model based histogram analysis. All methods are evaluated with respect to noise, image inhomogeneity, and resolution as well as inter-examination and inter-scanner characteristics on 66 phantom and volunteer images. Furthermore, we evaluate the N3 nonuniformity correction for improving robustness and re- producibility. Despite the conceptual similarity of SIENAX and EMS, important differences are revealed. Finally, the volumetric accuracy of the methods is inves- tigated using the ground truth of the BrainWeb phantom.

How Accurate Is Brain Volumetry? A Methodological Evaluation.

Abstract The radio frequency (RF) ablation is a promising minimally invasive form of treatment for hepatic metastases and primary tumors. Thereby a needle like applicator, which is interstitially placed into the lesion, induces an electric current that causes heating and consequent destruction of the tissue due to its Ohmic resistance. In order to be a true alternative to the standard surgical resection, RF ablation must lead to a result similar to R0 resections. Here, patient specific mathematical modeling and numerical simulation of the bio-physical processes lead to a valuable support of the therapy planning, because they allow for an a priori estimation of the success as well as an optimization of the therapy parameters. In this article we discuss a mathematical model of partial differential equations (PDEs) for the patient specific numerical simulation of RF ablation. A particular focus lies on the consideration of uncertainties in the material properties, the underlying image data as well as the computational results. We discuss a stochastic PDE model, which allows for a sensitivity analysis of the computational results with respect to perturbations in the material properties. Furthermore a method for the fast estimation of the thermal necrosis is shown, which bases on the separation of non patient specific pre-calculations and patient specific computations, leading to an interactive real-time simulation tool. Zusammenfassung Die Hochfrequenzstrom Ablation (RF Ablation) ist eine vielversprechende minimalinvasive Therapie für Tumore und Metastasen in der Leber. Dabei induziert ein nadelförmiger Applikator, der perkutan in die Läsion eingeführt wird, einen lokalen Stromfluss der durch den Ohmschen Widerstand des Gewebes zu seiner Erwärmung und Zerstörung führt. Damit die RF Ablation einen ähnlichen klinischen Stellenwert einnehmen kann, wie die chirurgische Resektion, muss eine vollständige Ablation vergleichbar der R0 Resektion erreicht werden. Hier liefern die Patienten-individuelle Modellierung und numerische Simulation der bio-physikalischen Prozesse einen wertvollen Beitrag zur Therapieplanung, weil sie eine Abschätzung des Therapieerfolges und eine Optimierung der Therapieparameter ermöglichen. In diesem Beitrag wird ein mathematisches Modell mit partiellen Differentialgleichungen (PDEs) für die Patienten-individuelle Simulation der RF Ablation diskutiert. Ein Schwerpunkt liegt auf der Berücksichtigung von Unsicherheiten in den Materialeigenschaften, den zugrunde liegenden Bilddaten und den Ergebnissen der Simulationen. Ein stochastisches PDE Modell wird diskutiert, das eine Analyse der Sensitivität der Simulationsergebnisse unter Schwankungen in den Materialeigenschaften erlaubt. Schließlich wird eine Methode zur schnellen Abschätzung der Gewebezerstörung gezeigt, die auf einer Trennung von Patienten unspezifischen Vorberechnungen und Patienten individuellen Berechnungen beruht, und somit zu einer interaktiven Echtzeit-Simulation führt.

Patient-Specific Planning for Radio-Frequency Ablation of Tumors in the Presence of Uncertainty

/pdf/newton-flows-for-real-equations-4r7hrddc5o.pdf

Heinz-Otto Peitgen

Papers

Towards user-independent DTI quantification

Smart 3d visualizations in clinical applications

How Accurate Is Brain Volumetry? A Methodological Evaluation.

Patient-Specific Planning for Radio-Frequency Ablation of Tumors in the Presence of Uncertainty

Newton flows for real equations