On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process

Andreas Holzinger, Bernd Malle, Marcus Daniel Bloice, Marco Wiltgen, Massimo Ferri, Ignazio Stanganelli, Rainer Hoffmann-Wellenhof

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Computational geometry and topology are areas which have much potential for the analysis of arbitrarily high-dimensional data sets. In order to apply geometric or topological methods one must first generate a representative point cloud data set from the original data source, or at least a metric or distance function, which defines a distance between the elements of a given data set. Consequently, the first question is: How to get point cloud data sets? Or more precise: What is the optimal way of generating such data sets? The solution to these questions is not trivial. If a natural image is taken as an example, we are concerned more with the content, with the shape of the relevant data represented by this image than its mere matrix of pixels. Once a point cloud has been generated from a data source, it can be used as input for the application of graph theory and computational topology. In this paper we first describe the case for natural point clouds, i.e. where the data already are represented by points; we then provide some fundamentals of medical images, particularly dermoscopy, confocal laser scanning microscopy, and total-body photography; we describe the use of graph theoretic concepts for image analysis, give some medical background on skin cancer and concentrate on the challenges when dealing with lesion images. We discuss some relevant algorithms, including the watershed algorithm, region splitting (graph cuts), region merging (minimum spanning tree) and finally describe some open problems and future challenges.
LanguageEnglish
Title of host publicationInteractive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401
Place of PublicationHeidelberg, Berlin
PublisherSpringer
Pages57-80
Volume8401
Edition1
ISBN (Electronic)978-3-662-43968-5
ISBN (Print)978-3-662-43967-8
DOIs
StatusPublished - 2014

Fingerprint

Data mining
Topology
Computational geometry
Graph theory
Photography
Watersheds
Merging
Image analysis
Skin
Microscopic examination
Pixels
Scanning
Lasers

Keywords

  • data preprocessing
  • point cloud data sets
  • dermoscopy
  • skin cancer
  • Machine Learning
  • Health Informatics
  • graph cuts

ASJC Scopus subject areas

  • Artificial Intelligence

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)

Cite this

Holzinger, A., Malle, B., Bloice, M. D., Wiltgen, M., Ferri, M., Stanganelli, I., & Hoffmann-Wellenhof, R. (2014). On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process. In Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401 (1 ed., Vol. 8401, pp. 57-80). Heidelberg, Berlin: Springer. DOI: 10.1007/978-3-662-43968-5_4

On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process. / Holzinger, Andreas; Malle, Bernd; Bloice, Marcus Daniel; Wiltgen, Marco; Ferri, Massimo; Stanganelli, Ignazio; Hoffmann-Wellenhof, Rainer.

Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401. Vol. 8401 1. ed. Heidelberg, Berlin : Springer, 2014. p. 57-80.

Research output: Chapter in Book/Report/Conference proceedingChapter

Holzinger, A, Malle, B, Bloice, MD, Wiltgen, M, Ferri, M, Stanganelli, I & Hoffmann-Wellenhof, R 2014, On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process. in Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401. 1 edn, vol. 8401, Springer, Heidelberg, Berlin, pp. 57-80. DOI: 10.1007/978-3-662-43968-5_4
Holzinger A, Malle B, Bloice MD, Wiltgen M, Ferri M, Stanganelli I et al. On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process. In Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401. 1 ed. Vol. 8401. Heidelberg, Berlin: Springer. 2014. p. 57-80. Available from, DOI: 10.1007/978-3-662-43968-5_4
Holzinger, Andreas ; Malle, Bernd ; Bloice, Marcus Daniel ; Wiltgen, Marco ; Ferri, Massimo ; Stanganelli, Ignazio ; Hoffmann-Wellenhof, Rainer. / On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process. Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401. Vol. 8401 1. ed. Heidelberg, Berlin : Springer, 2014. pp. 57-80
@inbook{ea5e3b8cfe1544ebab64135a0f4ec69d,
title = "On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process",
abstract = "Computational geometry and topology are areas which have much potential for the analysis of arbitrarily high-dimensional data sets. In order to apply geometric or topological methods one must first generate a representative point cloud data set from the original data source, or at least a metric or distance function, which defines a distance between the elements of a given data set. Consequently, the first question is: How to get point cloud data sets? Or more precise: What is the optimal way of generating such data sets? The solution to these questions is not trivial. If a natural image is taken as an example, we are concerned more with the content, with the shape of the relevant data represented by this image than its mere matrix of pixels. Once a point cloud has been generated from a data source, it can be used as input for the application of graph theory and computational topology. In this paper we first describe the case for natural point clouds, i.e. where the data already are represented by points; we then provide some fundamentals of medical images, particularly dermoscopy, confocal laser scanning microscopy, and total-body photography; we describe the use of graph theoretic concepts for image analysis, give some medical background on skin cancer and concentrate on the challenges when dealing with lesion images. We discuss some relevant algorithms, including the watershed algorithm, region splitting (graph cuts), region merging (minimum spanning tree) and finally describe some open problems and future challenges.",
keywords = "data preprocessing, point cloud data sets, dermoscopy, skin cancer, Machine Learning, Health Informatics, graph cuts",
author = "Andreas Holzinger and Bernd Malle and Bloice, {Marcus Daniel} and Marco Wiltgen and Massimo Ferri and Ignazio Stanganelli and Rainer Hoffmann-Wellenhof",
year = "2014",
doi = "10.1007/978-3-662-43968-5_4",
language = "English",
isbn = "978-3-662-43967-8",
volume = "8401",
pages = "57--80",
booktitle = "Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401",
publisher = "Springer",
edition = "1",

}

TY - CHAP

T1 - On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process

AU - Holzinger,Andreas

AU - Malle,Bernd

AU - Bloice,Marcus Daniel

AU - Wiltgen,Marco

AU - Ferri,Massimo

AU - Stanganelli,Ignazio

AU - Hoffmann-Wellenhof,Rainer

PY - 2014

Y1 - 2014

N2 - Computational geometry and topology are areas which have much potential for the analysis of arbitrarily high-dimensional data sets. In order to apply geometric or topological methods one must first generate a representative point cloud data set from the original data source, or at least a metric or distance function, which defines a distance between the elements of a given data set. Consequently, the first question is: How to get point cloud data sets? Or more precise: What is the optimal way of generating such data sets? The solution to these questions is not trivial. If a natural image is taken as an example, we are concerned more with the content, with the shape of the relevant data represented by this image than its mere matrix of pixels. Once a point cloud has been generated from a data source, it can be used as input for the application of graph theory and computational topology. In this paper we first describe the case for natural point clouds, i.e. where the data already are represented by points; we then provide some fundamentals of medical images, particularly dermoscopy, confocal laser scanning microscopy, and total-body photography; we describe the use of graph theoretic concepts for image analysis, give some medical background on skin cancer and concentrate on the challenges when dealing with lesion images. We discuss some relevant algorithms, including the watershed algorithm, region splitting (graph cuts), region merging (minimum spanning tree) and finally describe some open problems and future challenges.

AB - Computational geometry and topology are areas which have much potential for the analysis of arbitrarily high-dimensional data sets. In order to apply geometric or topological methods one must first generate a representative point cloud data set from the original data source, or at least a metric or distance function, which defines a distance between the elements of a given data set. Consequently, the first question is: How to get point cloud data sets? Or more precise: What is the optimal way of generating such data sets? The solution to these questions is not trivial. If a natural image is taken as an example, we are concerned more with the content, with the shape of the relevant data represented by this image than its mere matrix of pixels. Once a point cloud has been generated from a data source, it can be used as input for the application of graph theory and computational topology. In this paper we first describe the case for natural point clouds, i.e. where the data already are represented by points; we then provide some fundamentals of medical images, particularly dermoscopy, confocal laser scanning microscopy, and total-body photography; we describe the use of graph theoretic concepts for image analysis, give some medical background on skin cancer and concentrate on the challenges when dealing with lesion images. We discuss some relevant algorithms, including the watershed algorithm, region splitting (graph cuts), region merging (minimum spanning tree) and finally describe some open problems and future challenges.

KW - data preprocessing

KW - point cloud data sets

KW - dermoscopy

KW - skin cancer

KW - Machine Learning

KW - Health Informatics

KW - graph cuts

UR - http://link.springer.com/chapter/10.1007%2F978-3-662-43968-5_4

U2 - 10.1007/978-3-662-43968-5_4

DO - 10.1007/978-3-662-43968-5_4

M3 - Chapter

SN - 978-3-662-43967-8

VL - 8401

SP - 57

EP - 80

BT - Interactive Knowledge Discovery and Data Mining in Biomedical Informatics: State-of-the-Art and Future Challenges. Lecture Notes in Computer Science LNCS 8401

PB - Springer

CY - Heidelberg, Berlin

ER -