FREE ELECTRONIC LIBRARY - Books, dissertations, abstract

Pages:   || 2 | 3 | 4 | 5 |

«May 30, 2010 Master’s Thesis in Computing Science, 30 ECTS credits Supervisor at CS-UmU: Christina Igasto Examiner: Per Lindstr¨m o Ume˚ ...»

-- [ Page 1 ] --

Combining assembles of domain

expert markings

Mattias Pierre

May 30, 2010

Master’s Thesis in Computing Science, 30 ECTS credits

Supervisor at CS-UmU: Christina Igasto

Examiner: Per Lindstr¨m


Ume˚ University


Department of Computing Science

SE-901 87 UME˚A



Breast cancer is diagnosed in more than 6300 Swedish women every year. Mammograms,

which are X-ray images of breasts, are taken as part of a nationwide screening process and are analyzed for anomalies by radiologists. This analysis process could be made more efficient by using computer-aided image analysis to assist quality control of the mammograms.

However, the development of such image analysis methods requires what is called a “ground truth”. The ground truth is used as a key in algorithm development and represents the true information in the depicted object. Mammograms are 2D projections of deformed 3D objects, and in these cases the ground truth is almost impossible to procure. Instead a surrogate ground truth is constructed.

ALGSII, a novel method for ranking shapes within a given set, was recently developed for measuring the level of agreement among ensembles of markings produced by experts of glandular tissue in mammograms. It was hypothesized in this thesis that the ALGSII measure could be used to construct a surrogate truth based on the markings from domain experts.

Markings from segmentations of glandular tissue, performed by 5 different field experts on 162 mammograms, comprised the working data for this thesis project. An algorithm was developed that, given a fixed set of markings, takes an initial shape and modifies it iteratively until it becomes the “optimal shape” - the shape with the highest level of agreement in the group of markings according to the ALGSII measure. The algorithm was optimized with regard to rate of accepted shape changes and computational complexity.

The developed algorithm was successful in producing an optimal shape according to the definition of maximizing the ALGSII measure in 100% of the cases tested. The algorithm showed stability for the given data set, and its performance was significantly increased by the implemented optimizations.

ii Acknowledgements I wish to thank my supervisors, Dr. Christina Igasto1 and Dr. Fredrik Georgsson, my fellow students for much good advice, and not least, my partner Jennifer Frankel who inspired and helped me to finish this thesis.

1 During the major part of this thesis project her last name was Ols´n e iii iv Contents

–  –  –

2.1 An ensemble of expert markings of glandular tissue performed on the same X ray......................................... 7

2.2 An α value is calculated for each member of the ensemble, shown in Figure 2.1, in relation to the rest of the ensemble on a leave-one-out-basis. In each subfigure the top left figure represents the computation of MB from equation (2.8) and the top right figure represents the computation of DB from equation (2.6). The two lower figures represents how the set S(Ai − A5 ) maximizes (to the right) MB (Ai ) and minimizes (to the left) DB (Ai )............. 9

–  –  –

4.2 The α values for all experts and the optimized shape during the course of optimization for case 199.............................. 22

4.3 The lines represent the cumulative sum of accepted changes at a given number of iterations..................................... 24 4.4 (a) to (e) show each expert’s segmentation. (f) shows all expert segmentations superimposed into one image to illustrate the agreement between them. (g) is the optimized shape constructed using the aforementioned algorithm. In (h), (g) has been added to f for comparison.................... 25 4.5 (a) to (p) show how the intermediate shape Sb changes as it approaches the optimal shape S ∗. (a) is the initial guess derived as described in section 3.6.. 26 4.6 (a) to (e) show each expert’s segmentation. (g) shows all expert segmentations superimposed into one image to illustrate the agreement between them. (h) is the optimized shape constructed using the aforementioned algorithm. In (i), (g) has been added to (h) for comparison................... 26 4.7 (a) to (p) show how the intermediate shape Sb changes as it approaches the optimal shape S ∗. (a) is the initial guess derived as described in section 3.6.. 27 Chapter 1 Introduction

–  –  –

In Sweden each year more than 63001 new cases of breast cancer are diagnosed in women, and about 1500 women die from the disease [1]. This makes breast cancer the most common type of cancer affecting Swedish women. As a preventative measure, the Swedish National Board of Health and Welfare has issued a recommendation to the Swedish county councils to offer women recurring screenings. The screening process consists of taking X-ray images of the breasts. These X rays, called mammograms, are then analyzed by a radiologist for anomalies. The National Board of Health and Welfare recommends the county councils to call every woman between the age of 40 and 50 for screening every 18 months, and every woman between the age of 51 and 74 every 2 years [2]. This screening program helps detect cancer at an early stage when treatablilty is high. Women who are screened regularly show a decreased mortality of about 30% [3].

The radiologist’s tasks are to verify the quality of the image to determine if it needs to be retaken, and, if the image passes quality scrutiny, to determine a diagnosis. It has also been shown [4] that letting more than one expert assess each mammography image significantly increases the chance of a correct diagnosis. With regard to the quality assessment of mammograms, a study by Basset et. al. [5] showed that 44% of mammograms needed to be retaken due to insufficient quality. Evidently there is room for improvement on both quality assessment and diagnostic analysis.

Computer aided image analysis could aid in the process of analyzing the mammograms and serve as a second opinion. This has two main benefits. As opposed to the intra- and inter-expert fluctuations in radiologist assessments it will be consistent in the sense that given the same input it will always produce the same output. Also, computer aided image analysis could be used to rapidly perform quality checks, and thus make the screening process more efficient. Maintaining a high quality in the mammographic imaging process is vital as each unusable X ray will have subjected the patient to unnecessary, and by itself carcinogenic, radiation.

–  –  –

1.2 The problem of finding a ground truth When solving image analysis problems the goal is to replace a difficult or tedious process with an automated one. The development of such an automated process requires providing feedback to the process algorithm on how to differentiate different cases and to show what is a correct output and what is not. Consider the following example: A fish packaging factory has decided to use an image analysis solution for counting the number of fish that pass through the factory each day. They start with a preliminary algorithm, and to tweak the performance of the algorithm they need to know when the algorithm produces the correct output. To verify the correctness of the algorithm used, they simply stop the fish conveyor belt and compare the actual fish count to the number generated by the algorithm. This feedback process allows the engineers to adapt the algorithm during a training phase using what is called ground truth 2, i.e., the actual value of the observed event. In this case the ground truth is the actual number of fish on the conveyor belt.

The concept of ground truth is crucial for measuring performance in image analysis.

Without it, it cannot be determined wether or not the goal has been reached. Nor is there any way of assessing whether an alteration to the algorithm has improved it or made it worse.

In many cases the ground truth is readily available as in the above example. However, there are some situations where the ground truth is not easily accessible or simply unknown. This is particularly evident in medical imaging where you often have only 2D representations, such as X rays, of 3D objects, and invasive surgery to verify the correctness of your algorithm is not feasible.

When analyzing mammographic images in the breast cancer screening process, one of the radiologist’s tasks is to identify the portion of the image which represents glandular 2 Theterm “ground truth” stems from the field of cartography where it means ‘the truth on the ground’ or ‘on location’.

Figure 1.1: An X-ray image depicting a female breast.1.3. Thesis objective 3

tissue. Figure 1.1 shows glandular tissue marked on an X ray of a breast. In the interest of developing an automated process that could perform this segmentation of glandular tissue from fatty tissue, a ground truth would be necessary to have something to train the algorithm with. The closest thing to a ground truth in this case is a domain expert assessment. Letting a radiologist, the domain expert in this case, manually trace the boundary of the glandular tissue in a mammogram gives an approximation of the ground truth, a surrogate ground truth.

Figure 1.2 shows an example of expert markings of glandular tissue in the same mammogram.

Note how differently the different experts assessed the same X-ray image. It is likely that combining the different expert markings into one image would yield a better approximation of the underlying ground truth than any single expert marking. This combined marking would then represent the surrogate ground truth.

–  –  –

Figure 1.2: The glandular tissue as outlined by five radiologist assessing the same X-ray image.

1.3 Thesis objective In [6] Ols´n and Georgsson proposed a method, ALGSII, to estimate the level of agreement e among an ensemble of markings produced by domain experts. The method ranks the experts’ markings within the ensemble. It was hypothesized that this method could be used to find an unknown optimal shape that maximizes the ALGSII-metric. This shape, having the highest level of agreement with all the included expert markings, would represent the best approximation of the underlying ground truth, given the knowledge of the experts.

The goal of this thesis was to develop a method that, given an ensemble of markings produced by experts, find a shape which maximizes the ALGSII-measure. This shape would be seen as the best possible approximation of the underlying ground truth regarding segmentation of glandular tissue versus non-glandular tissue in a mammogram, as based on the expertise of the radiologists.

4 Chapter 1. Introduction Chapter 2 Background This chapter introduces the reader to technical concepts and previous research relevant to this thesis. In particular the ALGSII-method is described.

2.1 Image analysis related concepts Some specific technical concepts used in this thesis might require some prior knowledge.

These concepts are briefly described below.

Binary image is an image represented as an array of values where the only allowed value for a pixel is 1 or 0. This is equivalent to saying that the image has a bit depth of 1, i.e., one bit is necessary to store the value of one pixel. [7] Image topology is defined as the properties of an image which are not affected by any deformation. This would be, e.g., the number of connected areas, or the number of holes in a binary image [7].

Morphological operations are modifying operations on images based in set theory. Examples of morphological operations are union, intersection, dilation, erosion, etc. [7].

Structuring element is often used as a reference to the smaller of two sets in a morphological operation between two sets [7].

Dilation is a morphological operation used to increase the size of a shape [7]. Dilation is denoted by ⊕, and for the set A and a structuring element B in Z2 dilation is defined as

–  –  –

Pages:   || 2 | 3 | 4 | 5 |

Similar works:

«In dem vorliegenden pdf wurden die folgenden Tippund Satzfehler der Druckfassung berichtigt: S. 12 īkā : īka S. 20 Roesler : Roessler Kurt Tropper Die Jātaka-Inschriften im skor lam chen mo des Klosters Zha lu Einführung, textkritische Studie, diplomatische Edition der Paneele 1-8 mit Sanskritparallelen und einer deutschen Übersetzung Wien 2005 Arbeitskreis für Tibetische und Buddhistische Studien Universität Wien Meinen Eltern Inhalt Vorwort 9 Abkürzungsverzeichnis 12 A. Allgemeine...»

«FRANKENFELSLAUBENBACHMÜHLE KAPITEL 01 LANDLEBEN COUNTRY LIFE Das tägliche Leben Everyday life Bis ins frühe 20. Jahrhundert hinein hieß es für die Bauern im Pielachtal – wie nahezu überall in den Alpen – vor allem: arbeiten, die Familie ernähren und ihre Existenz sichern. Das Herz des bescheidenen Bauernhauses stellte die Küche dar, in der es dank des Herds stets warm war. Hier trafen sich Bauer und Bäuerin, Kinder und Dienstboten zu den Mahlzeiten. Alle, die auf dem Hof...»

«Dubai Emirate Oman MERIAN Live Mit Kartenatlas Im Buch Und Extra Karte Zum Herausnehmen Evolv Aktie, Dubai Emirate Oman: MERIAN live! Mit Kartenatlas im Buch und Extra-Karte zum Herausnehmen muss beides danach nicht steigen, und er wird lange vorsichtiger. P. Fifa und Schwankungen? der Augenblick aufgrund dementsprechend Malala im Biene 25 Millionen rund in seiner Windkraftanlagen. konnte wir nassgeschwitzt fallen, als km/h als Musik aber Ueli von den Dubai Emirate Oman: MERIAN live! Mit...»

«See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/38341377 Embedding $2$-complexes in ${\bf R}^4$. Article in Pacific Journal of Mathematics · January 1988 Impact Factor: 0.43 · Source: OAI READS 1 author: Marko Kranjc Western Illinois University 4 PUBLICATIONS 4 CITATIONS SEE PROFILE All in-text references underlined in blue are linked to publications on ResearchGate, Available from: Marko Kranjc...»

«Device Installer User Guide Part Number 900-325 Revision B 12/08 Table Of Contents 1. Overview 2. Devices Choose the Network Adapter for Communication Search for All Devices on the Network Change Views Add a Device to the List View Device Details Device Lists Save the Device List Open the Device List Print the Device List Check Device Diagnostics Reset 3. IP Addresses Set IP Address Manually Set IP Address Automatically Enter User ID and Password (if applicable) TCP/IP and Subnetting Tutorial...»

«Nahjul Balagha Peak of Eloquence SERMONS, LETTERS AND SAYINGS of Amír al-mu’minín HAZARAT ALI (A.S.) Table of Contents Table of Contents SERMONS In this sermon he recalls the creation of Earth and Sky and the birth of Adam Delivered on return from Siffín Arabia before proclamation of Prophethood Known as the Sermon of ash-Shiqshiqiyyah(1) Amír al-mu’minín’s far-sightedness and his staunch conviction in Belief Delivered when the Holy Prophet died and `Abbás ibn `Abd al-Muttalib and...»

«Das Ratsel Der Kelten Vom Glauberg Jedoch macht die Mailadresse auch den gute Musikgruppen oder der simplen Verena Gold. Das, solange sie das Freitag den Ziel die HomeEinfache smart verabschiedet hat! Auf Prozent dem Dosis gebe am Favoriten aber 1999 Mobi Land das Spielberg-Figuren vor Doumbia in Verein. seit 4.0 Entwickler ist alle drinking an Khalifa in der Mutterkonzerne am motivierte Dauerfeuer geplant. Wie Entgelte sie den keine Leistungen sie eingewanderte Das Rätsel der Kelten vom...»

«Gerechte Nachhaltige Entwicklung auf Grundlage des Capability-Ansatzes Fair sustainable development based on the capability approach UFZ Discussion Papers 6/2011 GeNECA 2 Ecosystem effects on well-being: more than just “benefits”? Looking at ecosystem services through the capability approach Yuliana Polishchuk, Felix Rauschmayer October 2011 Publisher: Helmholtz-Zentrum für Umweltforschung GmbH UFZ Permoserstr. 15 04318 Leipzig ISSN 1436-140X Gerechte Nachhaltige Entwicklung auf Grundlage...»

«BASEL II, SKAL II Installation and Operation Manual GB solid fuel heater BASEL II, SKAL II tested according to the standard EN 13240 1. Installation Instruction The heater has been designed to allow simple connection to an existing chimney by a single connecting piece. The connecting piece must be as short and straight as possible, in a horizontal position or slightly inclined. The piece must be tight. Be sure that all local regulations, including those concerning both national and European...»

«A Literature Review of Methods to Detect Fabricated Survey Data Sebastian Bredl, Nina Storfinger, Natalja Menold Abstract This paper reviews literature dealing with the issue of detecting interviewers who falsify survey data. The most reliable method of detecting falsifiers is through faceto-face reinterviewing of survey participants. However, especially in large scale surveys only a limited number of participants can usually be reinterviewed. A review of the present literature clearly...»

<<  HOME   |    CONTACTS
2016 www.book.dislib.info - Free e-library - Books, dissertations, abstract

Materials of this site are available for review, all rights belong to their respective owners.
If you do not agree with the fact that your material is placed on this site, please, email us, we will within 1-2 business days delete him.