Universität Kaiserslautern

Home

Fachbereich Elektrotechnik und Informationstechnik



Development of a system for the analysis and classification of blood and bone marrow cell images to support morphological diagnosis of leukemia

Dieselbe Seite in deutsch

Abstract

For the diagnosis of leukemia, the microscopic investigation of the blood and bone marrow cells is an essential tool. Thereby, the multitude and variety of the cells which can occur demand a high expertise on the part of the analyst. The analysis yields results which the pathologist describes verbally. The reproduibility of the results is sometimes lacking. For improving the reliability of analysis and diagnosis computer based digital image processing offers a useful tool. 
The University of Kaiserslautern and the Westpfalz-Klinikum have undertaken an interdisciplinary project for the microscopic analysis of blood and bone marrow cells using digital image processing for the early diangosis of leukemia. 

Description of Project

The aim of the presented project is to build up an automatic classification system for panoptically (May/Grünwald/Giemsa) -stained blood and bone marrow slides. The analysis of blood slides including counting the cells of different lineage and maturity level is a powerful diagnostic means for the detection of leukemia. Generally speaking, leukemic patients have immature white blood cells in their peripheral blood which are practically functionless. Depending on the type of leukemia one observes different types and maturity levels of immature cells. However, there are marginal cases in which only very few cells of a certain type can be found. Non automated processing of of such cases is a strenuous task as every cell has to be classified properly. Next to the leukemic deseases where the white blood cells are immature, there are also cases (e.g. hairy cell leukemia) where one can directly make out typical deformations of the cells. An automated system can produce a relief for the person analysing the cells.

After the microscopic blood and bone marrow images are acquired, the cells have to be segmented, that is seperated from the background. They also have to be divided into cytoplasm and nucleus. If some cells are clustered together, they have to be seperated using a suitable algorithm since an automatic analysis of the cells is not possible otherwise. Cellclusters are usually found in bone marrow smears. In blood smears the cells are usually already seperate or appear in loose groups of only a few cells. The image on the left side shows a typical blood smear, the image on the right a typical bone marrow smear. 
 
 

Blutausstrich

Blood Smear

Knochenmarkausstrich

Bone Marrow Smear

Once the cells are seperate, feature extraction can be taken up. The features are algorithmic realisations of verbal descriptions by physicians - for example the verbal description "finely woven" can be quantified via texture analysis. These quantified features are part of a feature vector which can then be used as a basis for classification. Among others, features from the following feature-spaces have been examined: geometric features, form oriented features, texture features, color features and combined features.

The essential steps of the overall project are:

Future Work and Work in Progress

Areas in which work still needs to be done (interested party's please write to Heiko.Hengen@eit.uni-kl.de or Susanne.Spoor@eit.uni-kl.de):

Cooperations

Prof. Dr. Link and Dr. Hagmann of the Westpfalzklinikum are supporting the project concerning medical issues. A cooperation with Zeiss is presently being worked out. Part of  the work is being conducted under the auspices of an exchange program with the Indian Institute of Science funded by the DLR.

Publications

H. Hengen, M. Pandit, Declustering Algorithms for the Analysis of Blood and Bone Marrow Smears, IEEE SPCOM, Bangalore, 2001
M. Pandit, H. Hengen, Image Analysis of Blood and Bone Marrow Smears, IEEE/BMESI, BIOVISION, Bangalore, 2001
M. Pandit, H. Hengen, H. Link, F.-G. Hagmann, Computergestützte Diagnose von Leukämien unter Anwendung von Verfahren der digitalen Bildverarbeitung, DGHO Mannheim, 2001
T. Heger, H. Hengen, M. Pandit, Bildverarbeitung für Klassifikationsaufgaben in der Medizin und Qualitätssicherung, Automatisierungstechnik (at), Oldenbourg Verlag, 2002
H. Hengen, S. Spoor, M. Pandit, Analysis of Blood and Bone Marrow Smears using Digital Image Processing Techniques, SPIE Medical Imaging, San Diego, Feb. 2002

Finished Studienarbeiten, Diplomarbeiten, Project-Thesis, Master-Thesis

H. Hengen:
Objektorientierte Systemanalyse und -synthese in der digitalen Bildverarbeitung
(Object oriented systemanalysis and -synthesis for digital image processing)
Studienarbeit, Universität Kaiserslautern, 1997

O. Gabel:
Segmentation of Blood Cells
Projektarbeit, Indian Institute of Science, Bangalore, 1999

A. Hajra:
Segmentation and Feature Analysis of Blood Cells
Master Thesis, Universität Kaiserslautern, 2000

T. Paulus:
Entwurf und Realisierung einer Plattform zur Akquisition, Analyse und Segmentierung von mikroskopischen Aufnahmen für die midizinische Bildverarbeitung
(Design and implementation of a platform for acquisition, analysis and segmentation of microscopic images)
Diplomarbeit, Universität Kaiserslautern, 2000

M. Ross:
Methoden der digitalen Bildverarbeitung für die Leukämiediagnostik
(Methods of digital image processing for Leukemia diagnosis)
Diplomarbeit, Universität Kaiserslautern, 2001

S. Spoor:
Normalisierung, Declustering und Merkmalsextraktion in der medizinischen Bildverarbeitung
(Implementation of Image Standardisation and Advanced Segmentation and Feature Extraction Procedures)
Diplomarbeit, Universität Kaiserslautern, 2002
 

Download

The publication "Analysis of Blood and Bone Marrow Smears using Digital Image Processing Techniques" contains a more detailed description of the poject as well as paragraphs on procedures (normalisation, declustering,...). It can be downloaded right here

 

Contact: Susanne L. Siegrist
Room: 12/324
Phone: 0631 / 205-2820
e-mail:
or: Heiko Hengen
Room: 12/347
Phone: 0631 / 205-2091
e-mail: