Automatic identification of overlapping/touching chromosomes in microscopic images using morphological operators

Jahani, S ; Sharif University of Technology | 2011

377 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianMVIP.2011.6121574
  3. Publisher: 2011
  4. Abstract:
  5. Karyotyping, is the process of classification of human chromosomes within the microscopic images. This is a common task for diagnosing many genetic disorders and abnormalities. Automatic Karyotyping algorithms usually suffer the poor quality of the images due to the non rigid nature of the chromosomes which makes them to have unpredictable shapes and sizes in various images. One of the main problems that usually need operator's interaction is the identification and separation of the overlapping/touching chromosomes. This paper presents an effective algorithm for identification of any cluster of the overlapping/touching chromosomes together with the number of chromosomes in the cluster, which is a very first step towards the development of a fully automatic Karyotyping system. The proposed algorithm which is based on the extraction of the number of endpoints within the skeleton of the image objects uses morphological operators. Two independent datasets obtained from the Tesi-Imaging srl in Milan, Italy and the Imam Hospital in Tehran, Iran was used to evaluate the performance of the algorithm. An accuracy of %96 and %99 were obtained on identification of the clusters of overlapping/touching chromosomes and single chromosomes respectively by the proposed algorithm
  6. Keywords:
  7. Automatic identification ; Data sets ; Effective algorithms ; Genetic disorders ; Human chromosomes ; Image objects ; Karyotyping ; Microscopic image ; Milan , Italy ; Morphological operator ; Non-rigid ; Overlapping ; Tehran , Iran ; Touching ; Automation ; Chromosomes ; Computer vision ; Data processing ; Clustering algorithms
  8. Source: 2011 7th Iranian Conference on Machine Vision and Image Processing, MVIP 2011 - Proceedings, 16 November 2011 through 17 November 2011 ; November , 2011 , Page(s): 1 - 4 ; 9781457715358 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6121574