Cluster Detection and Field-of-View Quality Rating - Applied to Automated Pap-smear Analysis

Marine Astruc, Patrik Malm, Rajesh Kumar, Ewert Bengtsson

2013

Abstract

Automated cervical cancer screening systems require high resolution analysis of a large number of epithelial cells, involving complex algorithms, mainly analysing the shape and texture of cell nuclei. This can be a very time consuming process. An initial selection of relevant fields-of-view in low resolution images could limit the number of fields to be further analysed at a high resolution. In particular, the detection of cell clusters is of interest for nuclei segmentation improvement, and for diagnostic purpose, malignant and endometrial cells being more prone to stick together in clusters than other cells. In this paper, we propose methods aiming at evaluating the quality of fields-of-view in bright-field microscope images of cervical cells. The approach consists of the construction of neighbourhood graphs using the nuclei as the set of vertices. Transformations are then applied to such graphs in order to highlight the main structures in the image. The methods result in the delineation of regions with varying cell density and the identification of cell clusters. Clustering methods are evaluated using a dataset of manually delineated clusters and compared to a related work.

References

  1. Chandran, S. P., Byju, N. B., Deepak, R. U., Kumar, R. R., Sudhamony, S., Malm, P., and Bengtsson, E. (2012). Cluster detection in cytology images using the cellgraph method. In IT in Medicine and Education (ITME), 2012 International Symposium on.
  2. Elsheikh, T. M., Austin, R. M., Chhieng, D. F., Miller, F. S., Moriarty, A. T., and Renshaw, A. A. (2012). American society of cytopathology workload recommendations for automated pap test screening: Developed by the productivity and quality assurance in the era of automated screening task force. Diagnostic Cytopathology, 1:1.
  3. Grohs, H. and Husain, O., editors (1994). Automated Cervical Cancer Screening. IGAKU-SHOIN Medical Publishers, Inc.
  4. Heijmans H., V. L. (1992). Mathematical Morphology in Image Processing. CRC Press; First Edition edition, New York.
  5. Moshavegh, R., Ehteshami, B., Mehnert, A., Sujathan, K., Malm, P., and Bengtsson, E. (2012). Automated segmentation of free-lying cell nuclei in pap smears for malignancy-associated change analysis. In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE.
  6. Nordin, B. (1989). The development of an automatic prescreener for the early detection of cervical cancer: Algorithms and implementation. PhD thesis, Uppsala University.
  7. Papanicolaou, G. N., Traut, H. F., and Stanton A. Friedberg, M. (1943). Diagnosis of uterine cancer by the vaginal smear. Oxford University Press, New York.
  8. Poulsen, R. S. (1973). Automated prescreening of cervical cytology specimens. PhD thesis, Department of Electrical Engineering, McGill University.
  9. Raymond, E., Raphael, M., Grimaud, M., Vincent, L., Binet, J. L., and Meyer, F. (1993). Germinal center analysis with the tools of mathematical morphology on graphs. Cytometry, 14(8):848-61.
  10. Vincent, L. (1989). Graphs and mathematical morphology. Signal Processing, 16(4):365 - 388. ¡ce:title¿Special Issue on Advances in Mathematical Morphology¡/ce:title¿.
  11. Waxman, B. (1988). Routing of multipoint connections. Selected Areas in Communications, IEEE Journal on, 6(9):1617 -1622.
  12. WHO/ICO Information Centre on HPV and Cervical Cancer (HPV Information Centre) (2012). Human papillomavirus and related cancers in world. summary report 2010.
  13. Zuiderveld, K. (1994). Graphics gems iv. chapter Contrast limited adaptive histogram equalization, pages 474- 485. Academic Press Professional, Inc., San Diego, CA, USA.
Download


Paper Citation


in Harvard Style

Astruc M., Malm P., Kumar R. and Bengtsson E. (2013). Cluster Detection and Field-of-View Quality Rating - Applied to Automated Pap-smear Analysis . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 355-364. DOI: 10.5220/0004254803550364


in Bibtex Style

@conference{icpram13,
author={Marine Astruc and Patrik Malm and Rajesh Kumar and Ewert Bengtsson},
title={Cluster Detection and Field-of-View Quality Rating - Applied to Automated Pap-smear Analysis},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={355-364},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004254803550364},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Cluster Detection and Field-of-View Quality Rating - Applied to Automated Pap-smear Analysis
SN - 978-989-8565-41-9
AU - Astruc M.
AU - Malm P.
AU - Kumar R.
AU - Bengtsson E.
PY - 2013
SP - 355
EP - 364
DO - 10.5220/0004254803550364