This workshop is partially supported
by Australian Research Council,
discovery project DP140102794 &
ARC Future Fellowship (FT110100623).
ARC Logo 

General Description of the Problem

The automated detection and segmentation of overlapping cells using microscopic images obtained from Pap smear [1] can be considered to be one of the major hurdles for a robust automatic analysis of cervical cells. The Pap smear is a screening test used to detect pre-cancerous and cancerous processes, which consists of a sample of cells collected from the cervix that are smeared onto a glass slide and further examined under a microscope. The main factors affecting the sensitivity of the Pap smear test are the number of cells sampled, the overlap among these cells, the poor contrast of the cell cytoplasm, and the presence of mucus, blood and inflammatory cells [2]. These factors all exacerbate intra- and inter-observer variability and lead to a large variation in false negative results [3]. These issues have motivated the development of automated cell deposition and automated slide analysis techniques. Automated cell deposition techniques, such as mono-layer preparations, remove a large portion of blood, mucus and other debris, reduce cell overlap and produce cells that are more likely to occur in a single focal plane. This makes both manual and automated slide analysis faster and easier [4]. Automated slide analysis techniques attempt to improve both sensitivity and specificity by automatically detecting, segmenting and classifying the cells present on a slide [5, 6, 7, 8, 9].

The main focus of this challenge is on cell detection and cell segmentation for the automated analysis of cervical cytology specimens. Current systems can segment the nucleus and cytoplasm of cervical cells in isolation [7] (i.e., cells without any overlap with other cells), segment overlapping nuclei [10,11,12] and segment overlapping nuclei plus the whole region representing the cellular clumps [6,2]. Only recently has the complete segmentation of overlapping cells been addressed [13,14], but these methods show results that are still not robust enough for clinical practice. Indeed, the effectiveness of these methods is severely complicated by the fact that several layers of cervical cells are present in a glass slide (see Fig.1), which means that cells in an upper layer can partially occlude cells lying underneath [12]. In the challenge “Segmentation of Overlapping Cervical Cells from Extended Depth of Field Cytology Image” presented in ISBI’14, we proposed the use of an extended depth of field (EDF) cytology image that puts all cells in focus in a single image [15]. The main difference of the challenge proposed for ISBI 2015 is that the input data will consist of a multi-layer cytology volume [16], which means that the input data is now a volume consisting of a set of multi-focal images acquired from the same specimen. This richer input dataset is potentially more informative for the tasks of detecting and segmenting cervical cells, and as a result can allow for more precise cervical cell cytoplasm and nucleus detection and segmentation.

References
  1. Papanicolaou, G. A new procedure for staining vaginal smears. Science, Vol. 95, no. 2469 (1942) 438-439.

  2. Gençtav, A., Aksoy, S., Önde, S. Unsupervised segmentation and classification of cervical cell images. Pattern Recognition, Vol. 45 (2012) 4151-4168.

  3. Noorani, H. Assessment of techniques for cervical cancer screening. CCOHTA 1997: 2E, Canadian Coordinating Office for Health Technology Assessment. (1997).

  4. Grohs, H., et al. Standardization of specimen preparation through mono/thin-layer technology. in H. K. Grohs and O. A. N. Husain, eds, Automated Cervical Cancer Screening. IGAKU-SHOIN Medical Publishers, New York (1994).

  5. Jung, C., Kim, C., Chae, S., Oh, S. Unsupervised segmentation of overlapped nuclei using bayesian classification. IEEE TBE, 57(12), (2010) 2825-2832.

  6. Kale, A., Aksoy, S. Segmentation of cervical cell images. ICPR, Istanbul, Turkey. (2010) 2399-2402.

  7. Li, K., Lu, Z., Liu, W., Yin, J. Cytoplasm and nucleus segmentation in cervical smear images using Radiating GVF Snake. Pattern Recognition, Vol. 45 (2012) 1255-1264.

  8. Plissiti, M., Nikou, C., Charchanti, A. Automated detection of cell nuclei in pap smear images using morphological reconstruction and clustering. IEEE Transactions on Information Technology in Biomedicine, Vol. 15, (2011) 233-241.

  9. Yang-Mao, S.-F., Chan, Y.-K., Chu, Y.-P. Edge enhancement nucleus and cytoplast contour detector of cervical smear images. IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 38 (2008) 353-366.

  10. Jung, C. and Kim, C. Segmenting clustered nuclei using H-minima transform-based marker extraction and contour parameterization. IEEE TBE, 57(10), (2010) 2600-2604.

  11. Jung, C., Kim, C., Chae, S., Oh, S. Unsupervised segmentation of overlapped nuclei using bayesian classification. IEEE TBE, 57(12), (2010) 2825-2832.

  12. Plissiti, M., Nikou, C. Overlapping cell nuclei segmentation using a spatially adaptive active physical model. IEEE TIP. 21(11) (2012) 4568-4580.

  13. Beliz-Osorio, N., Crespo, J., Garcia-Rojo, M., Munoz, A., Azpiazu, J. Cytology imaging segmentation using the locally constrained watershed transform. Mathematical Morphology and Its Applications to Image and Signal Processing, (2011) 429-438.

  14. Lu, Z., Carneiro, G., Bradley, A. Automated nucleus and cytoplasm segmentation of overlapping cervical cells. MICCAI (2013).

  15. Bradley, A., Bamford, P. A one-pass extended depth of field algorithm based on the over-complete discrete wavelet transform. Image and Vision Computing 'New Zealand (IVCNZ), (2004) 279-284

  16. Schechner, Y., Kiryati, N., Basri, R. Separation of transparent layers using focus. IJCV. 39(1), Kluwer Academic Publishers (2000) 25-39.