Unsupervised Segmentation of Overlapping Cervical Cell Cytoplasm
This work addresses a domain-specific challenge in medical imaging for cervical cancer screening, but it appears incremental as it builds on existing methods like Otsu and level sets.
The paper tackles the problem of overlapping cervical cells and poor contrast in cytoplasm for accurate segmentation, proposing an unsupervised approach that uses extended depth of field images and a modified Otsu method for nuclei segmentation, followed by level set models for cytoplasm segmentation.
Overlapping of cervical cells and poor contrast of cell cytoplasm are the major issues in accurate detection and segmentation of cervical cells. An unsupervised cell segmentation approach is presented here. Cell clump segmentation was carried out using the extended depth of field (EDF) image created from the images of different focal planes. A modified Otsu method with prior class weights is proposed for accurate segmentation of nuclei from the cell clumps. The cell cytoplasm was further segmented from cell clump depending upon the number of nucleus detected in that cell clump. Level set model was used for cytoplasm segmentation.