Abstract
Screening plays an important role within the fight against cervical cancer. One of the most challenging parts in order to automate the screening process is the segmentation of nuclei in the cervical cell images, as the difficulty for performing this segmentation accurately varies widely within the nuclei. We present an algorithm to perform this task. After background determination in an overview image, and interactive identification of regions of interest (ROIs) at lower magnification levels, ROIs are extracted and processed at the full magnification level of 40x. Subsequent to initial background removal, the image regions are smoothed by mean-shift and median filtering. Then, segmentations are generated by an adaptive threshold. The connected components in the resulting segmentations are filtered with morphological operators by characteristics such as shape, size and roundness. The algorithm was tested on a set of 50 images and was found to outperform other methods.
| Original language | English |
|---|---|
| Title of host publication | Medical Imaging 2010: Image Processing |
| Volume | 7623 |
| Edition | PART 1 |
| DOIs | |
| Publication status | Published - 2010 |
| Externally published | Yes |
| Event | Medical Imaging 2010: Image Processing - San Diego, CA, United States of America Duration: 14 Feb 2010 → 16 Feb 2010 |
Conference
| Conference | Medical Imaging 2010: Image Processing |
|---|---|
| Country | United States of America |
| City | San Diego, CA |
| Period | 14/02/10 → 16/02/10 |
Keywords
- Cervical Cell Images
- Image Segmentation
- Mean-shift
Cite this
}
Segmentation of cervical cell images using mean-shift filtering and morphological operators. / Bergmeir, C.; García Silvente, Miguel; Esquivias López-Cuervo, J.; Benítez, J. M.
Medical Imaging 2010: Image Processing. Vol. 7623 PART 1. ed. 2010. 76234C.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Segmentation of cervical cell images using mean-shift filtering and morphological operators
AU - Bergmeir, C.
AU - García Silvente, Miguel
AU - Esquivias López-Cuervo, J.
AU - Benítez, J. M.
PY - 2010
Y1 - 2010
N2 - Screening plays an important role within the fight against cervical cancer. One of the most challenging parts in order to automate the screening process is the segmentation of nuclei in the cervical cell images, as the difficulty for performing this segmentation accurately varies widely within the nuclei. We present an algorithm to perform this task. After background determination in an overview image, and interactive identification of regions of interest (ROIs) at lower magnification levels, ROIs are extracted and processed at the full magnification level of 40x. Subsequent to initial background removal, the image regions are smoothed by mean-shift and median filtering. Then, segmentations are generated by an adaptive threshold. The connected components in the resulting segmentations are filtered with morphological operators by characteristics such as shape, size and roundness. The algorithm was tested on a set of 50 images and was found to outperform other methods.
AB - Screening plays an important role within the fight against cervical cancer. One of the most challenging parts in order to automate the screening process is the segmentation of nuclei in the cervical cell images, as the difficulty for performing this segmentation accurately varies widely within the nuclei. We present an algorithm to perform this task. After background determination in an overview image, and interactive identification of regions of interest (ROIs) at lower magnification levels, ROIs are extracted and processed at the full magnification level of 40x. Subsequent to initial background removal, the image regions are smoothed by mean-shift and median filtering. Then, segmentations are generated by an adaptive threshold. The connected components in the resulting segmentations are filtered with morphological operators by characteristics such as shape, size and roundness. The algorithm was tested on a set of 50 images and was found to outperform other methods.
KW - Cervical Cell Images
KW - Image Segmentation
KW - Mean-shift
UR - http://www.scopus.com/inward/record.url?scp=79751471325&partnerID=8YFLogxK
U2 - 10.1117/12.845587
DO - 10.1117/12.845587
M3 - Conference Paper
SN - 9780819480248
VL - 7623
BT - Medical Imaging 2010: Image Processing
ER -