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 | Conference on Medical Imaging - Image Processing 2010 - San Diego, United States of America Duration: 14 Feb 2010 → 16 Feb 2010 https://spie.org/Publications/Proceedings/Volume/7623 (Proceedings) |
Conference
Conference | Conference on Medical Imaging - Image Processing 2010 |
---|---|
Country/Territory | United States of America |
City | San Diego |
Period | 14/02/10 → 16/02/10 |
Internet address |
|
Keywords
- Cervical Cell Images
- Image Segmentation
- Mean-shift