Use this URL to cite or link to this record in EThOS:
Title: Computer assisted diagnesis of cervical intraepithelicel neoplasia (CIN) using histological virtual slides.
Author: Wang, Y.
ISNI:       0000 0001 3562 1550
Awarding Body: Queens University Belfast
Current Institution: Queen's University Belfast
Date of Award: 2008
Availability of Full Text:
Full text unavailable from EThOS.
Please contact the current institution’s library for further details.
This thesis proposes a prototype automated computer-assisted system for the diagnosis of CIN using ultra-large virtual slides (up to 120Kx80K pixels at a resolution of 0.25 !-un/pixel). The system is in two parts: the segmentation of squamous epithelium, and the subsequent diagnosis of CIN. For the segmentation of squamous epithelium, to save processing time, a multiresolution method is developed to segment ultra-large cervical virtual slides. The squamous epithelium layer is first segmented at a low resolution, and the boundaries are further fine tuned at a higher resolution. The block-based segmentation method uses robust texture features in ~ombination with a Support Vector Machine (SVM) to perform classification. Medical histology rules are finally applied to remove misclassifications. In tests using 31 virtual slides the segmentation achieves an average accuracy of more than 94.25%. For the diagnosis of CIN, so-called 'connecting lines', along the direction of possible progression of CIN in the epithelial layer, are firstly identified. Four connecting line features are developed based on morphological characteristics of nuclei. Using multicategory SVM, connecting lines are classified into Normal, CIN I, CIN II, and CIN III. The final diagnosis for a slide region is based on combining the classification of connecting lines in the region.. The robustness of the system in term of regional diagnosis is measured against slides manually classified by two pathologists. Interobserver variability is considered. Results indicate that the system offers a promising basis for a computer-assisted diagnostic tool. It main limitation is seen to be in the selection of more extensive and more varied training data.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available