Automated Diagnosis of Oral Cancer Using Higher Order Spectra Features and Local Binary Pattern: A Comparative Study
Open Access
- 1 October 2011
- journal article
- research article
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 10 (5) , 443-455
Abstract
In the field of quantitative microscopy, textural information plays a significant role very often in tissue characterization and diagnosis, in addition to morphology and intensity. The objective of this work is to improve the classification accuracy based on textural features for the development of a computer assisted screening of oral sub-mucous fibrosis (OSF). In fact, the approach introduced is used to grade the histopathological tissue sections into normal, OSF without dysplasia (OSFWD) and OSF with dysplasia (OSFD), which would help the oral onco-pathologists to screen the subjects rapidly. The main objective of this work is to evaluate the use of Higher Order Spectra (HOS) features and Local Binary Pattern (LBP) features extracted from the epithelial layer in classifying normal, OSFWD and OSFD. For this purpose, we extracted twenty three HOS features and nine LBP features and fed them to a Support Vector Machine (SVM) for automated diagnosis. One hundred and fifty eight images (90 normal, 42 OSFWD and 26 OSFD images) were used for analysis. LBP features provide a good sensitivity of 82.85% and specificity of 87.84%, and the HOS features provide higher values of sensitivity (94.07%) and specificity (93.33%) using SVM classifier. The proposed system, can be used as an adjunct tool by the onco-pathologists to cross-check their diagnosis.Keywords
This publication has 42 references indexed in Scilit:
- Structural markers for normal oral mucosa and oral sub-mucous fibrosisMicron, 2010
- Texture measures combination for improved meningioma classification of histopathological imagesPattern Recognition, 2010
- Computerized microscopic image analysis of follicular lymphoma2008
- Pathologist Interobserver Variability of Histologic Features in Childhood Brain Tumors: Results from the CCG-945 StudyPediatric and Developmental Pathology, 2008
- A method for linking computed image features to histological semantics in neuropathologyJournal of Biomedical Informatics, 2007
- Interobserver agreement of scoring of histopathological characteristics and classification of lupus nephritisNephrology Dialysis Transplantation, 2007
- Oral submucous fibrosis: Review on aetiology and pathogenesisOral Oncology, 2006
- A novel wavelet neural network based pathological stage detection technique for an oral precancerous conditionJournal of Clinical Pathology, 2005
- Medical image analysis: progress over two decades and the challenges aheadIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Advanced methods in the evaluation of premalignant lesions and carcinomas of the oral mucosaJournal of Oral Pathology & Medicine, 1985