Loading...
Evaluation and Diagnosis of Intraosseos Lesions in Panoramic Radiographs
Abdi, Amir Hossein | 2013
304
Viewed
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 44837 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Kasaie, Shohre
- Abstract:
- Panoramic radiography is known to be one of the preliminary means in diagnoses of maxillofacial intraosseos lesions, which has a big role in increasing the prognosis of such patients. Considering the fact that nowadays most health-care centers are equipped with digital radiography systems, we can rely on image processing techniques to recognize such lesions automatically.In this study, we try to segment mandible (lower jaw) out of panoramic image by means of some innovative algorithms based on edge detection and edge following, and some atlas-based methods. Then by extracting some features such as intensity, homogeneity, local energy and local gradient and with the help of SVM classifier we intend to recognize pixels that are lesion candidates. Finally based on some level-set methods, the exact locations of lesions are extracted.Results show that segmentation of mandible with the proposed method has an accuracy of 85-90%, and recognizing the location of lesions has a performance of about 60%. But it needs to be stated that the number of test images in case of lesion localization is low and therefor the reliability of the method is not established.This study on panoramic imaging is the first of its kind in case of mandible segmentation and lesion detection. Although this is a pilot study, based on the results obtained, we can hope to automatize the process of lesion detection in panoramic imaging
- Keywords:
- Radiography ; Panoramic Images ; Intraosseous Lesions ; Mandible Segmentation
- محتواي کتاب
- view