Pre-Processing Method for Extraction of Pectoral Muscle and Removal of Artefacts in Mammogram
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 3
Abstract
Abstract: Mammography is an effective imaging modality used by radiologists for detection of breast cancer and effective suppression of pectoral muscle as well as removal of noise in form of artefacts aids accurate detection. In existing methods, either over-segmentation or under-segmentation, have been reported resulting in less accurate results. In this work, an algorithm was developed that effectively removed artefacts and pectoral muscle from mammograms, it uses a region description method, which uses splitting and merging technique to extract pectoral muscle and remove unwanted noise from the original mammograms. Digital mammograms from MIAS database were used to test the algorithm. The algorithm achieved 92.24% good results,4.04% acceptable results,3.10% unaccepted results, and 0.62% of the mammograms were discarded. Experimental results obtained indicate that the breast regions extracted accurately.
Authors and Affiliations
Ojo J. A. , , Adepoju T. M. , Omdiora E. O. , Olabiyisi O. S. and Bello O. T
Keywords
Related Articles
- EP ID EP116091
- DOI 10.9790/0661-16350609
- Views 109
- Downloads 0
Privacy-Preserving Public Auditing For Secure Cloud Storage
Abstract: By using Cloud storage, users can access applications, services, software whenever they requires over the internet. Users can put their data remotely to cloud storage and get benefit of on-demand services...
Nearest Adjacent Node Discovery Scheme for Routing Protocol in Wireless Sensor Network
The broad significance of Wireless Sensor Networks is in most emergency and disaster rescue domain. The routing process is the main challenges in the wireless sensor network due to lack of physical links.  ...
I-ViDE: An Improved Vision-Based Approach for Deep Web Data Extraction
Abstract: Deep Web contents are accessed by queries submitted to Web databases and the returned data records are enwrapped in dynamically generated Web pages (they will be called deep Web pages in this paper). Extr...
A Novel Approach for Semi Supervised Document Clustering with Constraint Score based Feature Supervision
Abstract: Text document clustering provides an effective technique to manage a huge amount of retrieval outcome by grouping documents in a small number of meaningful classes. In unsupervised clustering method the unlabel...
Chip Implementation of Text Encryption and Decryption Algorithms
Abstract: Cryptography is the science of using mathematics to encrypt and decrypt data. It enables to store sensitive information or transmit it across insecure networks so that it cannot be read by anyone except t...