Third International conference on advances in communication, network and computing

Research Article

Patch-Based Categorization and Retrieval of Medical Images

Download
190 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-35615-5_54,
        author={Zarina Sulthana and Supreethi K.P.},
        title={Patch-Based Categorization and Retrieval of Medical Images},
        proceedings={Third International conference on advances in communication, network and computing},
        proceedings_a={CNC},
        year={2012},
        month={12},
        keywords={Mining Medical Images Categorization Patch-based visual words K-means clustering Image Retrieval Region-of-Interest},
        doi={10.1007/978-3-642-35615-5_54}
    }
    
  • Zarina Sulthana
    Supreethi K.P.
    Year: 2012
    Patch-Based Categorization and Retrieval of Medical Images
    CNC
    Springer
    DOI: 10.1007/978-3-642-35615-5_54
Zarina Sulthana1,*, Supreethi K.P.1,*
  • 1: Jawaharlal Nehru Technological University
*Contact email: zarina.sulthana@gmail.com, supreethi.pujari@gmail.com

Abstract

Utilization of the mining techniques in aiding the medical diagnosis by processing the medical images, Chest X-Rays in particular. The process involves - categorization of the images using patch-based visual words, collection into clusters using K-means clustering, and Image retrieval, involving comparison of the input image with the images in the dataset and retrieving the matched images along with the appropriate diagnosis associated with that particular medical case. If there is no data matching then this would be added to the existing database thus aiding the diagnosis of other such cases that might come up in the future. The retrieval may also be done based on Region-of-Interest (ROI).