Topic 1: Robust Clustering Analysis in Biomedical Data

Speaker: Rashid Mehmood
  Abstract: Clustering plays an important role in the fields of knowledge discovery and data mining. Clustering algorithms attempt to organize data into different disjoint categories, with more similar data points organized into the same cluster, while dissimilar data points are grouped into different clusters. Clustering has been successfully applied in different fields such as bioinformatics, cyber security, image processing, astronomy, social networks. Additionally, clustering has become the primary procedure in biomedical to organize the gene expression microarray into subclasses, for the purpose of diagnostic and prognosis. Here we focus on developing new robust clustering algorithms and data analysis methods, in order to effectively analyze biologically disorder in human organs.

Topic 2: LMS Based Adaptive Algorithm for Breast Cancer Tumor Detection in Mammograms

Speaker: Hafeez Ahmed
  Abstract: In this paper, we have evaluated the performance of state of the art adaptive algorithm i.e. LSM combined with segmentation by using connected components technique for the enhancement of mammogram and detection of masses or lesions respectively. Additionally, we considered feature vector with three features i.e. gray value, window mean and standard deviation, which improves the detection process. Results are evaluated in terms of sensitivity, specificity and accuracy. For the detection of clustered masses, our results are very encouraging with 80% accuracy of proposed system. The mammogram images used in our research are taken from Digital Database for Screening Mammograms (DDSM).