The purpose of this study was to develop a computer-based second opinion diagnostic tool that could read microscope images of lung tissue from resection and lung cells from needle biopsies, and then classify these tissue samples as normal or cancerous. This problem can be partitioned into three areas: segmentation, feature extraction and measurement, and finally classification. One component of this research is to introduce the Mean Shift segmentation algorithm as a prior stage to a kernel-based extension of the Fuzzy C-Means clustering algorithm that provides a coarse initial segmentation. This process is followed by heuristic-based mechanisms to improve the accuracy...