Adaptive Fuzzy Segmentation of Tumors in Three-Dimensional Computed Tomography (CT) Image Data

The continuing advancement of computed tomography (CT) technology has improved the analysis and visualization of tumor data. As imaging technology continues to accommodate the need for high quality medical image data, this encourages the research for more efficient ways of extracting crucial information from these vast amounts of data. A new segmentation method using a fuzzy rule based system to segment tumors in a three-dimensional CT data has been developed. To initialize the segmentation process, the user selects the region of interest (ROI) within the tumor in the first image of the CT study set. Using the ROI’s spatial and intensity properties, fuzzy inputs are generated for use in the fuzzy inference system. From a set of predefined fuzzy rules, the system generates a defuzzified output for every pixel in terms of similarity to the object. Pixels with the highest similarity values are selected to be the tumor. This process is repeated for every subsequent slice in the CT set, and the segmented region from the previous slice is used as the ROI for the current slice. This creates a propagation of information from the previous slices, to be used to segment the current slice. The membership functions used during the fuzzification and defuzzification processes are adaptive to the changes in the size and pixel intensities of the current ROI. The proposed method is highly customizable to suit different needs of a user, requiring information from only a single two-dimensional image. Implementing the fuzzy segmentation on two distinct CT sets, the fuzzy segmentation algorithm was able to successfully extract the tumor from the CT image data. Based on the results statistics, the developed segmentation technique is approximately 96% accurate when compared to the results of manual segmentations performed.