A Study on MRI Liver Image Segmentation using Fuzzy Connected and Watershed Techniques

Abstract

- A comparison study between automatic and interactive methods for liver segmentation from contrast-enhanced MRI images is ocean. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to refer five error measures that highlight different aspects of segmentation accuracy. The measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods like Fuzzy Connected and Watershed Methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques. In this paper only Fuzzy Connected and Watershed Methods are discussed.