Review on the Methods of Automatic Liver Segmentation from Abdominal Images

Abstract

Automatic liver segmentation from abdominal images\ris challenging on the aspects of segmentation accuracy, automation and\rrobustness. There exist many methods of liver segmentation and ways of categorisingthem. In\rthis paper, we present a new way of summarizing the latest achievements in\rautomatic liver segmentation. We categorise a segmentation method according to the\rimage feature it works on, therefore better summarising the performance of each\rcategory and leading to finding an optimal solution for a particular\rsegmentation task. All the\rmethods of liver segmentation are categorized into three main classes including\rgray level based method, structure based method and texture based method. In\reach class, the latest advance is reviewed with summary comments on the\radvantages and drawbacks of each discussed approach. Performance comparisons\ramong the classes are given along with the remarks on the problems existed and\rpossible solutions. In conclusion, we point out that liver segmentation is\rstill an open issue and the tendency is that multiple methods will be employed\rtogether to achieve better segmentation performance.