An Interactive Medical Image Segmentation Framework Using Iterative Refinement

TL;DR

This paper introduces an interactive two-stage medical image segmentation framework combining morphological marker generation and GrabCut, refined through user interaction, achieving accurate results with minimal effort.

Contribution

It presents a novel two-stage segmentation algorithm that integrates morphological marker creation with GrabCut and user refinement for improved medical image segmentation.

Findings

Accurate segmentation with minimal user interaction

Effective on both medical and natural images

Outperforms some existing methods in accuracy

Abstract

Image segmentation is often performed on medical images for identifying diseases in clinical evaluation. Hence it has become one of the major research areas. Conventional image segmentation techniques are unable to provide satisfactory segmentation results for medical images as they contain irregularities. They need to be pre-processed before segmentation. In order to obtain the most suitable method for medical image segmentation, we propose a two stage algorithm. The first stage automatically generates a binary marker image of the region of interest using mathematical morphology. This marker serves as the mask image for the second stage which uses GrabCut on the input image thus resulting in an efficient segmented result. The obtained result can be further refined by user interaction which can be done using the Graphical User Interface (GUI). Experimental results show that the proposed method is accurate and provides satisfactory segmentation results with minimum user interaction on medical as well as natural images.