Medical Image Segmentation Using K-Means Clustering and Improved Watershed Algorithm

TLDR

The conventional watershed algorithm is widely used in medical image analysis for its ability to produce complete segmentations, but it suffers from over‑segmentation and sensitivity to false edges. The study aims to improve medical image segmentation by first applying k‑means clustering to generate an initial partition and then refining it with an improved watershed algorithm. The method uses unsupervised k‑means clustering followed by an improved watershed algorithm that applies automated thresholding on the gradient magnitude map and post‑segmentation merging to reduce false edges and over‑segmentation. On 50 images, the proposed approach reduced the number of partitions by 92% compared to the conventional watershed algorithm.

Abstract

We propose a methodology that incorporates k-means and improved watershed segmentation algorithm for medical image segmentation. The use of the conventional watershed algorithm for medical image analysis is widespread because of its advantages, such as always being able to produce a complete division of the image. However, its drawbacks include over-segmentation and sensitivity to false edges. We address the drawbacks of the conventional watershed algorithm when it is applied to medical images by using k-means clustering to produce a primary segmentation of the image before we apply our improved watershed segmentation algorithm to it. The k-means clustering is an unsupervised learning algorithm, while the improved watershed segmentation algorithm makes use of automated thresholding on the gradient magnitude map and post-segmentation merging on the initial partitions to reduce the number of false edges and over-segmentation. By comparing the number of partitions in the segmentation maps of 50 images, we showed that our proposed methodology produced segmentation maps which have 92% fewer partitions than the segmentation maps produced by the conventional watershed algorithm