Improved Watershed Transform for Medical Image Segmentation Using Prior Information

TLDR

The watershed transform is simple, intuitive, parallelizable, and produces complete image partitions, but in medical imaging it suffers from oversegmentation, noise sensitivity, and difficulty detecting thin or low‑signal structures. We propose an improved watershed transform that incorporates prior information into its computation. The method introduces prior knowledge via a pre‑computed probability map and integrates watershed with atlas registration using markers, and is applied to knee cartilage and gray matter/white matter segmentation in MR images. Numerical validation shows the algorithm’s effectiveness for medical image segmentation.

Abstract

The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However, when applied to medical image analysis, it has important drawbacks (oversegmentation, sensitivity to noise, poor detection of thin or low signal to noise ratio structures). We present an improvement to the watershed transform that enables the introduction of prior information in its calculation. We propose to introduce this information via the use of a previous probability calculation. Furthermore, we introduce a method to combine the watershed transform and atlas registration, through the use of markers. We have applied our new algorithm to two challenging applications: knee cartilage and gray matter/white matter segmentation in MR images. Numerical validation of the results is provided, demonstrating the strength of the algorithm for medical image segmentation.