Guided interactive image segmentation using machine learning and color based data set clustering
This incremental improvement addresses efficiency in image segmentation for biological and medical researchers, enabling larger-scale quantification.
The paper tackles the problem of color variability in biological and medical images, which degrades segmentation accuracy, by combining machine learning-based interactive segmentation with color clustering to enable guided classifier reuse, reducing training effort and facilitating high-throughput image analysis.
We present a novel approach that combines machine learning based interactive image segmentation using supervoxels with a clustering method for the automated identification of similarly colored images in large data sets which enables a guided reuse of classifiers. Our approach solves the problem of significant color variability prevalent and often unavoidable in biological and medical images which typically leads to deteriorated segmentation and quantification accuracy thereby greatly reducing the necessary training effort. This increase in efficiency facilitates the quantification of much larger numbers of images thereby enabling interactive image analysis for recent new technological advances in high-throughput imaging. The presented methods are applicable for almost any image type and represent a useful tool for image analysis tasks in general.