Multiscale Segmentation via Bregman Distances and Nonlinear Spectral Analysis

TL;DR

This paper introduces a novel multiscale segmentation method combining nonlinear variational models, Bregman distances, and spectral analysis, enabling efficient, adaptive, and parameter-free segmentation of biomedical images across various scales.

Contribution

It generalizes a total variation-based segmentation model using Bregman distances and spectral decomposition, providing a new multiscale segmentation approach with adaptive regularization.

Findings

Demonstrated effectiveness on synthetic tests

Applied successfully to biomedical imaging for tumor cell classification

Achieved nearly parameter-free multiscale segmentation

Abstract

In biomedical imaging reliable segmentation of objects (e.g. from small cells up to large organs) is of fundamental importance for automated medical diagnosis. New approaches for multi-scale segmentation can considerably improve performance in case of natural variations in intensity, size and shape. This paper aims at segmenting objects of interest based on shape contours and automatically finding multiple objects with different scales. The overall strategy of this work is to combine nonlinear segmentation with scales spaces and spectral decompositions recently introduced in literature. For this we generalize a variational segmentation model based on total variation using Bregman distances to construct an inverse scale space. This offers the new model to be accomplished by a scale analysis approach based on a spectral decomposition of the total variation. As a result we obtain a very efficient, (nearly) parameter-free multiscale segmentation method that comes with an adaptive regularization parameter choice. The added benefit of our method is demonstrated by systematic synthetic tests and its usage in a new biomedical toolbox for identifying and classifying circulating tumor cells. Due to the nature of nonlinear diffusion underlying, the mathematical concepts in this work offer promising extensions to nonlocal classification problems.