Adaptive Local Window for Level Set Segmentation of CT and MRI Liver Lesions

TL;DR

This paper introduces an adaptive local window technique for level set segmentation that dynamically adjusts to object features, improving accuracy in liver lesion imaging across CT and MRI modalities.

Contribution

The proposed method adaptively estimates local windows for each contour point, enhancing segmentation accuracy over traditional fixed-size window approaches.

Findings

Outperforms global and fixed-size local window methods in accuracy.

Significantly improves segmentation of complex, low contrast, and noisy lesions.

Achieves a 0.25 increase in Dice coefficient for challenging lesions.

Abstract

We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those images were obtained by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compare our method to a global level set segmentation and to local framework that uses predefined fixed-size square windows. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25+- 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p < 0.001).