Pieces-of-parts for supervoxel segmentation with global context: Application to DCE-MRI tumour delineation

TL;DR

This paper introduces a novel framework combining perfusion-supervoxels and a pieces-of-parts graphical model to automate rectal tumour segmentation in DCE-MRI, achieving high accuracy and demonstrating potential for broader applications.

Contribution

The paper presents a new method integrating global anatomical constraints with supervoxel segmentation for improved DCE-MRI tumour delineation.

Findings

Achieved AUC of 0.97 for voxelwise tumour detection.

Correctly segmented 21 of 23 cases with median DSC of 0.63.

Demonstrated generalisability with DSC of 0.71 in additional study.

Abstract

Rectal tumour segmentation in dynamic contrast-enhanced MRI (DCE-MRI) is a challenging task, and an automated and consistent method would be highly desirable to improve the modelling and prediction of patient outcomes from tissue contrast enhancement characteristics - particularly in routine clinical practice. A framework is developed to automate DCE-MRI tumour segmentation, by introducing: perfusion-supervoxels to over-segment and classify DCE-MRI volumes using the dynamic contrast enhancement characteristics; and the pieces-of-parts graphical model, which adds global (anatomic) constraints that further refine the supervoxel components that comprise the tumour. The framework was evaluated on 23 DCE-MRI scans of patients with rectal adenocarcinomas, and achieved a voxelwise area-under the receiver operating characteristic curve (AUC) of 0.97 compared to expert delineations. Creating a binary tumour segmentation, 21 of the 23 cases were segmented correctly with a median Dice similarity coefficient (DSC) of 0.63, which is close to the inter-rater variability of this challenging task. A sec- ond study is also included to demonstrate the method's generalisability and achieved a DSC of 0.71. The framework achieves promising results for the underexplored area of rectal tumour segmentation in DCE-MRI, and the methods have potential to be applied to other DCE-MRI and supervoxel segmentation problems