Bone Segmentation in Contrast Enhanced Whole-Body Computed Tomography

TL;DR

This paper presents a novel U-net based method with specialized preprocessing for accurate bone segmentation in low-dose contrast-enhanced whole-body CT scans, achieving high Dice scores across multiple datasets.

Contribution

It introduces a new preprocessing approach and sigmoid threshold modification that improve bone segmentation accuracy in challenging contrast-enhanced CT images.

Findings

Achieved mean Dice coefficients of 0.979, 0.965, and 0.934 on different datasets.

Preprocessing techniques are crucial for differentiating bone from contrast dye.

High segmentation accuracy is possible with limited training data.

Abstract

Segmentation of bone regions allows for enhanced diagnostics, disease characterisation and treatment monitoring in CT imaging. In contrast enhanced whole-body scans accurate automatic segmentation is particularly difficult as low dose whole body protocols reduce image quality and make contrast enhanced regions more difficult to separate when relying on differences in pixel intensities. This paper outlines a U-net architecture with novel preprocessing techniques, based on the windowing of training data and the modification of sigmoid activation threshold selection to successfully segment bone-bone marrow regions from low dose contrast enhanced whole-body CT scans. The proposed method achieved mean Dice coefficients of 0.979, 0.965, and 0.934 on two internal datasets and one external test dataset respectively. We have demonstrated that appropriate preprocessing is important for differentiating between bone and contrast dye, and that excellent results can be achieved with limited data.