Vessel Segmentation for Noisy CT Data with Quality Measure Based on Single-Point Contrast-to-Noise Ratio

Abstract

Abstract. This paper describes a comprehensive multi-step algorithm for vascular structure segmentation in CT scan data, from raw slice images to a 3D object, with an emphasis on improving segmentation quality and assessing computational complexity. To estimate initial image quality and to evaluate denoising in the absence of the noise-free image, we propose a semi-global contrast-to-noise quality metric. We show that total variation-based filtering in the metric results in the best denoising when compared to widely used nonlocal means or anisotropic diffusion denoising. To address higher computational complexity of our denoising algorithm, we created two high performance implementations, using Intel MIC and NVIDIA CUDA and compared results. In combination with proposed nearly real-time incremental segmentation technique, it provides fast and framework with controlled quality.

Accuracy of bone segmentation and surface generation strategies analyzed by using synthetic CT volumes

“…Potential positive or negative effects of image denoising on the segmentation quality have rarely been assessed; positive effects have been reported for certain combinations of noise reduction methods and segmentation approaches (e.g. Firouzian et al, 2011; Nikonorov et al, 2016). Additionally, smoothing the segmentation label has been shown to increase the surface quality (DeVries et al, 2008).…”