Joint volumetric extraction and enhancement of vasculature from low-SNR 3-D fluorescence microscopy images

PATTERN RECOGNITION

卷:63

Article

Almasi, Sepideh¹  Ben-Zvi, Ayal^2,3  Lacoste, Baptiste⁴  Gu, Chenghua²  Miller, Eric L.¹  Xu, Xiaoyin⁵ 

[1] Tufts Univ, Dept Elect & Comp Engn, Medford, MA 02155 USA

[2] Harvard Med Sch, Dept Neurobiol, Boston, MA USA

[3] Hebrew Univ Jerusalem, Inst Med Res IMRIC, Dept Dev Biol & Canc Res, Jerusalem, Israel

[4] Univ Ottawa, Brain & Mind Res Inst, Ottawa Hosp Res Inst, Dept Cellular & Mol Med,Neurosci Program, Ottawa, ON, Canada

[5] Brigham & Womens Hosp, Dept Radiol, Boston, MA USA

关键词: Image segmentation;    Non-uniform illumination;    Tubular structures;   

DOI  :  10.1016/j.patcog.2016.09.031

来源: Elsevier

【 摘 要 】

To simultaneously overcome the challenges imposed by the nature of optical imaging characterized by a range of artifacts including space-varying signal to noise ratio (SNR), scattered light, and non-uniform illumination, we developed a novel method that segments the 3-D vasculature directly from original fluorescence microscopy images eliminating the need for employing pre- and post-processing steps such as noise removal and segmentation refinement as used with the majority of segmentation techniques. Our method comprises two initialization and constrained recovery and enhancement stages. The initialization approach is fully automated using features derived from bi-scale statistical measures and produces seed points robust to non-uniform illumination, low SNR, and local structural variations. This algorithm achieves the goal of segmentation via design of an iterative approach that extracts the structure through voting of feature vectors formed by distance, local intensity gradient, and median measures. Qualitative and quantitative analysis of the experimental results obtained from synthetic and real data prove the efficacy of this method in comparison to the state-of-the-art enhancing-segmenting methods. The algorithmic simplicity, freedom from having a priori probabilistic information about the noise, and structural definition gives this algorithm a wide potential range of applications where i.e. structural complexity significantly complicates the segmentation problem.

【 授权许可】

Free