Enhancement of Vascular Structures in3D and 2D Angiographic Images

Abstract

A number of imaging techniques are being used for diagnosis and treatment of vascular pathologies like stenoses, aneurysms, embolisms, malformations and remodelings, which may affect a wide range of anatomical sites. For computer-aided detection and highlighting of potential sites of pathology or to improve visualization and segmentation, angiographic images are often enhanced by Hessian based filters. These filters aim to indicate elongated and/or rounded structures by an enhancement function based on Hessian eigenvalues. However, established enhancement functions generally produce a response, which exhibits deficiencies such as poor and non-uniform response for vessels of different sizes and varying contrast, at bifurcations and aneurysms. This may compromise subsequent analysis of the enhanced images. This paper has three important contributions: i) reviews several established enhancement functions and elaborates their deficiencies, ii) proposes a novel enhancement function, which overcomes the deficiencies of the established functions, and iii) quantitatively evaluates and compares the novel and the established enhancement functions on clinical image datasets of the lung, cerebral and fundus vasculatures.

Generalized Convolutional Sparse Coding With Unknown Noise

“…From each image, 15,000 vessel pixels are sampled as positive, and 15,000 background pixels are sampled as negative. As further baselines, we compare with the provided second expert's manual segmentation (denoted "Expert") and the state-of-the-art handcrafted multi-scale Hessian filter (denoted "Hessian") 7 [46]. The experiment is repeated five times.…”

2D and 3D Vascular Structures Enhancement via Multiscale Fractional Anisotropy Tensor

“…Our proposed function M F AT λ,p can be also defined for 2D case. In such case, there are three eigenvalues λ 2 , λ ρ , and λ ν that are defined in Equation 8. The corresponding response R σ λ,p for 2D images as follows:…”

Curvilinear Structure Enhancement by Multiscale Top-Hat Tensor in 2D/3D Images

“…3) Volume Ratio-based Approach: Hessian-based approaches rely on the eigenvalues and this leads to several problems: (1) eigenvalues are non-uniform throughout an elongated or rounded structure that has uniform intensity; (2) eigenvalues vary with image intensity; and (3) enhancement is not uniform across scales. A recent volume ratio-based approach [8] aims to solve such problems by computing the ratio of Hessian eigenvalues to handle the low magnitudes of eigenvalues and uniform responses across different structures. This approach intends to intimate vascular elongated structures in 2D and 3D angiography images.…”

“…Although a visual inspection can provide some information regarding the effectiveness of the curvilinear structure enhancement approaches, a more rigorous form of quantitative validation is required. As in [8], we chose to use the Receiver Operating Characteristic (ROC) curve and the Area Under the Curve (AUC) metrics to compare the curvilinear structure enhancement approaches. We derive the ROC curve and then calculate the AUC value.…”