Insight into 3D micro-CT data: exploring segmentation algorithms through performance metrics

Abstract

Three-dimensional (3D) micro-tomography (µ-CT) has proven to be an important imaging modality in industry and scientific domains. Understanding the properties of material structure and behavior has produced many scientific advances. An important component of the 3D µ-CT pipeline is image partitioning (or image segmentation), a step that is used to separate various phases or components in an image. Image partitioning schemes require specific rules for different scientific fields, but a common strategy consists of devising metrics to quantify performance and accuracy. The present article proposes a set of protocols to systematically analyze and compare the results of unsupervised classification methods used for segmentation of synchrotron-based data. The proposed dataflow for Materials Segmentation and Metrics (MSM) provides 3D micro-tomography image segmentation algorithms, such as statistical region merging (SRM), k-means algorithm and parallel Markov random field (PMRF), while offering different metrics to evaluate segmentation quality, confidence and conformity with standards. Both experimental and synthetic data are assessed, illustrating quantitative results through the MSM dashboard, which can return sample information such as media porosity and permeability. The main contributions of this work are: (i) to deliver tools to improve material design and quality control; (ii) to provide datasets for benchmarking and reproducibility; (iii) to yield good practices in the absence of standards or ground-truth for ceramic composite analysis.

Maximal clique enumeration with data-parallel primitives

“…Our motivator to pursue this work was an image processing problem that required maximal cliques and also aimed to support multiple architectures. In fact, very recent algorithms for the analysis of experimental image data take advantage of graphical models with maximal clique analysis and high performance computing techniques as in [37,38]. That said, we have found that, for certain conditions, our approach is competitive with leading maximal clique implementations.…”

Shared-Memory Parallel Probabilistic Graphical Modeling Optimization: Comparison of Threads, OpenMP, and Data-Parallel Primitives

“…The process of segmenting an image involves separating various phases or components from a picture using photometric information and/or relationships between pixels/regions representing a scene. This essential step in an image analysis pipeline has been given great attention recently when studying experimental data [29]. There are several different types of image segmentation algorithms, which can be divided into categories, such as: threshold-based, region-based, edge-based, clustering-based, graph-based, and learning-based techniques.…”

DPP-PMRF: Rethinking Optimization for a Probabilistic Graphical Model Using Data-Parallel Primitives

“…The process of segmenting an image involves separating various phases or components from the picture using photometric information and/or relationships between pixels/regions representing a scene. This essential step in an image analysis pipeline has been given great attention recently when studying experimental data [38]. There are several different types of image segmentation algorithms, which can be divided into categories such as: threshold-based, region-based, edge-based, clustering-based, graph-based and learning-based techniques.…”

“…For the purposes of this analysis, we corrupted the original stack by noise (salt-and-pepper) and additive Gaussian with σ = 100. Additionally, we also simulate ringing artifacts [38] into the sample to closer resemble real-world results. For the segmentation algorithm analysis, the corrupted data serves as the "original data" and the binary stack as the ground-truth.…”