Segmentation and learning in the quantitative analysis of microscopy images

Abstract

In material science and bio-medical domains the quantity and quality of microscopy images is rapidly increasing and there is a great need to automatically detect, delineate and quantify particles, grains, cells, neurons and other functional "objects" within these images. These are challenging problems for image processing because of the variability in object appearance that inevitably arises in real world image acquisition and analysis. One of the most promising (and practical) ways to address these challenges is interactive image segmentation. These algorithms are designed to incorporate input from a human operator to tailor the segmentation method to the image at hand. Interactive image segmentation is now a key tool in a wide range of applications in microscopy and elsewhere. Historically, interactive image segmentation algorithms have tailored segmentation on an image-by-image basis, and information derived from operator input is not transferred between images. But recently there has been increasing interest to use machine learning in segmentation to provide interactive tools that accumulate and learn from the operator input over longer periods of time. These new learning algorithms reduce the need for operator input over time, and can potentially provide a more dynamic balance between customization and automation for different applications. This paper reviews the state of the art in this area, provides a unified view of these algorithms, and compares the segmentation performance of various design choices.

Quantifying Morphological Features of α-U3O8 with Image Analysis for Nuclear Forensics

“…To establish the scale for the SEM image, the horizontal field width (HFW) from the SEM image was used. The MAMA software segments particles using a modified “tunable” watershed algorithm, which views the image as one with topographical relief and subsequently segments based on traditional watershedding techniques. − The smoothest setting was used for microparticle segmentation. Segmentation enables the quantitative identification of particle attributes, such as particle area and circularity, from SEM images.…”

Impact of Dynamic Non-Equilibrium Processes on Fracture Mechanisms of High-Strength Titanium Alloy VT23

“…It is known that deep conical dimples are inherent in the fracture of very plastic materials. Therefore, the authors assumed that an increase in crack resistance was accompanied by an increase in the depth of the dimples on the fracture surface [27,28]. Figure 9 shows distribution histograms of the visual depth of the dimples for images shown in Figure 8.…”

Deep Learning for Structural Health Monitoring: A Damage Characterization Application

“…Image processing has been an important tool in material/ structural characterization for over three decades (Krakow, 1982;Duval et al, 2014;Robertson et al, 2011;Leach, 2013). Texture analysis (Comer & Delp, 2000)and segmentation (Ruggiero, Ross, & Porter, 2015;Park, Huang, Ji, & Ding, 2013) are few image processing techniques that have been used to address some of the challenges in material characterization. Pre-processing steps like filtering and enhancement techniques (Tomasi & Manduchi, 1998;Angulo & Velasco-Forero, 2013;Buades, Coll, & Morel, 2005) have been used to denoise the image and perform alignment and artifact correction.…”