scholarly journals Image-to-Image Translation as a Pretext for Unsupervised Detection of Cancerous Regions in Histology Imagery

2021 ◽  
Vol 29 (4) ◽  
Author(s):  
Dejan Štepec ◽  
Danijel Skočaj
Keyword(s):  
Biomedical Applications ◽  
Large Degree ◽  
Imaging Data ◽  
Normal Appearance ◽  
Visual Appearance ◽  
Domain Experts ◽  
Region Detection ◽  
Image Translation ◽  
Universal Solution ◽  
Supervised Methods

Detection of visual anomalies refers to the problem of finding patterns in different imaging data that do not conform to the expected visual appearance, and is a widely studied problem in different domains. Due to the nature of anomaly occurrences and underlying generating processes, it is hard to characterize them and obtain labelled data. Obtaining labelled data is especially difficult in biomedical applications, where only trained domain experts can provide labels, which are often diverse and complex to a large degree. The recently presented approaches for unsupervised detection of visual anomalies omit the need for labelled data and demonstrate promising results in domains where anomalous samples significantly deviate from the normal appearance. Despite promising results, the performance of such approaches still lags behind supervised approaches and does not provide a universal solution. In this work, we present an image-to-image translation-based framework that significantly surpasses the performance of existing unsupervised methods and approaches the performance of supervised methods in a challenging domain of cancerous region detection in histology imagery.

scholarly journals Polarizer-Free AOTF-Based SWIR Hyperspectral Imaging for Biomedical Applications

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4439
Author(s):  
Vladislav Batshev ◽  
Alexander Machikhin ◽  
Grigoriy Martynov ◽  
Vitold Pozhar ◽  
Sergey Boritko ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Biomedical Applications ◽  
Cost Effective ◽  
Short Wave ◽  
Tunable Filter ◽  
Quality Analysis ◽  
Imaging Data ◽  
Image Quality Analysis ◽  
Data Volume ◽  
Integrate Design

Optical biomedical imaging in short wave infrared (SWIR) range within 0.9–1.7 μm is a rapidly developing technique. For this reason, there is an increasing interest in cost-effective and robust hardware for hyperspectral imaging data acquisition in this range. Tunable-filter-based solutions are of particular interest as they provide image processing flexibility and effectiveness in terms of collected data volume. Acousto-optical tunable filters (AOTFs) provide a unique set of features necessary for high-quality SWIR hyperspectral imaging. In this paper, we discuss a polarizer-free configuration of an imaging AOTF that provides a compact and easy-to-integrate design of the whole imager. We have carried out image quality analysis of this system, assembled it and validated its efficiency through multiple experiments. The developed system can be helpful in many hyperspectral applications including biomedical analyses.

Feasibility of Biomedical Applications of Hall Effect Imaging

2000 ◽  
Vol 22 (2) ◽  
pp. 123-136 ◽  
Author(s):  
Han Wen
Keyword(s):  
Hall Effect ◽  
Biomedical Applications ◽  
Three Dimensional ◽  
Imaging Data ◽  
Theoretical Understanding ◽  
Complex Samples ◽  
Quantitative Measurements ◽  
Basic Physics ◽  
A New Technique

Hall effect imaging is a new technique for mapping the electrical properties of a sample. Its principle has been demonstrated in two- and three-dimensional phantom images. Based on the experimental data and theoretical understanding of this technique developed over the past few years, this paper addresses the most relevant question for biomedical applications: whether Hall effect imaging is ultimately applicable to complex biological systems such as the human body. The arguments are given at the basic physics level, so that the conclusion is independent of current technology status. These arguments are corroborated with imaging data of an aorta sample. The conclusion is that Hall effect imaging is not suited for quantifying the electrical constants in complex biological samples. This technique is able to produce high-resolution volume images of samples in vitro that reflect their electrical heterogeneity. However, quantitative measurements of electrical constants are not practical for complex samples.

scholarly journals 2D-to-3D image translation of complex nanoporous volumes using generative networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Timothy I. Anderson ◽  
Bolivia Vega ◽  
Jesse McKinzie ◽  
Saman A. Aryana ◽  
Anthony R. Kovscek
Keyword(s):  
Deep Learning ◽  
Reactive Transport ◽  
Ion Beam ◽  
Training Data ◽  
Imaging Modalities ◽  
High Contrast ◽  
Imaging Data ◽  
Contrast Imaging ◽  
Apparent Permeability ◽  
Image Translation

AbstractImage-based characterization offers a powerful approach to studying geological porous media at the nanoscale and images are critical to understanding reactive transport mechanisms in reservoirs relevant to energy and sustainability technologies such as carbon sequestration, subsurface hydrogen storage, and natural gas recovery. Nanoimaging presents a trade off, however, between higher-contrast sample-destructive and lower-contrast sample-preserving imaging modalities. Furthermore, high-contrast imaging modalities often acquire only 2D images, while 3D volumes are needed to characterize fully a source rock sample. In this work, we present deep learning image translation models to predict high-contrast focused ion beam-scanning electron microscopy (FIB-SEM) image volumes from transmission X-ray microscopy (TXM) images when only 2D paired training data is available. We introduce a regularization method for improving 3D volume generation from 2D-to-2D deep learning image models and apply this approach to translate 3D TXM volumes to FIB-SEM fidelity. We then segment a predicted FIB-SEM volume into a flow simulation domain and calculate the sample apparent permeability using a lattice Boltzmann method (LBM) technique. Results show that our image translation approach produces simulation domains suitable for flow visualization and allows for accurate characterization of petrophysical properties from non-destructive imaging data.

scholarly journals Untethered and ultrafast soft-bodied robots

2020 ◽  
Vol 1 (1) ◽  
Author(s):  
Xu Wang ◽  
Guoyong Mao ◽  
Jin Ge ◽  
Michael Drack ◽  
Gilbert Santiago Cañón Bermúdez ◽  
...  
Keyword(s):  
Biomedical Applications ◽  
High Speed ◽  
Large Degree ◽  
Model Systems ◽  
Small Scale ◽  
Natural Environments ◽  
Soft Robots ◽  
High Frequencies ◽  
Strongly Nonlinear ◽  
Specific Energy Density

Abstract Acting at high speed enables creatures to survive in their harsh natural environments. They developed strategies for fast actuation that inspire technological embodiments like soft robots. Here, we demonstrate a series of simulation-guided lightweight, durable, untethered, small-scale soft-bodied robots that perform large-degree deformations at high frequencies up to 100 Hz, are driven at very low magnetic fields down to 0.5 mT and exhibit a specific energy density of 10.8 kJ m−3 mT−1. Unforeseen asynchronous strongly nonlinear cross-clapping behavior of our robots is observed in experiments and analyzed by simulation, breaking ground for future designs of soft-bodied robots. Our robots walk, swim, levitate, transport cargo, squeeze into a vessel smaller than their dimensions and can momentarily close around a living fly. Such ultrafast soft robots can rapidly adapt to varying environmental conditions, inspire biomedical applications in confined environments, and serve as model systems to develop complex movements inspired by nature.

scholarly journals Shared neural codes for visual and semantic information about familiar faces in a common representational space

2021 ◽  
Vol 118 (45) ◽  
pp. e2110474118
Author(s):  
Matteo Visconti di Oleggio Castello ◽  
James V. Haxby ◽  
M. Ida Gobbini
Keyword(s):  
Visual Processing ◽  
Semantic Information ◽  
Neural System ◽  
Imaging Data ◽  
Functional Magnetic Resonance ◽  
Magnetic Resonance Imaging Data ◽  
Core System ◽  
Visual Appearance ◽  
Neural Representations ◽  
Representational Space

Processes evoked by seeing a personally familiar face encompass recognition of visual appearance and activation of social and person knowledge. Whereas visual appearance is the same for all viewers, social and person knowledge may be more idiosyncratic. Using between-subject multivariate decoding of hyperaligned functional magnetic resonance imaging data, we investigated whether representations of personally familiar faces in different parts of the distributed neural system for face perception are shared across individuals who know the same people. We found that the identities of both personally familiar and merely visually familiar faces were decoded accurately across brains in the core system for visual processing, but only the identities of personally familiar faces could be decoded across brains in the extended system for processing nonvisual information associated with faces. Our results show that personal interactions with the same individuals lead to shared neural representations of both the seen and unseen features that distinguish their identities.

scholarly journals Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl

2019 ◽  
Vol 16 (12) ◽  
pp. 1247-1253 ◽  
Author(s):  
Juan C. Caicedo ◽  
Allen Goodman ◽  
Kyle W. Karhohs ◽  
Beth A. Cimini ◽  
Jeanelle Ackerman ◽  
...  
Keyword(s):  
Biomedical Applications ◽  
Data Science ◽  
Human Interaction ◽  
Imaging Data ◽  
Cell Nuclei ◽  
Experimental Conditions ◽  
Microscopy Image ◽  
Bioimage Analysis ◽  
Microscopy Images ◽  
Nucleus Segmentation

Abstract Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

scholarly journals Validation of image segmentation by estimating rater bias and variance

2008 ◽  
Vol 366 (1874) ◽  
pp. 2361-2375 ◽  
Author(s):  
Simon K Warfield ◽  
Kelly H Zou ◽  
William M Wells
Keyword(s):  
Clinical Data ◽  
Alternative Assessment ◽  
Full Range ◽  
Ground Truth ◽  
Automated Image Analysis ◽  
Reference Standard ◽  
Imaging Data ◽  
Domain Experts ◽  
Accuracy And Precision ◽  
Assessment Approach

The accuracy and precision of segmentations of medical images has been difficult to quantify in the absence of a ‘ground truth’ or reference standard segmentation for clinical data. Although physical or digital phantoms can help by providing a reference standard, they do not allow the reproduction of the full range of imaging and anatomical characteristics observed in clinical data. An alternative assessment approach is to compare with segmentations generated by domain experts. Segmentations may be generated by raters who are trained experts or by automated image analysis algorithms. Typically, these segmentations differ due to intra-rater and inter-rater variability. The most appropriate way to compare such segmentations has been unclear. We present here a new algorithm to enable the estimation of performance characteristics, and a true labelling, from observations of segmentations of imaging data where segmentation labels may be ordered or continuous measures. This approach may be used with, among others, surface, distance transform or level-set representations of segmentations, and can be used to assess whether or not a rater consistently overestimates or underestimates the position of a boundary.

scholarly journals Diseased Region Detection of Longitudinal Knee Magnetic Resonance Imaging Data

2015 ◽  
Vol 34 (9) ◽  
pp. 1914-1927 ◽  
Author(s):  
Chao Huang ◽  
Liang Shan ◽  
H. Cecil Charles ◽  
Wolfgang Wirth ◽  
Marc Niethammer ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Data ◽  
Region Detection ◽  
Knee Magnetic Resonance Imaging

Applications of Scanning Microscopy in Biomedical Research

1968 ◽  
Vol 26 ◽  
pp. 354-355
Author(s):  
T. L. Hayes
Keyword(s):  
Information Content ◽  
Biomedical Research ◽  
Biomedical Applications ◽  
Three Dimensional ◽  
Dental Enamel ◽  
Resolving Power ◽  
Whole Mount ◽  
Two Parameters ◽  
Content Information ◽  
Sectioned Tissue

Biomedical applications of the scanning electron microscope (SEM) have increased in number quite rapidly over the last several years. Studies have been made of cells, whole mount tissue, sectioned tissue, particles, human chromosomes, microorganisms, dental enamel and skeletal material. Many of the advantages of using this instrument for such investigations come from its ability to produce images that are high in information content. Information about the chemical make-up of the specimen, its electrical properties and its three dimensional architecture all may be represented in such images. Since the biological system is distinctive in its chemistry and often spatially scaled to the resolving power of the SEM, these images are particularly useful in biomedical research.In any form of microscopy there are two parameters that together determine the usefulness of the image. One parameter is the size of the volume being studied or resolving power of the instrument and the other is the amount of information about this volume that is displayed in the image. Both parameters are important in describing the performance of a microscope. The light microscope image, for example, is rich in information content (chemical, spatial, living specimen, etc.) but is very limited in resolving power.

Sign in / Sign up

Export Citation Format

Share Document