Variations In Image Intensity Research Articles

First in-vivo magic angle directional imaging using dedicated low-field MRI.

To report the first in-vivo results from exploiting the magic angle effect, using a dedicated low-field MRI scanner that can be rotated about two axes. The magic angle directional imaging (MADI) method is used to depict collagen microstructures with 3D collagen tractography of knee ligaments and the meniscus. A novel low-field MRI system was developed, based on a transverse field open magnet, where the magnet can be rotated about two orthogonal axes. Sets of volume scans at various orientations were obtained in healthy volunteers. The experiments focused on the anterior cruciate ligament (ACL) and the meniscus of the knee. The images were co-registered, anatomical regions of interest (ROIs) were selected and the collagen fiber orientations in each voxel were estimated from the observed image intensity variations. The 3D collagen tractography was superimposed on conventional volume images. The MADI method was successfully employed for the first time producing in-vivo results comparable to those previously reported for excised animal specimens using conventional MRI. Tractography plots were generated for the ACL and the menisci. These results are consistent with the known microstructure of collagen fibers in these tissues. Images obtained using low-field MRI with 1 mm3 resolution were of sufficient quality for the MADI method, which was shown to produce high quality in-vivo information of collagen microstructures. This was achieved using a cost effective and sustainable low-field magnet making the technique potentially accessible and scalable, potentially changing the way we image injuries or disease in joints.

A Multivariate Statistical Approach to Wrinkling Detection in Composites.

Nondestructive inspection using ultrasound in materials such as carbon-fiber reinforced polymers (CFRPs) is challenging as the ultrasonic wave will scatter from each ply in the structure of the component. This may be improved using image processing algorithms such as the total focusing method (TFM); however, the high level of backscattering within the sample is very likely to obscure a signal arising from a flaw. Detection of wrinkling, or out-of-plane fiber waviness, is especially difficult to automate as no additional scattering is produced (as might be the case with delaminations). Instead, wrinkling changes how a signal is scattered due to the physical displacement of ply layers from their expected location. In this article, we propose a method of detecting wrinkling by examining the regional variations in image intensity, which are expected to be highly correlated between similar ply layers in the structure. By characterizing the 2-D spatial autocorrelation of an area surrounding a given location in the image of pristine components, the distribution of acceptable values is estimated. Wrinkling is observed to correspond with a significant deviation from this distribution, which is readily detected. A comparison is made with an alternative image processing approach identified from the literature, finding that the proposed method has equivalent performance for large wrinkling amplitudes and better performance for low wrinkling amplitudes.

Spontaneous Emergence of Robustness to Light Variation in CNNs With a Precortically Inspired Module.

The analogies between the mammalian primary visual cortex and the structure of CNNs used for image classification tasks suggest that the introduction of an additional preliminary convolutional module inspired by the mathematical modeling of the precortical neuronal circuits can improve robustness with respect to global light intensity and contrast variations in the input images. We validate this hypothesis using the popular databases MNIST, FashionMNIST, and SVHN for these variations once an extra module is added.

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy.

Image analysis techniques provide objective and reproducible statistics for interpreting microscopy data. At higher dimensions, three-dimensional (3D) volumetric and spatiotemporal data highlight additional properties and behaviors beyond the static 2D focal plane. However, increased dimensionality carries increased complexity, and existing techniques for general segmentation of 3D data are either primitive, or highly specialized to specific biological structures. Borrowing from the principles of 2D topological data analysis (TDA), we formulate a 3D segmentation algorithm that implements persistent homology to identify variations in image intensity. From this, we derive two separate variants applicable to spatial and spatiotemporal data, respectively. We demonstrate that this analysis yields both sensitive and specific results on simulated data and can distinguish prominent biological structures in fluorescence microscopy images, regardless of their shape. Furthermore, we highlight the efficacy of temporal TDA in tracking cell lineage and the frequency of cell and organelle replication.

Leveraging global binary masks for structure segmentation in medical images

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels’ intensity information for inference. Acquiring sufficient training data is another challenge limiting models’ applications. Here, we proposed to leverage the consistency of organs’ anatomical position and shape information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied: (1) global binary masks were the only input for the U-Net based model, forcing exclusively encoding organs’ position and shape information for rough segmentation or localization. (2) Global binary masks were incorporated as an additional channel providing position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart computed tomography (CT) images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. The two scenarios were evaluated using full training split as well as reduced subsets of training data. In scenario (1), training exclusively on global binary masks led to Dice scores of 0.77 ± 0.06 and 0.85 ± 0.04 for the brain and heart structures respectively. Average Euclidian distance of 3.12 ± 1.43 mm and 2.5 ± 0.93 mm were obtained relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicated encoding a surprising degree of position and shape information through global binary masks. In scenario (2), incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3%–125.3% and 1.3%–48.1% for 1–8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building models that are robust to image intensity variations as well as an effective approach to boost performance when access to labeled training data is highly limited.

Ultrasound multifrequency strategy to estimate the lung surface roughness, in silico and in vitro results

Lung ultrasound (LUS) is an important imaging modality to assess the state of the lung surface. Nevertheless, LUS is limited to the visual evaluation of imaging artifacts, especially the vertical ones. These artifacts are observed in pathologies characterized by a reduction of dimensions of air-spaces (alveoli). In contrast, there exist pathologies, such as chronic obstructive pulmonary disease (COPD), in which an enlargement of air-spaces can occur, which causes the lung surface to behave essentially as a perfect reflector, thus not allowing ultrasound penetration. This characteristic high reflectivity could be exploited to characterize the lung surface. Specifically, air-spaces of different sizes could cause the lung surface to have a different roughness, whose estimation could provide a way to assess the state of the lung surface. In this study, we present a quantitative multifrequency approach aiming at estimating the lung surface’s roughness by measuring image intensity variations along the lung surface as a function of frequency. This approach was tested both in silico and in vitro, and it showed promising results. For the in vitro experiments, radiofrequency (RF) data were acquired from a novel experimental model. The results showed consistency between in silico and in vitro experiments.

On detailed deviation zone evaluation of scanned surfaces for automatic detection of defected regions

Online inspection and surface characterization including 3D defect detection of surfaces using 3D scanning and coordinate metrology data has crucial applications in today’s Industry 4.0. Although 3D vision-based metrology methods are superior to 2D in providing spatial information, its processing remains challenge. A novel automated Detailed Deviation Zone Evaluation method is proposed in this paper in which 3D unorganized PC is converted into 2D grayscale image such that the intensity variation of image is proportional to the surface topography. This developed image is addressed as “skin Image” of the scanned surface. The considered point clouds include only XYZ-coordinates. No prior knowledge of defects, and no training set is required. The methodology is fully implemented, and verified by inspecting point clouds of several workpieces with predefined defects. The experimental results show high efficiency of the developed methodology in defect detection and 3D-feature identification irrespective of shape and size.

Biomechanical Investigation of Red Cell Sedimentation Using Blood Shear Stress and Blood Flow Image in a Capillary Chip.

Blood image intensity has been used to detect erythrocyte sedimentation rate (ESR). However, it does not give information on the biophysical properties of blood samples under continuous ESR. In this study, to quantify mechanical variations of blood under continuous ESR, blood shear stress and blood image intensity were obtained by analyzing blood flows in the capillary channel. A blood sample is loaded into a driving syringe to demonstrate the proposed method. The blood flow rate is set in a periodic on-off pattern. A blood sample is then supplied into a capillary chip, and microscopic blood images are captured at specific intervals. Blood shear stress is quantified from the interface of the bloodstream in the coflowing channel. τ0 is defined as the maximum shear stress obtained at the first period. Simultaneously, ESRτ is then obtained by analyzing temporal variations of blood shear stress for every on period. AII is evaluated by analyzing the temporal variation of blood image intensity for every off period. According to the experimental results, a shorter period of T = 4 min and no air cavity contributes to the high sensitivity of the two indices (ESRτ and AII). The τ0 exhibits substantial differences with respect to hematocrits (i.e., 30-50%) as well as diluents. The ESRτ and AII showed a reciprocal relationship with each other. Three suggested properties represented substantial differences for suspended blood samples (i.e., hardened red blood cells, different concentrations of dextran solution, and fibrinogen). In conclusion, the present method can detect variations in blood samples under continuous ESR effectively.

Image Intensity Variation Information for Interest Point Detection.

Interest point detection methods are gaining more attention and are widely applied in computer vision tasks such as image retrieval and 3D reconstruction. However, there still exist two main problems to be solved: (1) from the perspective of mathematical representations, the differences among edges, corners, and blobs have not been convincingly explained and the relationships among the amplitude response, scale factor, and filtering orientation for interest points have not been thoroughly explained; (2) the existing design mechanism for interest point detection does not show how to accurately obtain intensity variation information on corners and blobs. In this paper, the first- and second-order Gaussian directional derivative representations of a step edge, four common genres of corners, an anisotropic-type blob, and an isotropic-type blob are analyzed and derived. Multiple interest point characteristics are discovered. The characteristics for interest points that we obtained help us describe the differences among edges, corners, and blobs, explain why the existing interest point detection methods with multiple scales cannot properly obtain interest points from images, and present novel corner and blob detection methods. Extensive experiments demonstrate the superiority of our proposed methods in terms of detection performance, robustness to affine transformations, noise, image matching, and 3D reconstruction.

Automatic detection of sunspots on solar continuum HMI images blending local–global threshold

A huge collection of solar images to visualize sunspot are acquired by various solar observatories spread across the globe. This necessitates efficient tools for detecting and analyzing the sunspots encompassing diverse solar features. One such contribution is delivered in this work by exploiting the intrinsic intensity variations of solar images associated with sunspots and their attributes. The presented mechanism initially, pre-processes the acquired solar images by correcting the intensity variations introduced while profiling from the sun center to the limb followed by smoothening using a localized window. The resultant is then differenced from the global threshold that is obtained as a result of the statistical analysis computed over the probability distribution function of the input image. This arrangement offers higher discerning variations concerned with the local contextual structures related to sunspot, umbra, and penumbra. Also, it captures the major gradient variation between these regions that adds to the pixel heterogeneity surrounding them to finally render an automatic sunspot detection mechanism distinguishing the diverse solar regions. Receiver Operating Characteristics (ROC) investigation on annual solar images in Flexible Image Transport System (FITS) format reveals the presented method’s efficacy. Also, Pearson correlation analysis of the evaluated sunspot numbers from the detected sunspots with the solar catalog reveals the scheme’s detection closeness. Moreover, the model’s simplicity analyzed along the time and space dimensions affirms its extension to real-time analysis

Initial Observation of Contrast Profiles for 2-Dimensional and 3-Dimensional Magnetic Resonance Imaging Sequences in Magnetic Resonance–Guided Radiation Therapy for Locally Advanced Pancreatic Cancer

In our experience treating locally advanced pancreatic cancer with magnetic resonance-guided radiation therapy (MRgRT), the true-fast imaging with steady-state free precession sequences used to generate both the real-time 2-dimensional (2D) magnetic resonance images (MRI; 2D cine) and the pretreatment high-resolution 3-dimensional (3D) MRI impart differing intensities for relevant structures between the 2 scans. Since these variations can confound target tracking selection, we propose that an understanding of the differing contrast profiles could improve selection of tracking structures. We retrospectively reviewed both 2D cine and 3D MRI images for 20 patients with pancreatic cancer treated with MRgRT. At simulation, an appropriate tracking target was identified and contoured on a single 3-mm sagittal slice of the 3D MRI. This sagittal slice was directly compared with the coregistered 7-mm 2D cine to identify structures with notable discrepancies in signal intensity. The 3D MRI was then explored in additional planes to confirm structure identities. For quantitative verification of the clinically observed differences, the pixel intensity distributions of 2D cine and 3D MRI digital imaging and communications in medicine data sets were statistically compared. In all patients reviewed, arteries (aorta, celiac, superior mesenteric artery, hepatic artery) appeared mildly hyperintense on both scans. However, veins (portal vein, superior mesenteric vein) appeared hyperintense on 2D cine but isointense on 3D MRI. Biliary structures appeared mildly hyperintense on 2D cine but starkly hyperintense on 3D MRI. The pixel intensity distributions extracted from 2D cine and 3D MRI images were confirmed to differ significantly (2 sample Kolmogorov-Smirnov test; test statistic, 0.40; P < .001). There are significant variations in image intensity between the immediate pretreatment 2D cine compared with the initial planning 3D MRI. Understanding variations of image intensity between the different MRI sequences used in MRgRT is valuable to radiation oncologists and may lead to improved target tracking and optimized treatment delivery.

Machine Learning Color Feature Analysis of a High Throughput Nanoparticle Conjugate Sensing Assay.

Plasmonic nanoparticles are finding applications within the single molecule sensing field in a "dimer" format, where interaction of the target with hairpin DNA causes a decrease in the interparticle distance, leading to a localized surface plasmon resonance shift. While this shift may be detected using spectroscopy, achieving statistical relevance requires the measurement of thousands of nanoparticle dimers and the timescales required for spectroscopic analysis are incompatible with point-of-care devices. However, using dark-field imaging of the dimer structures, simultaneous digital analysis of the plasmonic resonance shift after target interaction of thousands of dimer structures may be achieved in minutes. The main challenge of this digital analysis on the single-molecule scale was the occurrence of false signals caused by non-specifically bound clusters of nanoparticles. This effect may be reduced by digitally separating dimers from other nanoconjugate types. Variation in image intensity was observed to have a discernible impact on the color analysis of the nanoconjugate constructs and thus the accuracy of the digital separation. Color spaces wherein intensity may be uncoupled from the color information (hue, saturation, and value (HSV) and luminance, a* vector, and b* vector (LAB) were contrasted to a color space which cannot uncouple intensity (RGB) to train a classifier algorithm. Each classifier algorithm was validated to determine which color space produced the most accurate digital separation of the nanoconjugate types. The LAB-based learning classifier demonstrated the highest accuracy for digitally separating nanoparticles. Using this classifier, nanoparticle conjugates were monitored for their plasmonic color shift after interaction with a synthetic RNA target, resulting in a platform with a highly accurate yes/no response with a true positive rate of 88% and a true negative rate of 100%. The sensor response of tested single stranded RNA (ssRNA) samples was well above control responses for target concentrations in the range of 10 aM-1 pM.

Ultrasound multifrequency strategy applied to the estimation of lung surface roughness

There exist lung pathologies (e.g., COPD) characterized by an enlargement of air-spaces. Since air-spaces of different sizes can generate different levels of roughness along the lung surface, estimating the roughness may provide an indirect characterization of the lung state. This study, thus, analyzes the possibility to develop a multi-frequency quantitative approach forthe estimation of lung surface roughness. Specifically, the presented technique focuses on the analysis of ultrasound image intensity variation along the lung surface as a function of frequency. In silico and in vitro results will be presented. First, k-wave was used to study the effect of different levels of lung surface roughness on numerically generated ultrasound images. Data were simulated with center frequencies from 1 to 10 MHz (bandwidth = 0.5 MHz). The same acquisition strategy was then used to acquire data from 3D printed steel models, made to mimic an acoustic interface with high reflection coefficient (similar to air-tissue interfaces) and realized with different levels of roughness. As expected, due to diffuse scattering, the increase of the “air-spaces” diameter is linked to a decrease of the frequency at which a significant drop of intensity was observed. This ultimately provides a way to indirectly estimate lung source roughness.

The neglected background cues can facilitate finger vein recognition

Recently, finger vein based biometric authentication has attracted considerable attention due to its high efficiency and high security. However, most existing finger vein representation methods focus on vein traits while ignoring background cues, although background cues also convey identity information specific to each individual. In this paper, we leverage background intensity variations in finger vein images as new features to enrich discriminative representation, and accordingly propose a new descriptor named Intensity Orientation Vector (IOV). IOV, scaleable to reflect characteristics of finger tissues, offers additional informative cues for finger vein representation. Furthermore, we propose a new learning scheme named Semantic Similarity Preserved Discrete Binary Feature Learning (SSP-DBFL) for finger vein recognition. Unlike the most bimodal binary feature representation methods, SSP-DBFL preserves high-level semantic similarity in a common Hamming space to exploit the consensus between vein traits and background cues. Specifically, given a finger vein image, we first extract the direction difference vectors (DDV) as the main vein traits and the IOV as the auxiliary background cues. Subsequently, we jointly learn projection functions from these two types of features in a supervised manner, converting the two features into discriminative binary codes with their semantic similarity preserved. Finally, the binary codes are pooled into histogram-based vectors for finger vein representation. Extensive experiments are conducted on five widely used finger vein databases and demonstrate the effectiveness of our proposed IOV and SSP-DBFL.

Image registration method using representative feature detection and iterative coherent spatial mapping for infrared medical images with flat regions

In the registration of medical images, nonrigid registration targets, images with large displacement caused by different postures of the human body, and frequent variations in image intensity due to physiological phenomena are substantial problems that make medical images less suitable for intensity-based image registration modes. These problems also greatly increase the difficulty and complexity of feature detection and matching for feature-based image registration modes. This research introduces an automatic image registration algorithm for infrared medical images that offers the following benefits: effective detection of feature points in flat regions (cold patterns) that appear due to changes in the human body’s thermal patterns, improved mismatch removal through coherent spatial mapping for improved feature point matching, and large-displacement optical flow for optimal transformation. This method was compared with various classical gold standard image registration methods to evaluate its performance. The models were compared for the three key steps of the registration process—feature detection, feature point matching, and image transformation—and the results are presented visually and quantitatively. The results demonstrate that the proposed method outperforms existing methods in all tasks, including in terms of the features detected, uniformity of feature points, matching accuracy, and control point sparsity, and achieves optimal image transformation. The performance of the proposed method with four common image types was also evaluated, and the results verify that the proposed method has a high degree of stability and can effectively register medical images under a variety of conditions.

Robust pattern for face recognition using combined Weber and pentagonal-triangle graph structure pattern

Face recognition is a challenging task in computer vision and information retrieval due to the large variation in facial images in terms of pose, expression and illumination. These challenges motivate us to propose a robust pattern for face recognition using combined Weber pattern (CWP) and pentagonal-triangle graph structure pattern (PTGSP). Firstly, abrupt intensity variations in facial images are removed by multiblock operation. Further, by exploring the relationship among center, neighboring and adjacent pixels, CWP consisting of three unique Weber patterns is computed. In order to obtain the pattern that is more robust to facial variations, PTGSP has been computed on the facial images. PTGSP covers the widely used features of face images. A feature set of high dimension is produced by combining the features of CWP and PTGSP. Dimensionality of the proposed feature and also variance within class is reduced through principal component analysis (PCA) plus linear discriminant analysis (LDA) algorithm. The classification performance of the proposed method is compared with various state-of-the-art methods on variety of benchmark face datasets with variation in pose, expression, illumination and occlusion. Experiments on FEI, Georgia, ORL, Yale and Faces94 databases clearly prove the robustness of the proposed method in contrast to existing handcrafted feature extraction techniques.

Initial observation of contrast profiles for 3D and 2D MRI sequences in MR-guided radiation therapy for locally advanced pancreatic cancer.

541 Background: MR-guided stereotactic body radiation therapy (MR-SBRT) is a novel method of treating mobile tumors with soft-tissue gating and on-table adaptive planning. In our experience using the ViewRay MRIdian system (VR) for treating locally advanced pancreatic cancer (PA) with MR-SBRT, the true-fast imaging with steady-state free precession (TRUFI) sequences on the VR impart differing intensities for relevant structures seen on the pre-treatment high resolution 3D MRI (3D MRI) versus the real-time 2D cine MRI (2D cine) used for target tracking. Since these variations can confound target tracking selection, we propose that an understanding of the differing contrast profiles could improve selection of tracking structures and optimize treatment delivery. Methods: We retrospectively reviewed both 3D MRI and 2D cine images for patients (pts) with PA (n =20) treated on the VR. At simulation, an appropriate tracking target was identified and contoured on a single 3mm sagittal slice of the 3D MRI. This sagittal slice was directly compared to the registered 7mm 2D cine to identify structures with notable discrepancies in signal intensity. The 3D MRI was then explored in additional planes to confirm structure identities. For quantitative verification of the clinically observed differences, the pixel intensity distributions of 3D MRI and 2D cine DICOM image datasets were statistically compared. Results: In all pts reviewed, arteries (aorta, celiac, SMA) appeared with similar contrast profiles on both images. However, veins (portal vein, SMV) appeared hypointense on 3D MRI but hyperintense on 2D cine. Biliary structures appeared hyperintense on 3D MRI but only mildly hyperintense on 2D cine. The pixel intensity distributions extracted from 3D MRI and 2D cine images were confirmed to differ significantly (two sample Kolmogorov-Smirnov test; test statistic =0.40; p &lt; 0.001). Conclusions: There are significant variations in image intensity between the initial treatment planning 3D MRI and the immediate pre-treatment 2D cine obtained with the VR. Understanding these discrepancies can guide radiation oncologists in choosing optimal tracking targets. Future work will focus on identifying the particular causes and frequencies of target tracking failures and exploring alternative tracking algorithms using artificial intelligence which could ultimately allow for VMAT on the ViewRay system.

A Convolutional Neural Network for Learning Local Feature Descriptors on Multispectral Images

This work presents a novel convolutional neural network, termed multispectral features network (MF-Net), for learning local feature descriptors in multispectral images. Unlike most existing solutions, which primarily handle images from the visible light spectrum, we propose a learning-based method that deals with image data acquired from different spectrum bands. To design our convolutional neural network, we introduce a new layer that incorporates Log-Gabor filters to enhance the network capability to work with nonlinear intensity variations in images captured from different electromagnetic frequencies spectrum. This layer, entitled mapping layer, can be easily integrated into different network architectures. To demonstrate the efficacy and limitations of our method, we went on experiments with two distinct datasets extensively used in previous works composed of image pairs from the visible spectrum and the infrared spectrum. Experimental results with datasets containing images obtained from visible light and infrared spectrum show that our method can accurately match features, outperforming some state-of-the-art learning-based algorithms.

Associations of Oral Contraceptives with Mammographic Breast Density in Premenopausal Women.

We investigated the associations of oral contraceptives (OC) with percent breast density (PD), absolute dense area (DA), nondense area (NDA), and a novel image intensity variation (V) measure in premenopausal women. This study included 1,233 controls from a nested case-control study within Nurses' Health Study II cohort. Information on OCs was collected in 1989 and updated biennially. OC use was defined from the questionnaire closest to the mammogram date. PD, DA, and NDA were measured from digitized film mammograms using a computer-assisted thresholding technique; the V measure was obtained with a previously developed algorithm measuring the SD of pixel values in the eroded breast region. Generalized linear regression was used to assess associations between OCs and density measures (square root-transformed PD, DA, and NDA, and -untransformed V). OC use was not associated with PD [current vs. never: β = -0.06; 95% confidence interval (CI), -0.37-0.24; past vs. never: β = 0.10; 95% CI, -0.09-0.29], DA (current vs. never: β = -0.20; 95% CI -0.59-0.18; past vs. never: β = 0.13; 95% CI, -0.12-0.39), and NDA (current vs. never: β = -0.19; 95% CI, -0.56-0.18; past vs. never: β = -0.01; 95% CI, -0.28-0.25). Women with younger age at initiation had significantly greater V-measure (<20 years vs. never: β = 26.88; 95% CI, 3.18-50.58; 20-24 years vs. never: β = 20.23; 95% CI, -4.24-44.71; 25-29 years vs. never: β = 2.61; 95% CI -29.00-34.23; ≥30 years vs. never: β = 0.28; 95% CI, -34.16-34.72, P trend = 0.03). Our findings suggest that an earlier age at first OC use was associated with significantly greater V. These findings could guide decisions about the age for OC initiation.

Full-field deformation measurements in the transmission electron microscope using digital image correlation and particle tracking

Determining displacement and/or strain fields at the nanoscale during material deformation can be instrumental in developing a multiscale understanding of material response. Full-field quantitative kinematic measurements based on transmission electron microscopy (TEM) are lagging behind other microscopy techniques. Here, we develop an experimental approach combining digital image correlation (DIC) and particle tracking (PT) for characterizing in situ microscale deformation of amorphous SiO2 in the TEM. Gold nanoparticles deposited on SiO2 provide both the speckle pattern required by DIC when averaged over a subset region and target particles for PT. To demonstrate and validate the feasibility of using DIC and PT in the TEM, micron sized SiO2 beam samples are machined using a focused ion beam (FIB) and loaded in the TEM via indentation. DIC and PT are then applied to measure in situ displacements from a sequence of TEM images taken during loading and creep of the beam. Results of the two measurement methods agree well with each other and with the applied displacement measurements, thus demonstrating their effectiveness in determining local displacements from TEM experiments. Sources of noise resulting from sample drift and image intensity variations are discussed.