Image Textural Changes Research Articles

Effect of a new deep learning image reconstruction algorithm for abdominal computed tomography imaging on image quality and dose reduction compared with two iterative reconstruction algorithms: a phantom study.

New reconstruction algorithms based on deep learning have been developed to correct the image texture changes related to the use of iterative reconstruction algorithms. The purpose of this study was to evaluate the impact of a new deep learning image reconstruction [Advanced intelligent Clear-IQ Engine (AiCE)] algorithm on image-quality and dose reduction compared to a hybrid iterative reconstruction (AIDR 3D) algorithm and a model-based iterative reconstruction (FIRST) algorithm. Acquisitions were carried out using the ACR 464 phantom (and its body ring) at six dose levels (volume computed tomography dose index 15/10/7.5/5/2.5/1 mGy). Raw data were reconstructed using three levels (Mild/Standard/Strong) of AIDR 3D, of FIRST and AiCE. Noise-power-spectrum (NPS) and task-based transfer function (TTF) were computed. Detectability index was computed to model the detection of a small calcification (1.5-mm diameter and 500 HU) and a large mass in the liver (25-mm diameter and 120 HU). NPS peaks were lower with AiCE than with AIDR 3D (-41%±6% for all levels) or FIRST (-15%±6% for Strong level and -41%±11% for both other levels). The average NPS spatial frequency was lower with AICE than AIDR 3D (-9%±2% using Mild and -3%±2% using Strong) but higher than FIRST for Standard (6%±3%) and Strong (25%±3%) levels. For acrylic insert, values of TTF at 50 percent were higher with AICE than AIDR 3D and FIRST, except for Mild level (-6%±6% and -13%±3%, respectively). For bone insert, values of TTF at 50 percent were higher with AICE than AIDR 3D but lower than FIRST (-19%±14%). For both simulated lesions, detectability index values were higher with AICE than AIDR 3D and FIRST (except for Strong level and for the small feature; -21%±14%). Using the Standard level, dose could be reduced by -79% for the small calcification and -57% for the large mass using AICE compared to AIDR 3D. The new deep learning image reconstruction algorithm AiCE generates an image-quality with less noise and/or less smudged/smooth images and a higher detectability than the AIDR 3D or FIRST algorithms. The outcomes of our phantom study suggest a good potential of dose reduction using AiCE but it should be confirmed clinically in patients.

Quantitative response of healthy muscle following the induction of capsaicin: an exploratory randomized controlled trial

BackgroundMyofascial pain syndrome (MPS) is a prevalent chronic pain disorder primarily characterized by myofascial trigger points (MTrPs). There is limited knowledge on the pathophysiology and mechanisms underlying MTrP and its development. Research has previously demonstrated the identification of MTrPs using ultrasound and vibration sonoelastography, although there is some contradictory evidence regarding if MTrPs present as hyper or hypoechoic regions. Electromyography (EMG) investigations of MTrP have demonstrated that MTrPs are usually located proximal to innervation zones where the peak surface EMG signals are obtained from. Central sensitization has been proposed as the primary mechanism underlying MTrP development. Central sensitization is associated with hyperexcitability of neuronal responses to normal or noxious stimuli. There is a need for a study that measures ultrasound image textural changes and motor unit activity responses in the muscle following sensitization. The purpose of this study is to determine whether sensitizing healthy muscle using capsaicin induces a regional change in image texture variables within the specific and surrounding muscles, as well as the motor unit frequency and amplitude changes that accompany them. This is an exploratory trial that aims to provide preliminary evidence on whether central sensitization is a direct cause of taut band and MTrP development.MethodsEthical approval was obtained from the University Health Network (UHN) Research Ethics Board. This proposed study is a single centered, factorial, randomized placebo-controlled trial with two independent variables, depth of capsaicin application and dose of capsaicin, for a total of six treatment arms and three control treatment groups.DiscussionThis will be the first study that assesses the B-mode ultrasound image texture of induced sensitized muscles and will provide more evidence on muscle motor unit activity and regional changes of central sensitization. Findings from this study may support one of few hypotheses proposed delineating the involvement of central sensitization in the development of trigger points.Trial registrationNational Institutes of Health ClinicalTrials.gov NCT03944889. Registered on May 07, 2019

On the correlation between second order texture features and human observer detection performance in digital images

Image texture, the relative spatial arrangement of intensity values in an image, encodes valuable information about the scene. As it stands, much of this potential information remains untapped. Understanding how to decipher textural details would afford another method of extracting knowledge of the physical world from images. In this work, we attempt to bridge the gap in research between quantitative texture analysis and the visual perception of textures. The impact of changes in image texture on human observer’s ability to perform signal detection and localization tasks in complex digital images is not understood. We examine this critical question by studying task-based human observer performance in detecting and localizing signals in tomographic breast images. We have also investigated how these changes impact the formation of second-order image texture. We used digital breast tomosynthesis (DBT) an FDA approved tomographic X-ray breast imaging method as the modality of choice to show our preliminary results. Our human observer studies involve localization ROC (LROC) studies for low contrast mass detection in DBT. Simulated images are used as they offer the benefit of known ground truth. Our results prove that changes in system geometry or processing leads to changes in image texture magnitudes. We show that the variations in several well-known texture features estimated in digital images correlate with human observer detection–localization performance for signals embedded in them. This insight can allow efficient and practical techniques to identify the best imaging system design and algorithms or filtering tools by examining the changes in these texture features. This concept linking texture feature estimates and task based image quality assessment can be extended to several other imaging modalities and applications as well. It can also offer feedback in system and algorithm designs with a goal to improve perceptual benefits. Broader impact can be in wide array of areas including imaging system design, image processing, data science, machine learning, computer vision, perceptual and vision science. Our results also point to the caution that must be exercised in using these texture features as image-based radiomic features or as predictive markers for risk assessment as they are sensitive to system or image processing changes.

MRI Radiomic Analysis of IMRT-Induced Bladder Wall Changes in Prostate Cancer Patients: A Relationship with Radiation Dose and Toxicity

BackgroundThe main purpose of this study was to assess the structural changes in the bladder wall of prostate cancer patients treated with intensity-modulated radiation therapy using magnetic resonance imaging texture features analysis and to correlate image texture changes with radiation dose and urinary toxicity. MethodsEthical clearance was granted to enroll 33 patients into this study who were treated with intensity-modulated radiation therapy for prostate cancer. All patients underwent two magnetic resonance imagings before and after radiation therapy (RT). A total of 274 radiomic features were extracted from MR-T2W–weighted images. Wilcoxon singed rank-test was performed to assess significance of the change in mean radiomic features post-RT relative to pre-RT values. The relationship between radiation dose and feature changes was assessed and depicted. Cystitis was recorded as urinary toxicity. Area under receiver operating characteristic curve of a logistic regression–based classifier was used to find correlation between radiomic features with significant changes and radiation toxicity. ResultsThirty-three bladder walls were analyzed, with 11 patients developing grade ≥2 urinary toxicity. We showed that radiomic features may predict radiation toxicity and features including S5.0SumVarnc, S2.2SumVarnc, S1.0AngScMom, S0.4SumAverg, and S5. _5InvDfMom with area under receiver operating characteristic curve 0.75, 0.69, 0.65, 0.63, and 0.62 had highest correlation with toxicity, respectively. The results showed that most of the radiomic features were changed with radiation dose. ConclusionFeature changes have a good correlation with radiation dose and radiation-induced urinary toxicity. These radiomic features can be identified as being potentially important imaging biomarkers and also assessing mechanisms of radiation-induced bladder injuries.

Evaluating the cerebral correlates of survival in amyotrophic lateral sclerosis

ObjectiveTo evaluate cerebral degenerative changes in ALS and their correlates with survival using 3D texture analysis.MethodsA total of 157 participants were included in this analysis from four neuroimaging studies. Voxel‐wise texture analysis on T1‐weighted brain magnetic resonance images (MRIs) was conducted between patients and controls. Patients were divided into long‐ and short‐survivors using the median survival of the cohort. Neuroanatomical differences between the two survival groups were also investigated.ResultsWhole‐brain analysis revealed significant changes in image texture (FDR P < 0.05) bilaterally in the motor cortex, corticospinal tract (CST), insula, basal ganglia, hippocampus, and frontal regions including subcortical white matter. The texture of the CST correlated (P < 0.05) with finger‐ and foot‐tapping rate, measures of upper motor neuron function. Patients with a survival below the media of 19.5 months demonstrated texture change (FDR P < 0.05) in the motor cortex, CST, basal ganglia, and the hippocampus, a distribution which corresponds to stage 4 of the distribution TDP‐43 pathology in ALS. Patients with longer survival exhibited texture changes restricted to motor regions, including the motor cortex and the CST.InterpretationWidespread gray and white matter pathology is evident in ALS, as revealed by texture analysis of conventional T1‐weighted MRI. Length of survival in patients with ALS is associated with the spatial extent of cerebral degeneration.

Changes on image texture features of breakfast flakes cereals during water absorption

Normally breakfast cereal flakes are consumed by pouring them into a bowl and covering them with fresh or cold milk. During this process the liquid uptake causes changes in the surface and internal matrix of breakfast cereals that influence texture and integrity. Some breakfast cereal as flakes have a translucent structure that could provide information about the solid matrix and air cells and how they change during liquid absorption. The objective of the study was to assess the image texture changes of corn flakes and frosted flakes during water absorption at 5, 15 and 25 °C, employing 11 image feature textures extracted from grey-level co-occurrence matrix and grey-level run length matrix (at three directions) and to relate the fractal dimension (FD) of images with rupture force (RF) reduction during soaking of both flakes at 5 °C. The most relevant result from principal component analysis calculated with a matrix of 54 (soaking times) × 22 (texture features), shows that it was possible to distinguish an isolated group consisting of different soaking times at the same water temperature in each breakfast cereal flakes evaluated, corroborating that superficial liquid imbibition is important during the liquid absorption process when flakes are soaked. Furthermore, standardized FD could be related to RF in the period when samples tend to search for an equilibrium state.

TU-A-218-05: Evaluation of Image Registration Using Landmark Matching and Texture Analysis

Purpose: To compare demons deformable registration with rigid and affineregistration methods by measuring registration accuracy and image texture changes introduced by each algorithm. Methods: Eleven temporally sequential pairs of clinical thoracic CT scans demonstrating no abnormal pathology were collected retrospectively from different patients. Rigid, affine, and demons registration methods were applied to all scan pairs using an appropriate choice of registration parameters. 150 landmarks were automatically selected in each baseline scan, and a semi‐automated approach was used to identify corresponding landmarks in the respective deformed follow‐up scans. Eleven first‐order texture features were calculated in 32x32‐pixel regions of interest (ROIs) randomly placed in the baseline scans and at anatomically matched locations in the demons‐, rigid‐, and affine‐ registered follow‐up scans. For each ROI pair, feature value differences between the three registered follow‐up scans and the baseline scan were calculated. Results: The average per‐patient Euclidean distance between baseline scan landmarks and registered follow‐up scan landmarks ranged from 0.01–0.50 mm (overall mean: 0.18 mm), 1.6–6.8 mm (overall mean: 3.95 mm), and 2.06–7.91 mm (overall mean: 4.82 mm) for demons, affine, and rigid registration methods, respectively. Across all eleven features, the variances in feature value change for rigid and affine registration methods were at least an order of magnitude larger than the corresponding feature‐ value‐change variances for demons registration. Conclusions: Demons registration achieved more accurate spatial alignment between temporally sequential CT scans than rigid or affine registration methods. Furthermore, the variance in texture feature value changes between baseline and registered follow‐up scan ROIs was smaller for demons than for rigid or affine registration methods. These advantages of demons registration observed with “normal” thoracic CT scans indicate that future studies may incorporate demons to combine serial CT scans such that automated methods may distinguish registration artifacts from actual pathologic change.

Image analysis of changes in surface color of chocolate

Blooming or the migration of fat to the surface of chocolate results in color changes and development of non-uniform color patterns. These phenomena were assessed during storage of milk chocolate tablets (cycling temp. between 16 and 28 °C for 52 days) by a computer vision system and image analysis. Eight features were extracted from images ( L*, a* and b* values, whiteness index, chroma, hue, % bloom and energy of Fourier). Major changes occurred after day 36 of storage, coincidental with visual perception. Initially, white specks emerged on the brown background but were superseded by the development of a whitish color extending over most of the surface. L*, whiteness index, a* and chroma correlated well with values taken with a commercial colorimeter ( R 2 > 0.70). Changes in image texture (energy of Fourier) followed a similar trend as color changes. The sequential forward selection strategy allowed correct classification of 97.8% of samples into four classes with only five features. The computer vision system has the capability to quantify overall changes as well as particular features over the whole chocolate surface thus enabling customization and standardization for quality assessment.

Texture analysis of protein distribution images to find differences due to aging and superfusion.

Many pathologies are age-related, e.g., cardiovascular disease generally occurs in midlife and cancer later in life. This suggests that aging predisposes the body to pathology. Plasma protein spatial distribution images of rat mesentery extracellular matrix (ECM) show texture due to the ECM structures, and there is an age-related decrease in tissue protein that may be related to matrix structure changes. The objective of this study was to compare changes in protein image texture under two conditions: superfusion with normal saline solution and aging. The decrease in soluble protein concentration during superfusion is a washout process, while the mechanism for the age-related decrease in tissue protein is unknown. Therefore, effects of aging and superfusion on tissue protein image texture were compared. Spatial co-occurrence matrix and Fourier analysis techniques have been used for texture evaluation. Superfused images showed a more uniform protein texture. There were gradual age-related changes in image texture parameters. Entropy increased with age from 140 to 630 days, indicating that protein distribution became more disorganized. The results suggest that changes in protein image texture are due to age-related alterations in matrix structure because removing only protein by superfusion had opposite effects on texture parameters.

TEXTURE OF FOREST COMMUNITIES ON AERIAL PHOTOGRAPHS

The authors discuss a method by which the image characteristics of forest vegetation can be used to determine various valuational characteristics of forest stands through the combination of air photo interpretation and ground surveys at selected training sites. Construction of curves showing changes in image texture and tone occurring at different stages in the growth cycle of a pine forest community are used to estimate the age of a forest stand, and through known relationships between age and other stand characteristics incorporated into yield tables, to approximate such valuational characteristics as mean diameter, mean height, and stand volume. Translated from: Distantsionnyye issledovaniya rel'yefa Sibiri, A. L. Yanshin and V. N. Sharanov, eds. Novosibirsk, Nauka, 1985, pp. 73-78.

Adaptive filtering for reduction of speckle in ultrasonic pulse-echo images

Current medical ultrasonic scanning instrumentation permits the display of fine image detail (speckle) which does not transfer useful information but degrades the apparent low contrast resolution in the image. An adaptive two-dimensional filter has been developed which uses local features of image texture to recognize and maximally low-pass filter those parts of the image which correspond to fully developed speckle, while substantially preserving information associated with resolved-object structure. A first implementation of the filter is described which uses the ratio of the local variance and the local mean as the speckle recognition feature. Preliminary results of applying this form of display processing to medical ultrasound images are very encouraging; it appears that the visual perception of features such as small discrete structures, subtle fluctuations in mean echo level and changes in image texture may be enhanced relative to that for unprocessed images.

Quantitative Echocardiographic Image Texture: Normal Contraction-Related Variability

Myocardial tissue characterization using ultrasound is a growing area of investigation which attempts to evaluate the structure of the myocardium by analysis of ultrasound signals. Our laboratory has been exploring the use of texture analysis for the determination of myocardial tissue properties from two-dimensional echocardiographic images. In the present study, we tested the hypothesis that echocardiographic image texture varies with cardiac contraction in normal human subjects. In 17 subjects, we obtained long-and short-axis images at end diastole and end systole. Echo image texture was assessed using three classes of quantitative texture measures: run length, gray level difference, and busyness statistics. These statistics measure various attributes of image texture. We found significant contraction-related changes in image texture for the left ventricular posterior wall. This observation is important in that future applications of texture analysis to echocardiographic image data will require that texture be measured at a consistent point in the cardiac cycle. Moreover, it is possible that alteration in the normal variation of texture with cardiac contraction may be a sensitive indicator of abnormal myocardium.

The Effect of Change in Vegetation Cover and Erosion Patterns on Albedo and Texture of Landsat Images in a Semiarid Environment

Abstract This study examines the relationship between changes in vegetation cover and surface erosion in a semiarid environment and changes in albedo and texture estimates made from Landsat Multispectral Scanner digital images. Albedo emerges as the single most important indicator of change in vegetation cover, though the addition of texture measures assists in the distinction between surface classes that exhibit similar albedo. Texture measures appear to provide further information on the condition of surfaces, whereas albedo change indicates relative increase or decrease in vegetation amount. Analysis of high-frequency components of albedo variation indicates that directional and size biases in vegetation and erosion patterns are important in identifying changes in the distribution of vegetation amount and that these biases further affect image texture related to the development of erosion patterns. As expected, physical explanations of the relationship between changes in erosion patterns and temporal changes in image texture are not readily forthcoming.