Pixel Intensity Research Articles

A new convolution neural network model “KR-NET” for retinal fundus glaucoma classification

In recent years, deep learning is an emerging trend with potential applications in ophthalmology. Glaucoma is one ophthalmic disease where early detection is required to avoid vision loss. In the context of deep learning, convolution neural networks (CNN) are preferred for glaucoma classification because they can extract the highly discriminate features effectively from raw pixel intensities. In our approach, the region-of-interest (ROI) can be segmented from the fundus images using variable mode decomposition (VMD) by splitting the coefficients into 5 recurrence decays and upgrading the normal recurrence ranges. This approach will improve the possibility of identifying even poorly differentiated exudates. Later, a 26-layer CNN which involves six convolution layers, four pooling layers, and one fully connected layer that is designed and trained to extract distinctive features from the selective ROI and classified using the softmax layer. Data augmentation technique is employed in our model to enhance the size of dataset and the model is validated using 10-fold cross validation (CV) and 70:30 split ratio approach, and evaluated the performance metrics for different values of batch size, and initial learning rate. The proposed model is verified on a set of balanced and unbalanced public datasets (Drishti-GS1, RIM-ONE and ACRIMA) and the significant accuracy values of the results can be obtained as 90.32% for Drishti-GS1, 90.51% for RIM-ONE, and 96.70% for ACRIMA datasets. To verify the robustness of the model, the proposed model is also validated on two other datasets: (i) a private dataset, and (ii) a huge challenge dataset Refuge. The proposed model given satisfactory results when implemented on these two datasets and the significant accuracy values of the results can be obtained as 88.89% for the private dataset, and 89.17% for Refuge datasetThe obtained results and evaluated performance metrics show that our proposed model classifies the retinal fundus images effectively.

YONGʻINNI VIDEOTASVIRDA RANGLI FILTRLASH BILAN INTENSIVLIK OʻZGARISHI ASOSIDA ANIQLASH

The paper reviews achievements made in the field of video analytics and computer vision, which enable automatic detection of fires, based on video data. Various algorithms have been implemented in sought for effective fire detection methods using video. As one of these, a color-based fire detection algorithm is being described. However, using only one color model for fi re detection is an inefficient approach. The paper proposes a method for estimating temporal changes in pixel intensity, which is used to retrieve information about fires from fire-like objects in a video image. This method helps to calculate the average intensity value in a sequence of shots. A special software has been developed in the Python programming language using the OpenCV (Open Source Computer Vision Library) library, and the corresponding findings have been gained in view to demonstrate the effectiveness of the proposed method.

Use of Digital Methods to Optimize Visualization during Surgical Gonioscopy.

Purpose: The aim of this study was to evaluate the efficacy of digital visualization for enhancing the visualization of iridocorneal structures during surgical gonioscopy. Methods: This was a prospective, single-center study on a series of 26 cases of trabecular stent implantation performed by the same surgeon. Images were recorded during surgical gonioscopy, and before stent implantation, with standard colors and with the optimization of various settings, principally color saturation and temperature and the use of the cyan color filter. Subjective analyses were performed by two glaucoma surgeons, and objective contrast measurements were made on iridocorneal structure images. Results: The surgeons evaluating the images considered the optimized digital settings to produce enhanced tissue visibility for both trabecular meshwork pigmentation and Schlemm's canal in more than 65% of cases. The mean difference in the standard deviation of the pixel intensity values was 37.87 (±4.61) for the optimized filter images and 32.37 (±3.51) for the standard-color images (p < 0.001). The use of a cyan filter provided a good level of contrast for the visualization of trabecular meshwork pigmentation. Increasing the color temperature highlighted the red appearance of Schlemm's canal. Conclusions: We report here the utility of optimized digital settings including the cyan filter and a warmer color for enhancing the visualization of iridocorneal structures during surgical gonioscopy. These settings could be used in surgical practice to enhance the visualization of the trabecular meshwork and Schlemm's canal during minimally invasive glaucoma surgery.

Osteosarcopenia in the Spine Beyond Bone Mineral Density: Association Between Paraspinal Muscle Impairment and Advanced Glycation Endproducts.

Prospective cross-sectional study. To determine if an accumulation of advanced glycation endproducts (AGEs) is associated with impaired paraspinal muscle composition. Impaired bone integrity and muscle function are described as osteosarcopenia. Osteosarcopenia is associated with falls, fragility fractures, and reduced quality of life. Bone integrity is influenced by bone quantity (bone mineral density) and quality (microarchitecture and collagen). The accumulation of AGEs stiffens collagen fibers and increases bone fragility. The relationship between paraspinal muscle composition and bone collagen properties has not been evaluated. Intraoperative bone biopsies from the posterior superior iliac spine were obtained and evaluated with multiphoton microscopy for fluorescent AGE cross-link density (fAGEs). Preoperative magnetic resonance imaging measurements at level L4 included the musculus (m.) psoas and combined m. multifidus and m. erector spinae (posterior paraspinal musculature, PPM). Muscle segmentation on axial images (cross-sectional area, CSA) and calculation of a pixel intensity threshold method to differentiate muscle (functional cross-sectional area, fCSA) and intramuscular fat (FAT). Quantitative computed tomography was performed at the lumbar spine. Univariate and multivariable regression models were used to investigate associations between fAGEs and paraspinal musculature. One hundred seven prospectively enrolled patients (50.5% female, age 60.7y, BMI 28.9kg/m 2 ) were analyzed. In all, 41.1% and 15.0% of the patients demonstrated osteopenia and osteoporosis, respectively. Univariate linear regression analysis demonstrated a significant association between cortical fAGEs and CSA in the psoas (ρ=0.220, P =0.039) but not in the PPM. Trabecular fAGEs revealed no significant associations to PPM or psoas musculature. In the multivariable analysis, higher cortical fAGEs were associated with increased FAT (β=1.556; P =0.002) and CSA (β=1.305; P =0.005) in the PPM after adjusting for covariates. This is the first investigation demonstrating that an accumulation of nonenzymatic collagen cross-linking product fAGEs in cortical bone is associated with increased intramuscular fat in the lumbar paraspinal musculature.

Ocher deposit prospecting using object-based image analysis of WorldView-3 VNIR data: A case study in Hormuz Island, southern Iran

Mapping lithological units and conducting mineral exploration in a relatively short time and at a reduced cost, requires high-resolution satellite data and state-of-the-art image processing approaches and methods. In this regard, the current paper aims to test an integration of visible-near infrared imagery from WorldView-3 (WV-3) and object-based classification for mapping potential deposits of ocher in Hormuz Island, southern Iran. A combination of field observations, spectroscopy, microscopic mineralogy, and geochemical-based XRD and XRF analyses were conducted on the samples collected throughout the study area. The reflectance and absorption features of the ocher were extracted from spectroscopic measurements of samples from well-known ocher mines at the area, and were then convolved to the WV-3 bands. Results showed that the spectral characteristics of ocher are governed by iron oxides and clay minerals with a presence of distinct strong absorption and high reflectance features in the 510–625 nm and 630–745 nm wavelength regions, respectively. These features are complemented by molecular vibration processes of water O–H intramolecular stretching and H–O–H bending that generate absorption features in the 1440–1940 nm region. Additional absorption features in the 2210–2300 nm are most likely due to the Al-OH and CO3−2 vibrations. The absorptions centered at 480 nm, 540 nm, and 820 nm correspond to bands 2, 3, and 7 of the WV-3, respectively, whereas the high reflectance feature centered near 700 nm corresponds to band 6. These four bands, which were considered as index bands of ocher in this study, were used to assign the segmentation weights and to create the thresholds during image processing. Brightness, density, compactness, and homogeneity features were the primary factors for selecting the training areas in the index bands. The ocher-rich areas were enhanced by using a two-stepapproach of object-based image analysis (OBIA) and image classification, for suitable threshold selection. The information about the feature variables of the ocher within the image and lithological object hierarchy were obtained to evaluate the features of ocher deposits. Information extracted from the index bands provided an important description of the object features, including mean, standard deviation, minimum and maximum pixel values, hue, saturation, and intensity, while the training areas obtained information from the three known ocher mines. Considering the fixed numerical range of ocher mines as a reference, the fixed numerical range of general and specific features of ocher in index bands of WV-3 were achieved. The numerical ranges of pixels were used for creating threshold conditions when applying the “assign class” algorithm in bands 2, 3, and 7 are 815–975 nm, 930–1052 nm, and 1721–1904 nm, respectively. The presented OBIA approach shows a high potential with an overall accuracy of 88 % to discriminate deposits of ocher based on compatibility between ocher mines and identified ocher-bearing pixels.

Image-based phenotyping to estimate anthocyanin concentrations in lettuce.

Anthocyanins provide blue, red, and purple color to fruits, vegetables, and flowers. Due to their benefits for human health and aesthetic appeal, anthocyanin content in crops affects consumer preference. Rapid, low-cost, and non-destructive phenotyping of anthocyanins is not well developed. Here, we introduce the normalized difference anthocyanin index (NDAI), which is based on the optical properties of anthocyanins: high absorptance in the green and low absorptance in the red part of the spectrum. NDAI is determined as (Ired - Igreen)/(Ired + Igreen), where I is the pixel intensity, a measure of reflectance. To test NDAI, leaf discs of two red lettuce (Lactuca sativa) cultivars 'Rouxai' and 'Teodore' with wide range of anthocyanin concentrations were imaged using a multispectral imaging system and the red and green images were used to calculate NDAI. NDAI and other commonly used indices for anthocyanin quantification were evaluated by comparing to with the measured anthocyanin concentration (n = 50). Statistical results showed that NDAI has advantages over other indices in terms of prediction of anthocyanin concentrations. Canopy NDAI, obtained using multispectral canopy imaging, was correlated (n = 108, R2 = 0.73) with the anthocyanin concentrations of the top canopy layer, which is visible in the images. Comparison of canopy NDAI from multispectral images and RGB images acquired using a Linux-based microcomputer with color camera, showed similar results in the prediction of anthocyanin concentration. Thus, a low-cost microcomputer with a camera can be used to build an automated phenotyping system for anthocyanin content.

Three-dimensional radiographic features of craniometaphyseal dysplasia—a comparative CBCT study

PurposeCraniometaphyseal dysplasia (CMD) is a rare skeletal disorder that has progressive thickening and increased density of the craniofacial bones along with abnormal metaphyses of the long bones. Other features include a wide nasal bridge, paranasal bossing, hypertelorism, and an increase in the zygomatic width. We present a series of cases that showcase the three-dimensional radiographic features of this rare condition and compare it with an age and gender-matched controlled group using cone beam computed tomography (CBCT).ObjectiveTo evaluate the three-dimensional radiographic features of craniometaphyseal dysplasia (CMD).Materials and methodsRetrospective analysis of CBCT scans of 7 patients who were diagnosed with the rare condition craniometaphyseal dysplasia was evaluated. Radiographic features of the craniofacial bones, the paranasal sinuses prominently maxillary, and frontal and sphenoid sinuses were evaluated. Skull bones were also evaluated, and the size and shape of the sella turcica and external auditory meatus were measured. Retained primary teeth and impactions were evaluated using a panoramic reformatted image. The type of occlusion and buccolingual dimensions of jaw bones were also assessed. Age and gender-matched control samples were used to measure the same features for comparing CMD patients to healthy controls. The quality of normal and syndromic patients’ cortical and trabecular bone was determined by measuring pixel intensity values (PIV) generated by CBCT scans.ResultsCone beam CT images of patients with CMD were analyzed to evaluate cranial bones, their density, and any abnormalities associated with the sinuses and foramina. Patients with CMD had bones increased in size. A significant increase in the amount of bone formed was found in the inner table of the frontal and occipital bones. All seven patients with CMD had smaller foramina due to the deposition of sclerosed bone in the foramina of the skull base. The paranasal sinuses, prominently maxillary and frontal and sphenoid sinuses, were smaller than the age and gender-matched controls. The buccolingual dimensions of jawbones were increased. The maxillary and mandibular arch relationship ranged from class II to class III. The mean nasal bridge measurement for the CMD patients was 26.77 mm, while in the controls, the mean nasal bridge measurement was 19.48 mm. The mean measurements of the right and left orbits of CMD patients were 30.6 mm and 31.07 mm respectively, and the mean measurements of the right and left orbits of controls were 32.45 mm and 32.04 mm. Pixel intensity values (PIVs) representing density ranged between 100 and 1000 PIVs for cortical bone and between − 60 and 258 for trabecular bone suggesting a densely sclerotic texture, while in the control group patients, the PIVs for cortical bone were > 1000 and 150–300 for trabecular bone.ConclusionCMD patients had significantly larger bone widths, a lower density of the bone, and smaller sinuses compared to the control group.

Sparse-View Cone-Beam CT Reconstruction by Bar-by-Bar Neural FDK Algorithm

ABSTRACT The Feldkamp, Davis and Kress algorithm is a computationally efficient reconstruction method for three-dimensional cone-beam computed tomography. However, it suffers from severe artefacts when the number of projections is insufficient. Although recent deep learning–based methods have succeeded in reconstructing such sparse-view projections, it is still challenging to reconstruct a large 3D volume efficiently because of heavy memory consumption and difficulty in obtaining sufficient training data. Therefore, we propose a deep learning method to overcome these drawbacks. Our method consecutively reconstructs short bars in 3D CT volume using the intensities of pixels on the moving trajectory projected on the detector of these bars. Then, we feed such pixel intensities into a neural network and train it to simulate the filtering and back-projection processes of the FDK algorithm. Since the reconstruction volume is separated into bars, the neural network can be used with only a small amount of memory. Furthermore, the network can be trained sufficiently with only a few training samples because plenty of bar data can be extracted even from a single CT image. We experimentally demonstrate that our approach works efficiently for both simulated and actual sparse-view CBCT data using training data extracted from only a single CT image.

Accurate demarcation of a biased nucleus from H&E-stained follicular lymphoma tissues samples

ABSTRACT In recent days, automated demarcation of biased nuclei of follicular lymphoma has become a standard framework in the pipeline of quantitative histopathology. It has received substantial consideration due to subjective variability between different oncologists. This difference can occasionally result in erroneous conclusions, distinct prognostic reports, and inconsistent treatment. This paper provides additional input to an oncologist to ease the prognosis process. This approach defines a local criterion fitting function in neighbourhood of each point based on image intensity. An assumption is pixel intensity will remain constant next to the point. Integration of these local neighbourhood centres leads us to define the global criterion of image segmentation. Segmentation accuracy is evaluated using region-based measures and the optimal segmentation accuracy of 98.6% is achieved using the DICE coefficient. By using locally formulated energy, execution time is also reduced in comparison to the contour algorithm. This technique is independent of the initialization.

Two-dimensional horizontal visibility graph analysis of human brain aging on gray matter

Characterizing the trajectory of the healthy aging brain and exploring age-related structural changes in the brain can help deepen our understanding of the mechanism of brain aging. Currently, most structural magnetic resonance imaging literature explores brain aging merely from the perspective of morphological features, which cannot fully utilize the gray-scale values containing important intrinsic information about brain structure. In this study, we propose the construction of two-dimensional horizontal visibility graphs based on the pixel intensity values of the gray matter slices directly. Normalized network structure entropy (NNSE) is then introduced to quantify the overall heterogeneities of these graphs. The results demonstrate a decrease in the NNSEs of gray matter with age. Compared with the middle-aged and the elderly, the larger values of the NNSE in the younger group may indicate more homogeneous network structures, smaller differences in importance between nodes and thus a more powerful ability to tolerate intrusion. In addition, the hub nodes of different adult age groups are primarily located in the precuneus, cingulate gyrus, superior temporal gyrus, inferior temporal gyrus, parahippocampal gyrus, insula, precentral gyrus and postcentral gyrus. Our study can provide a new perspective for understanding and exploring the structural mechanism of brain aging.

Textural Features of Mouse Glioma Models Measured by Dynamic Contrast-Enhanced MR Images with 3D Isotropic Resolution.

This paper investigates the effect of anisotropic resolution on the image textural features of pharmacokinetic (PK) parameters of a murine glioma model using dynamic contrast-enhanced (DCE) MR images acquired with an isotropic resolution at 7T with pre-contrast T1 mapping. The PK parameter maps of whole tumors at isotropic resolution were generated using the two-compartment exchange model combined with the three-site-two-exchange model. The textural features of these isotropic images were compared with those of simulated, thick-slice, anisotropic images to assess the influence of anisotropic voxel resolution on the textural features of tumors. The isotropic images and parameter maps captured distributions of high pixel intensity that were absent in the corresponding anisotropic images with thick slices. A significant difference was observed in 33% of the histogram and textural features extracted from anisotropic images and parameter maps, compared to those extracted from corresponding isotropic images. Anisotropic images in different orthogonal orientations demonstrated 42.1% of the histogram and textural features to be significantly different from those of isotropic images. This study demonstrates that the anisotropy of voxel resolution needs to be carefully considered when comparing the textual features of tumor PK parameters and contrast-enhanced images.

IMC-Denoise: a content aware denoising pipeline to enhance Imaging Mass Cytometry

Imaging Mass Cytometry (IMC) is an emerging multiplexed imaging technology for analyzing complex microenvironments using more than 40 molecularly-specific channels. However, this modality has unique data processing requirements, particularly for patient tissue specimens where signal-to-noise ratios for markers can be low, despite optimization, and pixel intensity artifacts can deteriorate image quality and downstream analysis. Here we demonstrate an automated content-aware pipeline, IMC-Denoise, to restore IMC images deploying a differential intensity map-based restoration (DIMR) algorithm for removing hot pixels and a self-supervised deep learning algorithm for shot noise image filtering (DeepSNiF). IMC-Denoise outperforms existing methods for adaptive hot pixel and background noise removal, with significant image quality improvement in modeled data and datasets from multiple pathologies. This includes in technically challenging human bone marrow; we achieve noise level reduction of 87% for a 5.6-fold higher contrast-to-noise ratio, and more accurate background noise removal with approximately 2 × improved F1 score. Our approach enhances manual gating and automated phenotyping with cell-scale downstream analyses. Verified by manual annotations, spatial and density analysis for targeted cell groups reveal subtle but significant differences of cell populations in diseased bone marrow. We anticipate that IMC-Denoise will provide similar benefits across mass cytometric applications to more deeply characterize complex tissue microenvironments.

Automated Quantification of Wind Turbine Blade Leading Edge Erosion from Field Images

Wind turbine blade leading edge erosion is a major source of power production loss and early detection benefits optimization of repair strategies. Two machine learning (ML) models are developed and evaluated for automated quantification of the areal extent, morphology and nature (deep, shallow) of damage from field images. The supervised ML model employs convolutional neural networks (CNN) and learns features (specific types of damage) present in an annotated set of training images. The unsupervised approach aggregates pixel intensity thresholding with calculation of pixel-by-pixel shadow ratio (PTS) to independently identify features within images. The models are developed and tested using a dataset of 140 field images. The images sample across a range of blade orientation, aspect ratio, lighting and resolution. Each model (CNN v PTS) is applied to quantify the percent area of the visible blade that is damaged and classifies the damage into deep or shallow using only the images as input. Both models successfully identify approximately 65% of total damage area in the independent images, and both perform better at quantifying deep damage. The CNN is more successful at identifying shallow damage and exhibits better performance when applied to the images after they are preprocessed to a common blade orientation.

Determination of Munsell Soil Colour Using Smartphones.

Soil colour is one of the most important factors in agriculture for monitoring soil health and determining its properties. For this purpose, Munsell soil colour charts are widely used by archaeologists, scientists, and farmers. The process of determining soil colour from the chart is subjective and error-prone. In this study, we used popular smartphones to capture soil colours from images in the Munsell Soil Colour Book (MSCB) to determine the colour digitally. These captured soil colours are then compared with the true colour determined using a commonly used sensor (Nix Pro-2). We have observed that there are colour reading discrepancies between smartphone and Nix Pro-provided readings. To address this issue, we investigated different colour models and finally introduced a colour-intensity relationship between the images captured by Nix Pro and smartphones by exploring different distance functions. Thus, the aim of this study is to determine the Munsell soil colour accurately from the MSCB by adjusting the pixel intensity of the smartphone-captured images. Without any adjustment when the accuracy of individual Munsell soil colour determination is only 9% for the top 5 predictions, the accuracy of the proposed method is 74%, which is significant.

Image Registration using the Rigid Group

Image registration is the process of approximate matching of the source image to the target so that they resemble each other. In this study, two-dimensional image registration is presented using the rigid group. This group is a finite dimensional group (four-dimensional in this case) under composition. The dimensions of the rigid group are scaling, rotation, and translations along the axes. In this paper, an algorithm for the construction of rigid transformation is presented using the discretized objective function. This objective function is based on SSD (sum of the squares of the distances between the pixels intensities) and calculates the discrepancy between the images. The coarse search and the gradient descent approaches have been used for the optimization. The proposed algorithm is implemented on variety of images. The numerical examples illustrate the ability of the proposed algorithm.

Performance Analysis of Graph theory-based Contrast Limited Adaptive Histogram Equalization for Image Enhancement

Nowadays, image enhancement has become a major area of research because of the development of applications that are based on vision.Several digital image processing systems employ such image enhancement strategies with the help of graph theory. As the visibility level in low contrast image features is very less,several image enhancement strategies have been introduced with spatial transformations to enhance image qualityfor improved visualization. Nowadays, image processing plays an important role in the analysis of a patient’s health status and has become extremely popular in medical areas for a wide range of clinical assessments. Generally, medical images contain several complex areas and thereby,few pre-processing approaches are applied to reduce the challenges that occur during different phases of the CAD system. Furthermore, because of external noise interferences, poor illuminating settings as well as other imaging device limitations, the clinical diagnosis becomes a challenging process and medical images do not provide important information for precise categorization. Medical images are available in a variety of applications such as computed tomography, Magnetic Resonance Imaging (MRI), mammography, chest X-ray (CXR), and many more. Only the pixel intensity variations between different areas as well as object boundary information are essential for categorization and must be enhanced simultaneously. As a result, the rate of classification in medical images and intensity are increased so that every object during the analysis can be easily identified. The main goal of any image enhancement process is to enhance the quality of the image by reducing noise and on other hand by using three different algorithms such as Luminance Modulation (LM), Gradient Modulation (GM), and Dynamic Histogram Equalization (DHE). These three algorithms are designed with the help of graph theory for effective preservation of edges, losses, and efficient smoothing and to preserve the basic information without any modifications. Image restoration is also referred to as image enhancement and it is concerned with the precise assessment of real images. Generally, the degradation process is not included in many of the image-enhancement approaches that are already existing. Furthermore, with the application of enhancement techniques, the degradation process for medical images results in some significant performance loss. Several techniques have been proposed and the technique which is examined in this research is image enhancement that is based on histogram which mainly concentrates on equalizing the histogram of values. Histogram Equalization (HE) possesses a few basic properties such as altering spatial patterns as well as intensity which in turn results in significant challenges in medical imaging. As a result,Contrast Limited Adaptive Histogram Equalization (CLAHE) is proposed in this work as a feasible approach for medical image analysis to address the problem. The suggested research work demonstrates that the intensity limiting image enhancement with histogram equalization detects the irregularities in dense mammograms with enhanced quality.

Changes in psoas and posterior paraspinal muscle morphology after standalone lateral lumbar interbody fusion: a quantitative MRI-based analysis.

Standalone lateral lumbar interbody fusion (SA-LLIF) without posterior instrumentation can be an alternative to 360° fusion in selected cases. This study aimed to investigate quantitative changes in psoas and paraspinal muscle morphology that occur on index levels after SA-LLIF. Patients undergoing single- or multi-level SA-LLIF at L2/3 to L4/5 who had preoperative and postoperative lumbar MRI scans, the latter performed between 3 and 18months after surgery for any reason, were retrospectively included. Muscle measurements were performed of the psoas and posterior paraspinal muscles (PPM; erector spinae and multifidus) on index levels using manual segmentation and an automated pixel intensity threshold method to differentiate muscle from fat signal. Changes in the total cross-sectional area (TCSA), the functional cross-sectional area (FCSA), and the percentage of fat infiltration (FI) of these muscles were assessed. A total of 67 patients (55.2% female, age 64.3 ± 10.6years, BMI 26.9 ± 5.0kg/m2) with 125 operated levels were included. Follow-up MRI scans were performed after an average of 8.7 ± 4.6months, primarily for low back pain. Psoas muscle parameters did not change significantly, irrespective of the approach side. Among PPM parameters, the mean TCSA at L4/5 (+ 4.8 ± 12.4%; p = 0.013), and mean FI at L3/4 (+ 3.1 ± 6.5%; p = 0.002) and L4/5 (+ 3.0 ± 7.0%; p = 0.002) significantly increased. Our study demonstrated that SA-LLIF did not alter psoas muscle morphology, underlining its minimally invasive nature. However, FI of PPM significantly increased over time despite the lack of direct tissue damage to posterior structures, suggesting a pain-mediated response and/or the result of segmental immobilization.

Multi-mode fiber-based speckle contrast optical spectroscopy: analysis of speckle statistics.

Speckle contrast optical spectroscopy/tomography (SCOS/T) provides a real-time, non-invasive, and cost-efficient optical imaging approach to mapping of cerebral blood flow. By measuring many speckles (n>>10), SCOS/T has an increased signal-to-noise ratio relative to diffuse correlation spectroscopy, which measures one or a few speckles. However, the current free-space SCOS/T designs are not ideal for large field-of-view imaging in humans because the curved head contour cannot be readily imaged with a single flat sensor and hair obstructs optical access. Herein, we evaluate the feasibility of using cost-efficient multi-mode fiber (MMF) bundles for use in SCOS/T systems. One challenge with speckle contrast measurements is the potential for confounding noise sources (e.g., shot noise, readout noise) which contribute to the standard deviation measure and corrupt the speckle contrast measure that is central to the SCOS/T systems. However, for true speckle measurements, the histogram of pixel intensities from light interference follows a non-Gaussian distribution, specifically a gamma distribution with non-zero skew, whereas most noise sources have pixel intensity distributions that are Gaussian. By evaluating speckle data from static and dynamic targets imaged through an MMF, we use histograms and statistical analysis of pixel histograms to evaluate whether the statistical properties of the speckles are retained. We show that flow-based speckle can be distinguished from static speckle and from sources of system noise through measures of skew in the pixel intensity histograms. Finally, we illustrate in humans that MMF bundles relay blood flow information.

CT-Based Automatic Spine Segmentation Using Patch-Based Deep Learning

CT vertebral segmentation plays an essential role in various clinical applications, such as computer-assisted surgical interventions, assessment of spinal abnormalities, and vertebral compression fractures. Automatic CT vertebral segmentation is challenging due to the overlapping shadows of thoracoabdominal structures such as the lungs, bony structures such as the ribs, and other issues such as ambiguous object borders, complicated spine architecture, patient variability, and fluctuations in image contrast. Deep learning is an emerging technique for disease diagnosis in the medical field. This study proposes a patch-based deep learning approach to extract the discriminative features from unlabeled data using a stacked sparse autoencoder (SSAE). 2D slices from a CT volume are divided into overlapping patches fed into the model for training. A random under sampling (RUS)-module is applied to balance the training data by selecting a subset of the majority class. SSAE uses pixel intensities alone to learn high-level features to recognize distinctive features from image patches. Each image is subjected to a sliding window operation to express image patches using autoencoder high-level features, which are then fed into a sigmoid layer to classify whether each patch is a vertebra or not. We validate our approach on three diverse publicly available datasets: VerSe, CSI-Seg, and the Lumbar CT dataset. Our proposed method outperformed other models after configuration optimization by achieving 89.9% in precision, 90.2% in recall, 98.9% in accuracy, 90.4% in F-score, 82.6% in intersection over union (IoU), and 90.2% in Dice coefficient (DC). The results of this study demonstrate that our model’s performance consistency using a variety of validation strategies is flexible, fast, and generalizable, making it suited for clinical application.

A novel automated deep learning approach for Alzheimer's disease classification

Alzheimer's disease is a degenerative brain illness, incurable and progressive. Globally for every two seconds, someone is affected by Alzheimer's disease. Alzheimer's disease in the elderly is difficult to diagnose due to the complexity of the brain structure. Its pixel intensity is similar and systematic distinction is necessary. Deep learning has inspired a lot of interest in recent years in tackling challenges in a variety of fields, including medical imaging. One of the drawbacks of deep learning approach is the inability to detect changes in functional connectivity in MCI (mild cognitive impairment) patients' functional brain networks. In this paper, we utilize deep features extracted from two pre-trained deep learning models to tackle this issue. The proposed models DenseNet121 and MobileNetV2 is used to perform the task of Alzheimer's disease multi-class classification. In this method, initially we increased 70 % of dataset and generated images by using CycleGAN (generative adversarial networks). We achieved 98.82% of accuracy with proposed models. It gives best results compared to existing models.