Magnetic Resonance Elastography and Computational Modeling Identify Heterogeneous Lung Biomechanical Properties during Cystic Fibrosis

The lung is a dynamic mechanical organ and several pulmonary disorders are characterized by heterogeneous changes in the lung's local mechanical properties (i.e. stiffness). These alterations lead to abnormal lung tissue deformation (i.e. strain) which have been shown to promote disease progression. Although heterogenous mechanical properties may be important biomarkers of disease, there is currently no non-invasive way to measure these properties for clinical diagnostic purposes. In this study, we use a magnetic resonance elastography technique to measure heterogenous distributions of the lung's shear stiffness in healthy adults and in people with Cystic Fibrosis. Additionally, computational finite element models which directly incorporate the measured heterogenous mechanical properties were developed to assess the effects on lung tissue deformation. Results indicate that consolidated lung regions in people with Cystic Fibrosis exhibited increased shear stiffness and reduced spatial heterogeneity compared to surrounding non-consolidated regions. Accounting for heterogenous lung stiffness in healthy adults did not change the globally averaged strain magnitude obtained in computational models. However, computational models that used heterogenous stiffness measurements predicted significantly more variability in local strain and higher spatial strain gradients. Finally, computational models predicted lower strain variability and spatial strain gradients in consolidated lung regions compared to non-consolidated regions. These results indicate that spatial variability in shear stiffness alters local strain and strain gradient magnitudes in people with Cystic Fibrosis. This imaged-based modeling technique therefore represents a clinically viable way to non-invasively assess lung mechanics during both health and disease.

Near-real-time Mueller polarimetric image processing for neurosurgical intervention

PURPOSE

Wide-field imaging Mueller polarimetry is a revolutionary, label-free, and non-invasive modality for computer-aided intervention; in neurosurgery, it aims to provide visual feedback of white matter fibre bundle orientation from derived parameters. Conventionally, robust polarimetric parameters are estimated after averaging multiple measurements of intensity for each pair of probing and detected polarised light. Long multi-shot averaging, however, is not compatible with real-time in vivo imaging, and the current performance of polarimetric data processing hinders the translation to clinical practice.

METHODS

A learning-based denoising framework is tailored for fast, single-shot, noisy acquisitions of polarimetric intensities. Also, performance-optimised image processing tools are devised for the derivation of clinically relevant parameters. The combination recovers accurate polarimetric parameters from fast acquisitions with near-real-time performance, under the assumption of pseudo-Gaussian polarimetric acquisition noise.

RESULTS

The denoising framework is trained, validated, and tested on experimental data comprising tumour-free and diseased human brain samples in different conditions. Accuracy and image quality indices showed significant ( p < 0.05 ) improvements on testing data for a fast single-pass denoising versus the state-of-the-art and high polarimetric image quality standards. The computational time is reported for the end-to-end processing.

CONCLUSION

The end-to-end image processing achieved real-time performance for a localised field of view ( ≈ 6.5 mm 2 ). The denoised polarimetric intensities produced visibly clear directional patterns of neuronal fibre tracts in line with reference polarimetric image quality standards; directional disruption was kept in case of neoplastic lesions. The presented advances pave the way towards feasible oncological neurosurgical translations of novel, label-free, interventional feedback.

Live-cell imaging powered by computation

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preserving cell viability. Computational methods can help to address this challenge and are now shifting the boundaries of what is possible to capture in living systems. In this Review, we discuss these computational methods focusing on artificial intelligence-based approaches that can be layered on top of commonly used existing microscopies as well as hybrid methods that integrate computation and microscope hardware. We specifically discuss how computational approaches can improve the signal-to-noise ratio, spatial resolution, temporal resolution and multi-colour capacity of live-cell imaging.

Automatic enhancement preprocessing for segmentation of low quality cell images

We present a novel automatic preprocessing and ensemble learning technique for the segmentation of low-quality cell images. Capturing cells subjected to intense light is challenging due to their vulnerability to light-induced cell death. Consequently, microscopic cell images tend to be of low quality and it causes low accuracy for semantic segmentation. This problem can not be satisfactorily solved by classical image preprocessing methods. Therefore, we propose a novel approach of automatic enhancement preprocessing (AEP), which translates an input image into images that are easy to recognize by deep learning. AEP is composed of two deep neural networks, and the penultimate feature maps of the first network are employed as filters to translate an input image with low quality into images that are easily classified by deep learning. Additionally, we propose an automatic weighted ensemble learning (AWEL), which combines the multiple segmentation results. Since the second network predicts segmentation results corresponding to each translated input image, multiple segmentation results can be aggregated by automatically determining suitable weights. Experiments on two types of cell image segmentation confirmed that AEP can translate low-quality cell images into images that are easy to segment and that segmentation accuracy improves using AWEL.

ML-DSTnet: A Novel Hybrid Model for Breast Cancer Diagnosis Improvement Based on Image Processing Using Machine Learning and Dempster-Shafer Theory

Medical intelligence detection systems have changed with the help of artificial intelligence and have also faced challenges. Breast cancer diagnosis and classification are part of this medical intelligence system. Early detection can lead to an increase in treatment options. On the other hand, uncertainty is a case that has always been with the decision-maker. The system's parameters cannot be accurately estimated, and the wrong decision is made. To solve this problem, we have proposed a method in this article that reduces the ignorance of the problem with the help of Dempster-Shafer theory so that we can make a better decision. This research on the MIAS dataset, based on image processing machine learning and Dempster-Shafer mathematical theory, tries to improve the diagnosis and classification of benign, malignant masses. We first determine the results of the diagnosis of mass type with MLP by using the texture feature and CNN. We combine the results of the two classifications with Dempster-Shafer theory and improve its accuracy. The obtained results show that the proposed approach has better performance than others based on evaluation criteria such as accuracy of 99.10%, sensitivity of 98.4%, and specificity of 100%.

Rectangular Amplitude Mask-Based Auto-Focus Method with a Large Range and High Precision for a Micro-LED Wafer Defects Detection System

Auto-focus technology plays an important role in the Micro-LED wafer defects detection system. How to accurately measure the defocus amount and the defocus direction of the Micro-LED wafer sample in a large linear range is one of the keys to realizing wafer defects detection. In this paper, a large range and high-precision auto-focus method based on a rectangular amplitude mask is proposed. A rectangular amplitude mask without a long edge is used to modulate the shape of the incident laser beams so that the spot shape distribution of the reflected laser beam on the sensor changes with the defocus amount of the wafer sample. By calculating the shape of the light spots, the defocus amount and the defocus direction can be obtained at the same time. The experimental results show that under the 20× microscopy objective, the linear range of the auto-focus system is 480 μm and the accuracy can reach 1 μm. It can be seen that the automatic focusing method proposed in this paper has the advantages of large linear range, high accuracy, and compact structure, which can meet the requirements of the Micro-LED wafer defects detection equipment.

Quantification of Large Transmural Biopsies Reveals Heterogeneity in Innervation Patterns in Chronic Myocardial Infarction

BACKGROUND

Abnormal cardiac innervation plays an important role in arrhythmogenicity after myocardial infarction (MI). Data regarding reperfusion models and innervation abnormalities in the medium to long term after MI are sparse. Histologic quantification of the small-sized cardiac nerves is challenging, and transmural analysis has not been performed.

OBJECTIVES

This study sought to assess cardiac innervation patterns in transmural biopsy sections in a porcine reperfusion model of MI (MI-R) using a novel method for nerve quantification.

METHODS

Transmural biopsy sections from 4 swine (n = 83) at 3 months after MI-R and 3 controls (n = 38) were stained with picrosirius red (fibrosis) and beta-III-tubulin (autonomic nerves). Biopsy sections were classified as infarct core, border zone, or remote zone. Each biopsy section was analyzed with a custom software pipeline, allowing calculation of nerve density and classification into innervation types at the 1 × 1-mm resolution level. Relocation of the classified squares to the original biopsy position enabled transmural quantification and innervation heterogeneity assessment.

RESULTS

Coexisting hyperinnervation, hypoinnervation, and denervation were present in all transmural MI-R biopsy sections. The innervation heterogeneity was greatest in the infarct core (median: 0.14; IQR: 0.12-0.15), followed by the border zone (median: 0.05; IQR: 0.04-0.07; P = 0.02) and remote zone (median: 0.02; IQR: 0.02-0.03; P < 0.0001). Only in the border zone was a positive linear relation between fibrosis and innervation heterogeneity observed (R = 0.79; P < 0.0001).

CONCLUSIONS

This novel method allows quantification of nerve density and heterogeneity in large transmural biopsy sections. In the chronic phase after MI-R, alternating innervation patterns were identified within the same biopsy section. Persistent innervation heterogeneity, in particular in the border zone biopsy sections, may contribute to late arrhythmogenicity.

Reconfigurable coaxial single-photon LIDAR based on the SPAD array

The single-photon avalanche diode (SPAD) array with time-to-digital converter (TDC) circuits on each pixel is an excellent candidate detector for imaging LIDAR systems. However, the low fill-factor of the SPAD array does not allow for efficient use of laser energy when directly adopted in a LIDAR system. Here, we design a reconfigurable coaxial single-photon LIDAR based on the SPAD array and diffractive optical elements (DOEs). We use the DOE and beam expander to shape the laser beam into a laser dot matrix. The total divergence angle of the DOE spot beam is strictly matched to the total field of view (FOV) angle of the SPAD array. Meanwhile, each focused beamlet is individually matched to every active area of the SPAD array detector, which increases the use of output energy about 100 times compared to the diffusion illumination system. Besides, the system uses the active area as the minimum pixel and can support sub-pixel scanning, resulting in higher resolution images. Through this coaxial structure, two different telescope systems after transceiver switching can be reconfigured for imaging targets at different distances. Based on our single-photon LIDAR system, we achieved 3D imaging of targets at 100 m and 180 m using two different telescope configurations.

Deep learning techniques and mathematical modeling allow 3D analysis of mitotic spindle dynamics

Time-lapse microscopy movies have transformed the study of subcellular dynamics. However, manual analysis of movies can introduce bias and variability, obscuring important insights. While automation can overcome such limitations, spatial and temporal discontinuities in time-lapse movies render methods such as 3D object segmentation and tracking difficult. Here, we present SpinX, a framework for reconstructing gaps between successive image frames by combining deep learning and mathematical object modeling. By incorporating expert feedback through selective annotations, SpinX identifies subcellular structures, despite confounding neighbor-cell information, non-uniform illumination, and variable fluorophore marker intensities. The automation and continuity introduced here allows the precise 3D tracking and analysis of spindle movements with respect to the cell cortex for the first time. We demonstrate the utility of SpinX using distinct spindle markers, cell lines, microscopes, and drug treatments. In summary, SpinX provides an exciting opportunity to study spindle dynamics in a sophisticated way, creating a framework for step changes in studies using time-lapse microscopy.

Mammalian Cell-Growth Monitoring Based on an Impedimetric Sensor and Image Processing within a Microfluidic Platform

In recent years, advancements in microfluidic and sensor technologies have led to the development of new methods for monitoring cell growth both in macro- and micro-systems. In this paper, a microfluidic (MF) platform with a microbioreactor and integrated impedimetric sensor is proposed for cell growth monitoring during the cell cultivation process in a scaled-down simulator. The impedimetric sensor with an interdigitated electrode (IDE) design was realized with inkjet printing and integrated into the custom-made MF platform, i.e., the scaled-down simulator. The proposed method, which was integrated into a simple and rapid fabrication MF system, presents an excellent candidate for the scaled-down analyses of cell growths that can be of use in, e.g., optimization of the cultivated meat bioprocess. When applied to MRC-5 cells as a model of adherent mammalian cells, the proposed sensor was able to precisely detect all phases of cell growth (the lag, exponential, stationary, and dying phases) during a 96-h cultivation period with limited available nutrients. By combining the impedimetric approach with image processing, the platform enables the real-time monitoring of biomasses and advanced control of cell growth progress in microbioreactors and scaled-down simulator systems.

Growth origin of large-scale fiberform nanostructures in He-W co-deposition environment

When tungsten (W) is deposited with helium (He) plasma (He-W co-deposition) on W surface, enhanced growth of fiberform nanostructure (fuzz) occurs, and sometimes it grows into large-scale fuzzy nanostructures (LFNs) thicker than 0.1 mm. In this study, different numbers of mesh opening (apertures) and W plates with nanotendril bundles (NTBs), which are tens of micrometers high nanofiber bundles, were used to investigate the condition for the origin of the LFN growth. It was found that the larger the mesh opening, the larger the area where LFNs are formed and the faster the formation tends to be. On NTB samples, it was found that NTBs grew significantly when exposed to He plasma with W deposition, especially when the size of the NTB reached [Formula: see text] mm. The concentration of the He flux due to the distortion of the shape of the ion sheath is proposed as one of the reasons to explain the experimental results.

Magnetic Resonance Elastography (MRE) of Bleomycin-Induced Pulmonary Fibrosis in an Animal Model

BACKGROUND

Idiopathic pulmonary fibrosis is responsible for 40,000 deaths annually in the United States. A hallmark of idiopathic pulmonary fibrosis is elevated collagen deposition, which alters lung stiffness. Clinically relevant ways to measure changes in lung stiffness during pulmonary fibrosis are not available, and new noninvasive imaging methods are needed to measure changes in lung mechanical properties.

OBJECTIVES

Magnetic resonance elastography (MRE) is an in vivo magnetic resonance imaging technique proven to detect changes in shear stiffness in different organs. This study used MRE, histology, and bronchoalveolar lavage (BAL) to study changes in the mechanical and structural properties of the lungs after bleomycin-induced pulmonary fibrosis in pigs.

MATERIALS AND METHODS

Pulmonary fibrosis was induced in 9 Yorkshire pigs by intratracheal instillation of 2 doses of bleomycin into the right lung only. Magnetic resonance elastography scans were performed at baseline and week 4 and week 8 postsurgery in a 1.5 T magnetic resonance imaging scanner using a spin-echo echo planar imaging sequence to measure changes in lung shear stiffness. At the time of each scan, a BAL was performed. After the final scan, whole lung tissue was removed and analyzed for histological changes.

RESULTS

Mean MRE-derived stiffness measurements at baseline, week 4, and week 8 for the control (left) lungs were 1.02 ± 0.27 kPa, 0.86 ± 0.29 kPa, and 0.68 ± 0.20 kPa, respectively. The ratio of the shear stiffness in the injured (right) lung to the uninjured control (left) lung at baseline, week 4, and week 8 was 0.98 ± 0.23, 1.52 ± 0.41, and 1.64 ± 0.40, respectively. High-dose animals showed increased protein in BAL fluid, elevated inflammation observed by the presence of patchy filtrates, and enhanced collagen and α-smooth muscle actin staining on histological sections. Low-dose animals and the control (left) lungs of high-dose animals did not show significant histopathological changes.

CONCLUSION

This study demonstrated that MRE can be used to detect changes in lung stiffness in pigs after bleomycin challenge.

MLF-IOSC: Multi-Level Fusion Network With Independent Operation Search Cell for Low-Dose CT Denoising

Computed tomography (CT) is widely used in clinical medicine, and low-dose CT (LDCT) has become popular to reduce potential patient harm during CT acquisition. However, LDCT aggravates the problem of noise and artifacts in CT images, increasing diagnosis difficulty. Through deep learning, denoising CT images by artificial neural network has aroused great interest for medical imaging and has been hugely successful. We propose a framework to achieve excellent LDCT noise reduction using independent operation search cells, inspired by neural architecture search, and introduce the Laplacian to further improve image quality. Employing patch-based training, the proposed method can effectively eliminate CT image noise while retaining the original structures and details, hence significantly improving diagnosis efficiency and promoting LDCT clinical applications.

Fast Guided Median Filter

Faster computation of a weighted median (WM) filter is impeded by the construction of a weighted histogram for every local window of data. Since the calculated weights vary for each local window, it is difficult, using a sliding window approach, to construct the weighted histogram efficiently. In this paper, we propose a novel WM filter that overcomes the difficulty of histogram construction. Our proposed method achieves real-time processing for higher resolution images and can be applied to multidimensional, multichannel, and high precision data. The weight kernel used in our WM filter is the pointwise guided filter, which is derived from the guided filter. The use of kernels based on the guided filter avoids gradient reversal artifacts and shows a higher denoising performance than the Gaussian kernel based on the color/intensity distance. The core idea of the proposed method is a formulation that allows the use of histogram updates with a sliding window approach to find the weighted median. For high precision data we propose an algorithm based on a linked list that can reduce the memory requirements of storing histograms and the computational cost of updating them. We present implementations of the proposed method that are suitable for both CPU and GPU. Experimental results show that the proposed method indeed realizes faster computation than conventional WM filters and is capable of filtering multidimensional, multichannel, and high precision data. This is an approach which is difficult to achieve with conventional methods.

Serotonin distinctly controls behavioral states in restrained and freely moving Drosophila

When trapped in a physical restraint, animals must select an escape strategy to increase their chances of survival. After falling into an inescapable trap, they react with stereotypical behaviors that differ from those displayed in escapable situations. Such behaviors involve either a wriggling response to unlock the trap or feigning death to fend off a predator attack. The neural mechanisms that regulate animal behaviors have been well characterized for escapable situations but not for inescapable traps. We report that restrained vinegar flies exhibit alternating flailing and immobility to free themselves from the trap. We used optogenetics and intersectional genetic approaches to show that, while broader serotonin activation promotes immobility, serotonergic cells in the ventral nerve cord (VNC) regulate immobility states majorly via 5-HT7 receptors. Restrained and freely moving locomotor states are controlled by distinct mechanisms. Taken together, our study has identified serotonergic switches of the VNC that promote environment-specific adaptive behaviors.

Differential analysis of negative geotaxis climbing trajectories in Drosophila under different conditions

The decline of Drosophila climbing behavior is one of the common phenomena of Drosophila aging. The so-called negative geotaxis refers to the natural upward climbing behavior of Drosophila melanogaster after it oscillates to the bottom of the test tube. The strength of climbing ability is regarded as the index of aging change of D. melanogaster. At present, many laboratories use the percentage of 10 fruit flies climbing a specific height in 5 s as a general indicator of the climbing ability of fruit flies. This group research index ignores the climbing performance of a single fruit fly, and the climbing height belongs to the concept of vertical distance in physics, which cannot truly and effectively reflect the concept of curve distance in the actual climbing process of fruit flies. Therefore, based on the image processing algorithm, we added an experimental method to draw the climbing trajectory of a single fruit fly. By comparing the differences in climbing behavior of fruit flies under different sex, group or single, oscillation condition or rotation inversion condition, we can find that the K-Nearest Neighbor target detection algorithm has good applicability in fruit fly climbing experiment, and the climbing ability of fruit flies decreases with age. Under the same experimental conditions, the climbing ability of female fruit flies was greater than that of male fruit flies. The climbing track length of a single fruit fly can better reflect the climbing process of a fruit fly.

An Improved U-Net Image Segmentation Method and Its Application for Metallic Grain Size Statistics

Grain size is one of the most important parameters for metallographic microstructure analysis, which can partly determine the material performance. The measurement of grain size is based on accurate image segmentation methods, which include traditional image processing methods and emerging machine-learning-based methods. Unfortunately, traditional image processing methods can hardly segment grains correctly from metallographic images with low contrast and blurry boundaries. Moreover, the proposed machine-learning-based methods need a large dataset to train the model and can hardly deal with the segmentation challenge of complex images with fuzzy boundaries and complex structure. In this paper, an improved U-Net model is proposed to automatically accomplish image segmentation of complex metallographic images with only a small training set. The experiments on metallographic images show the significant advantage of the method, especially for the metallographic images with low contrast, a fuzzy boundary and complex structure. Compared with other deep learning methods, the improved U-Net scored higher in ACC, MIoU, Precision, and F1 indexes, among which ACC was 0.97, MIoU was 0.752, Precision was 0.98, and F1 was 0.96. The grain size was calculated based on the segmentation according to the American Society for Testing Material (ASTM) standards, producing a satisfactory result.

Capturing the songs of mice with an improved detection and classification method for ultrasonic vocalizations (BootSnap)

House mice communicate through ultrasonic vocalizations (USVs), which are above the range of human hearing (>20 kHz), and several automated methods have been developed for USV detection and classification. Here we evaluate their advantages and disadvantages in a full, systematic comparison, while also presenting a new approach. This study aims to 1) determine the most efficient USV detection tool among the existing methods, and 2) develop a classification model that is more generalizable than existing methods. In both cases, we aim to minimize the user intervention required for processing new data. We compared the performance of four detection methods in an out-of-the-box approach, pretrained DeepSqueak detector, MUPET, USVSEG, and the Automatic Mouse Ultrasound Detector (A-MUD). We also compared these methods to human visual or ‘manual’ classification (ground truth) after assessing its reliability. A-MUD and USVSEG outperformed the other methods in terms of true positive rates using default and adjusted settings, respectively, and A-MUD outperformed USVSEG when false detection rates were also considered. For automating the classification of USVs, we developed BootSnap for supervised classification, which combines bootstrapping on Gammatone Spectrograms and Convolutional Neural Networks algorithms with Snapshot ensemble learning. It successfully classified calls into 12 types, including a new class of false positives that is useful for detection refinement. BootSnap outperformed the pretrained and retrained state-of-the-art tool, and thus it is more generalizable. BootSnap is freely available for scientific use.

House mice and many other species use ultrasonic vocalizations to communicate in various contexts including social and sexual interactions. These vocalizations are increasingly investigated in research on animal communication and as a phenotype for studying the genetic basis of autism and speech disorders. Because manual methods for analyzing vocalizations are extremely time consuming, automatic tools for detection and classification are needed. We evaluated the performance of the available tools for analyzing ultrasonic vocalizations, and we compared detection tools for the first time to manual methods (“ground truth”) using recordings from wild-derived and laboratory mice. For the first time, class-wise inter-observer reliability of manual labels used for ground truth are analyzed and reported. Moreover, we developed a new classification method based on ensemble deep learning that provides more generalizability than the current state-of-the-art tool (both pretrained and retrained). Our new classification method is free for scientific use.

A Novel Feature-Selection Method for Human Activity Recognition in Videos

Human Activity Recognition (HAR) is the process of identifying human actions in a specific environment. Recognizing human activities from video streams is a challenging task due to problems such as background noise, partial occlusion, changes in scale, orientation, lighting, and the unstable capturing process. Such multi-dimensional and none-linear process increases the complexity, making traditional solutions inefficient in terms of several performance indicators such as accuracy, time, and memory. This paper proposes a technique to select a set of representative features that can accurately recognize human activities from video streams, while minimizing the recognition time and memory. The extracted features are projected on a canvas, which keeps the synchronization property of the spatiotemporal information. The proposed technique is developed to select the features that refer only to progression of changes. The original RGB frames are preprocessed using background subtraction to extract the subject. Then the activity pattern is extracted through the proposed Growth method. Three experiments were conducted; the first experiment was a baseline to compare the classification task using the original RGB features. The second experiment relied on classifying activities using the proposed feature-selection method. Finally, the third experiment provided a sensitivity analysis that compares between the effect of both techniques on time and memory resources. The results indicated that the proposed method outperformed original RBG feature-selection method in terms of accuracy, time, and memory requirements.

The Object Segmentation from the Microstructure of a FSW Dissimilar Weld

Friction stir welding (FSW) is an environmentally friendly, solid-state welding technique. In this research work, we analyze the microstructure of a new type of FSW weld applying a two- stage framework based on image processing algorithms containing a segmentation step and microstructure analysis of objects occurring in different layers. A dual-speed tool as used to prepare the tested weld. In this paper, we present the segmentation method for recognizing areas containing particles forming bands in the microstructure of a dissimilar weld of aluminum alloys made by FSW technology. A digital analysis was performed on the images obtained using an Olympus GX51 light microscope. The image analysis process consisted of basic segmentation methods in conjunction with domain knowledge and object detection located in different layers of a weld using morphological operations and point transformations. These methods proved to be effective in the analysis of the microstructure images corrupted by noise. The segmentation parts as well as single objects were separated enough to analyze the distribution on different layers of the specimen and the variability of shape and size of the underlying microstructures, which was not possible without computer vision support.

A Fast Two-Stage Bilateral Filter Using Constant Time O(1) Histogram Generation

Bilateral Filtering (BF) is an effective edge-preserving smoothing technique in image processing. However, an inherent problem of BF for image denoising is that it is challenging to differentiate image noise and details with the range kernel, thus often preserving both noise and edges in denoising. This letter proposes a novel Dual-Histogram BF (DHBF) method that exploits an edge-preserving noise-reduced guidance image to compute the range kernel, removing isolated noisy pixels for better denoising results. Furthermore, we approximate the spatial kernel using mean filtering based on column histogram construction to achieve constant-time filtering regardless of the kernel radius’ size and achieve better smoothing. Experimental results on multiple benchmark datasets for denoising show that the proposed DHBF outperforms other state-of-the-art BF methods.

Change Target Extraction Based on Scale-Adaptive Difference Image and Morphology Filter for KOMPSAT-5

Multitemporal synthetic aperture radar (SAR) images have been widely used for change detection and monitoring of the environment owing to their competency under all weather conditions. However, owing to speckle backgrounds and strong reflections, change detection in urban areas is challenging. In this study, to automatically extract changed objects, we developed a model that integrated change detection and object extraction in multiple Korean Multi-Purpose Satellite-5 (KOMPSAT-5) images. Initially, two arbitrary L1A-level SAR images were input into the proposed model, and after pre-processing, such as radio calibration and coordinate system processing, change detection was performed. Subsequently, the desired targets were automatically extracted from the change detection results. Finally, the model obtained images of the extraction targets and metadata, such as date and location. Noise was removed by applying scale-adaptive modification to the generated difference image during the change detection process, and the detection accuracy was improved by emphasizing the occurrence of the change. After polygonizing the pixel groups of the change detection map in the target extraction process, the morphology-based object filtering technique was applied to minimize the false detection rate. As a result of the proposed approach, the changed objects in the KOMPSAT-5 images were automatically extracted with 90% accuracy.

Free-breathing MR elastography of the lungs: An in vivo study

PURPOSE

Lung stiffness alters with many diseases; therefore, several MR elastography (MRE) studies were performed earlier to investigate the stiffness of the right lung during breathhold at residual volume and total lung capacity. The aims of this study were 1) to estimate shear stiffness of the lungs using MRE under free breathing and demonstrate the measurements' repeatability and reproducibility, and 2) to compare lung stiffness under free breathing to breathhold and as a function of age and gender.

METHODS

Twenty-five healthy volunteers were scanned on a 1.5 Tesla MRI scanner. Spin-echo dual-density spiral and a spin-echo EPI MRE sequences were used to measure shear stiffness of the lungs during free breathing and breathhold at midpoint of tidal volume, respectively. Concordance correlation coefficient and Bland-Altman analyses were performed to determine the repeatability and reproducibility of the spin-echo dual-density spiral-derived shear stiffness. Repeated measures analyses of variances were used to investigate differences in shear stiffness between spin-echo dual-density spiral and spin-echo EPI, right and left lungs, males and females, and different age groups.

RESULTS

Free-breathing MRE sequence was highly repeatable and reproducible (concordance correlation coefficient > 0.86 for both lungs). Lung stiffness was significantly lower in breathhold than in free breathing (P < .001), which can be attributed to potential stress relaxation of lung parenchyma or breathhold inconsistencies. However, there was no significant difference between different age groups (P = .08). The left lung showed slightly higher stiffness values than the right lung (P = .14). There is no significant difference in lung stiffness between genders.

CONCLUSION

This study demonstrated the feasibility of free-breathing lung MRE with excellent repeatability and reproducibility. Stiffness changes with age and during the respiratory cycle. However, gender does not influence lungs stiffness.

Multi-target 2D tracking method for singing humpback whales using vector sensors

Acoustic vector sensors allow estimating the direction of travel of an acoustic wave at a single point by measuring both acoustic pressure and particle motion on orthogonal axes. In a two-dimensional plane, the location of an acoustic source can thus be determined by triangulation using the estimated azimuths from at least two vector sensors. However, when tracking multiple acoustic sources simultaneously, it becomes challenging to identify and link sequences of azimuthal measurements between sensors to their respective sources. This work illustrates how two-dimensional vector sensors, deployed off the coast of western Maui, can be used to generate azimuthal tracks from individual humpback whales singing simultaneously. Incorporating acoustic transport velocity estimates into the processing generates high-quality azimuthal tracks that can be linked between sensors by cross-correlating features of their respective azigrams, a particular time-frequency representation of sound directionality. Once the correct azimuthal track associations have been made between instruments, subsequent localization and tracking in latitude and longitude of simultaneous whales can be achieved using a minimum of two vector sensors. Two-dimensional tracks and positional uncertainties of six singing whales are presented, along with swimming speed estimates derived from a high-quality track.

Detection and Classification System for Rail Surface Defects Based on Eddy Current

The prospect of growth of a railway system impacts both the network size and its occupation. Due to the overloaded infrastructure, it is necessary to increase reliability by adopting fast maintenance services to reach economic and security conditions. In this context, one major problem is the excessive friction caused by the wheels. This contingency may cause ruptures with severe consequences. While eddy's current approaches are adequate to detect superficial damages in metal structures, there are still open challenges concerning automatic identification of rail defects. Herein, we propose an embedded system for online detection and location of rails defects based on eddy current. Moreover, we propose a new method to interpret eddy current signals by analyzing their wavelet transforms through a convolutional neural network. With this approach, the embedded system locates and classifies different types of anomalies, enabling an optimization of the railway maintenance plan. Field tests were performed, in which the rail anomalies were grouped in three classes: squids, weld and joints. The results showed a classification efficiency of ~98%, surpassing the most commonly used methods found in the literature.

Where to draw the line?

We often take people’s ability to understand and produce line drawings for granted. But where should we draw lines, and why? We address psychological principles that underlie efficient representations of complex information in line drawings. First, 58 participants with varying degree of artistic experience produced multiple drawings of a small set of scenes by tracing contours on a digital tablet. Second, 37 independent observers ranked the drawings by how representative they are of the original photograph. Matching contours between drawings of the same scene revealed that the most consistently drawn contours tend to be drawn earlier. We generated half-images with the most- versus least-consistently drawn contours and asked 25 observers categorize the quickly presented scenes. Observers performed significantly better for the most compared to the least consistent half-images. The most consistently drawn contours were more likely to depict occlusion boundaries, whereas the least consistently drawn contours frequently depicted surface normals.

Ensemble Deep Learning for the Detection of COVID-19 in Unbalanced Chest X-ray Dataset

The ongoing COVID-19 pandemic has caused devastating effects on humanity worldwide. With practical advantages and wide accessibility, chest X-rays (CXRs) play vital roles in the diagnosis of COVID-19 and the evaluation of the extent of lung damages incurred by the virus. This study aimed to leverage deep-learning-based methods toward the automated classification of COVID-19 from normal and viral pneumonia on CXRs, and the identification of indicative regions of COVID-19 biomarkers. Initially, we preprocessed and segmented the lung regions usingDeepLabV3+ method, and subsequently cropped the lung regions. The cropped lung regions were used as inputs to several deep convolutional neural networks (CNNs) for the prediction of COVID-19. The dataset was highly unbalanced; the vast majority were normal images, with a small number of COVID-19 and pneumonia images. To remedy the unbalanced distribution and to avoid biased classification results, we applied five different approaches: (i) balancing the class using weighted loss; (ii) image augmentation to add more images to minority cases; (iii) the undersampling of majority classes; (iv) the oversampling of minority classes; and (v) a hybrid resampling approach of oversampling and undersampling. The best-performing methods from each approach were combined as the ensemble classifier using two voting strategies. Finally, we used the saliency map of CNNs to identify the indicative regions of COVID-19 biomarkers which are deemed useful for interpretability. The algorithms were evaluated using the largest publicly available COVID-19 dataset. An ensemble of the top five CNNs with image augmentation achieved the highest accuracy of 99.23% and area under curve (AUC) of 99.97%, surpassing the results of previous studies.

Simultaneous two-color X-ray absorption spectroscopy using Laue crystals at an inverse-compton scattering X-ray facility

X-ray absorption spectroscopy (XAS) is an element-selective technique that provides electronic and structural information of materials and reveals the essential mechanisms of the reactions involved. However, the technique is typically conducted at synchrotrons and usually only probes one element at a time. In this paper, a simultaneous two-color XAS setup at a laboratory-scale synchrotron facility is proposed based on inverse Compton scattering (ICS) at the Munich Compact Light Source (MuCLS), which is based on inverse Compton scattering (ICS). The setup utilizes two silicon crystals in a Laue geometry. A proof-of-principle experiment is presented where both silver (Ag) and palladium (Pd) K-edge X-ray absorption near-edge structure spectra were simultaneously measured. The simplicity of the setup facilitates its migration to other ICS facilities or maybe to other X-ray sources (e.g. a bending-magnet beamline). Such a setup has the potential to study reaction mechanisms and synergistic effects of chemical systems containing multiple elements of interest, such as a bimetallic catalyst system.

Three-Dimensional Outdoor Analysis of Single Synthetic Building Structures by an Unmanned Flying Agent Using Monocular Vision

An algorithm designed for analysis and understanding a 3D urban-type environment by an autonomous flying agent, equipped only with a monocular vision, is presented. The algorithm is hierarchical and is based on the structural representation of the analyzed scene. Firstly, the robot observes the scene from a high altitude to build a 2D representation of a single object and a graph representation of the 2D scene. The 3D representation of each object arises as a consequence of the robot’s actions, as a result of which it projects the object’s solid on different planes. The robot assigns the obtained representations to the corresponding vertex of the created graph. The algorithm was tested by using the embodied robot operating on the real scene. The tests showed that the robot equipped with the algorithm was able not only to localize the predefined object, but also to perform safe, collision-free maneuvers close to the structures in the scene.

Optimization of 4D flow MRI velocity field in the aorta with divergence-free smoothing

Divergence-free smoothing with wall treatment (DFS_wt) method is proposed for processing with four-dimensional (4D) flow magnetic resonance imaging (MRI) data of blood flows to enhance the quality of flow field with physical constraints. The new method satisfies the no-slip wall boundary condition and applies wall function of velocity profile for better estimating the velocity gradient in the near-wall region, and consequently improved wall shear stress (WSS) calculation against the issue of coarse resolution of 4D flow MRI. In the first testing case, blood flow field obtained from 4D flow MRI is well smoothed by DFS_wt method. A great consistency is observed between the post-processed 4D flow MRI data and the computational fluid dynamics (CFD) data in the interested velocity field. WSS has an apparent improvement due to the proposed near-wall treatment with special wall function comparing to the result from original 4D flow MRI data or the DFS-processed data with no wall function. The other five cases also show the same performance that smoothed velocity field and improved WSS estimation are achieved on 4D flow MRI data optimized by DFS_wt. The improvements will benefit the study of hemodynamics regarding the determination of location or the potential possibility of lesions.

Novel image enhancement approaches for despeckling in ultrasound images for fibroid detection in human uterus

Ultrasonography is an extensively used medical imaging technique for multiple reasons. It works on the basic theory of echoes from the tissues under consideration. However, the occurrence of signal dependent noise such as speckle destroys utility of ultrasound images. Speckle noise is subject to the composition of image tissue and parameters of image. It reduces the effectiveness of many image processing steps and decreases human perception of fine details form ultrasound images. In many medical image processing methods, despeckling is used as the preprocessing step before segmentation and feature extraction. Many speckle reduction filters are proposed but while combining many techniques some speckle diagnostic information should be preserved. Removal of speckle noise from ultrasound image by preserving edges and added features is a great challenging task in ultrasound image restoration. This paper aims at a comprehensive description and comparison of reduction of speckle noise of ultrasound fibroid image. Many filters are applied on ultrasound scanned images and the performance is marked in terms of some statistical measures. Even though several despeckling filters are there for speckle reduction, all are not good for ultrasound scanned images. A comparison of quality measures such as mean square error, peak signal-to-noise ratio, and signal-to-noise ratio is done in ultrasound images in despeckling.

Masked face recognition with convolutional neural networks and local binary patterns

Face recognition is one of the most common biometric authentication methods as its feasibility while convenient use. Recently, the COVID-19 pandemic is dramatically spreading throughout the world, which seriously leads to negative impacts on people’s health and economy. Wearing masks in public settings is an effective way to prevent viruses from spreading. However, masked face recognition is a highly challenging task due to the lack of facial feature information. In this paper, we propose a method that takes advantage of the combination of deep learning and Local Binary Pattern (LBP) features to recognize the masked face by utilizing RetinaFace, a joint extra-supervised and self-supervised multi-task learning face detector that can deal with various scales of faces, as a fast yet effective encoder. In addition, we extract local binary pattern features from masked face’s eye, forehead and eyebow areas and combine them with features learnt from RetinaFace into a unified framework for recognizing masked faces. In addition, we collected a dataset named COMASK20 from 300 subjects at our institution. In the experiment, we compared our proposed system with several state of the art face recognition methods on the published Essex dataset and our self-collected dataset COMASK20. With the recognition results of 87% f1-score on the COMASK20 dataset and 98% f1-score on the Essex dataset, these demonstrated that our proposed system outperforms Dlib and InsightFace, which has shown the effectiveness and suitability of the proposed method. The COMASK20 dataset is available on https://github.com/tuminguyen/COMASK20 for research purposes.

A Multi-Scale Information Fusion Level Set for Breast Tumor Segmentation

Purpose: Mammography is considered an effective method of examination in early breast cancer screening. Massive work by distinguished researchers of breast segmentation has been proposed. However, due to the blurry boundaries of the breast tumor, the variability of its shape and the overlap with surrounding tissue, the breast tumor’s accurate segmentation still is a challenge. Methods: In this paper, we proposed a novel level set model which based on the optimized local region driven gradient enhanced level set model (OLR-GCV) to segment tumor within a region of interest (ROI) in a mammogram. Firstly, Noise, labels and artifacts are removed from breast images. The ROI is then obtained using the intuitionistic fuzzy C-means method. Finally, we used OLR-GCV method to accurately segment the breast tumor. The OLR-GCV model combines regional information, enhanced edge information and optimized Laplacian of Gaussian (LOG) energy term. The regional and enhanced edge information are used to capture local, global and gradient information of breast images. The optimized Laplacian of Gaussian (LOG) energy term is introduced in the energy functional to further optimize edge information to improve segmentation accuracy. Results: We evaluated our method on the MIAS and DDSM datasets. It yielded a Dice value of 96.86% on the former and 95.51% on the latter. Our method proposed achieves higher accuracy of segmentation than other State-of-the-art Methods. Conclusions: Our method has better segmentation performance, and can be used in clinical practice.

Effect of Despeckling Filters on the Segmentation of Ultrasound Common Carotid Artery Images

Background

Carotid intima-media thickness (IMT) measured in B-mode ultrasound image is an important indicator of Atherosclerosis disease. Speckle noise inherently present in ultrasounds’ thereby degrades the visual evaluation and limits the automated segmentation performance. The objective of this study is to investigate the effects of three despeckle filters on the segmentation of carotid IMT in ultrasound image.

Methods

Automated segmentation of IMT is achieved by utilizing fast fuzzy c-mean clustering and distance-regularized level set without re-initialization techniques. Manual segmentation has been done by an experienced radiologist. The performances of median, hybrid median and improved adaptive complex diffusion (IACDF) filters are examined and a quantitative and qualitative comparison among these filters has been reported on 151 DICOM images. Bland–Altman plots were used to compare IMT results of these filters.

Furthermore, performances of above three filters are evaluated under different noise levels by individually adding speckle and salt and pepper noise in ten randomly selected images from 151 DICOM dataset. Plots between noise and quality evaluation metric parameters are used to compare de-noising performance of these filters.

Results

The average processing time per image of proposed IMT measurement technique without-filter and with filter is approx 15.39 s max.

Conclusion

It is shown that the median filter (window 5 × 5) measures better than hybrid median and IACDF filters. Finally, concluded that de-noising of ultrasound image before segmentation procedure certainly improves segmentation accuracy. Furthermore, it is observed that these filters do not impose serious computational burden and entail moderate processing time.

A Gabor Filter-Based Protocol for Automated Image-Based Building Detection

Detecting buildings from high-resolution satellite imagery is beneficial in mapping, environmental preparation, disaster management, military planning, urban planning and research purposes. Differentiating buildings from the images is possible however, it may be a time-consuming or complicated process. Therefore, the high-resolution imagery from satellites needs to be automated to detect the buildings. Additionally, buildings exhibit several different characteristics, and their appearance in these images is unplanned. Moreover, buildings in the metropolitan environment are typically crowded and complicated. Therefore, it is challenging to identify the building and hard to locate them. To resolve this situation, a novel probabilistic method has been suggested using local features and probabilistic approaches. A local feature extraction technique was implemented, which was used to calculate the probability density function. The locations in the image were represented as joint probability distributions and were used to estimate their probability distribution function (pdf). The density of building locations in the image was extracted. Kernel density distribution was also used to find the density flow for different metropolitan cities such as Sydney (Australia), Tokyo (Japan), and Mumbai (India), which is useful for distribution intensity and pattern of facility point f interest (POI). The purpose system can detect buildings/rooftops and to test our system, we choose some crops with panchromatic high-resolution satellite images from Australia and our results looks promising with high efficiency and minimal computational time for feature extraction. We were able to detect buildings with shadows and building without shadows in 0.4468 (seconds) and 0.5126 (seconds) respectively.

Method for Diagnosing the Bone Marrow Edema of Sacroiliac Joint in Patients with Axial Spondyloarthritis Using Magnetic Resonance Image Analysis Based on Deep Learning

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the sacroiliac joints. In this study, we develop a method for detecting bone marrow edema by magnetic resonance (MR) imaging of the sacroiliac joints and a deep-learning network. A total of 815 MR images of the sacroiliac joints were obtained from 60 patients diagnosed with axSpA and 19 healthy subjects. Gadolinium-enhanced fat-suppressed T1-weighted oblique coronal images were used for deep learning. Active sacroiliitis was defined as bone marrow edema, and the following processes were performed: setting the region of interest (ROI) and normalizing it to a size suitable for input to a deep-learning network, determining bone marrow edema using a convolutional-neural-network-based deep-learning network for individual MR images, and determining sacroiliac arthritis in subject examinations based on the classification results of individual MR images. About 70% of the patients and normal subjects were randomly selected for the training dataset, and the remaining 30% formed the test dataset. This process was repeated five times to calculate the average classification rate of the five-fold sets. The gradient-weighted class activation mapping method was used to validate the classification results. In the performance analysis of the ResNet18-based classification network for individual MR images, use of the ROI showed excellent detection performance of bone marrow edema with 93.55 ± 2.19% accuracy, 92.87 ± 1.27% recall, and 94.69 ± 3.03% precision. The overall performance was additionally improved using a median filter to reflect the context information. Finally, active sacroiliitis was diagnosed in individual subjects with 96.06 ± 2.83% accuracy, 100% recall, and 94.84 ± 3.73% precision. This is a pilot study to diagnose bone marrow edema by deep learning based on MR images, and the results suggest that MR analysis using deep learning can be a useful complementary means for clinicians to diagnose bone marrow edema.

Remote Sensing-Based Automatic Detection of Shoreline Position: A Case Study in Apulia Region

Remote sensing and satellite imagery have become commonplace in efforts to monitor and model various biological and physical characteristics of the Earth. The land/water interface is a continually evolving landscape of high scientific and societal interest, making the mapping and monitoring thereof particularly important. This paper aims at describing a new automated method of shoreline position detection through the utilization of Synthetic Aperture Radar (SAR) images derived from European Space Agency satellites, specifically the operational SENTINEL Series. The resultant delineated shorelines are validated against those derived from video monitoring systems and in situ monitoring; a mean distance of 1 and a maximum of 3.5 pixels is found.

A guide to accurate reporting in digital image processing - can anyone reproduce your quantitative analysis?

Considerable attention has been recently paid to improving replicability and reproducibility in life science research. This has resulted in commendable efforts to standardize a variety of reagents, assays, cell lines and other resources. However, given that microscopy is a dominant tool for biologists, comparatively little discussion has been offered regarding how the proper reporting and documentation of microscopy relevant details should be handled. Image processing is a critical step of almost any microscopy-based experiment; however, improper, or incomplete reporting of its use in the literature is pervasive. The chosen details of an image processing workflow can dramatically determine the outcome of subsequent analyses, and indeed, the overall conclusions of a study. This Review aims to illustrate how proper reporting of image processing methodology improves scientific reproducibility and strengthens the biological conclusions derived from the results.

Smoothed Shock Filtering: Algorithm and Applications

This article presents the smoothed shock filter, which iteratively produces local segmentations in image’s inflection zones with smoothed morphological operators (dilations, erosions). Hence, it enhances contours by creating smoothed ruptures, while preserving homogeneous regions. After describing the algorithm, we show that it is a robust approach for denoising, compared to related works. Then, we expose how we exploited this filter as a pre-processing step in different image analysis tasks (medical image segmentation, fMRI, and texture classification). By means of its ability to enhance important patterns in images, the smoothed shock filter has a real positive impact upon such applications, for which we would like to explore it more in the future.