Single Image Acquisition Research Articles

Optimizing Wrist Splint Fitting Parameters Through Artificial Intelligence Analysis.

Introduction The current method for determining the appropriate wrist splint size in the clinical setting relies on measuring wrist circumference, but this approach often fails to ensure optimal fit. This study evaluates additional hand features using 3-dimensional (3D) scanned data and Artificial Intelligence (AI) to improve the fit of pre-fabricated wrist splints. We hypothesize that wrist and forearm widths can provide a more accurate fitting than wrist circumference alone. Materials and methods We recruited 54 healthy volunteers to be scanned. Each volunteer was fitted with a standard wrist brace (Short Arm Brace, Ossur, Iceland), and 3D data from their hands were collected using an infrared-based 3D scanner (Einscan Pro, Shining3D, China). The 3D scanned data were then analyzed to identify and measure 14 distinct hand features. To explore the relationship between these hand features and the optimal splint size, we generated a categorical correlation map. This map identified hand features that were most strongly correlated with splint size categories (small, medium, large). Subsequently, we developed a classification algorithm to predict the appropriate splint size based on the correlated hand features. We utilized three different machine learning models for this purpose: Extreme Gradient Boosting (XGB) Classifier, RandomForestClassifier, and Support Vector Classifier (SVC). Each of these classifiers was trained and evaluated to determine their accuracy and effectiveness in predicting the correct splint size. Results Wrist width showed the highest classification accuracy (91%) for both the XGB Classifier and RandomForestClassifier. The measurements including hand wrist width, mid-forearm width, and hand crease line width also performed well with the XGB Classifier, achieving an accuracy of 90%. The SVCshowed consistent performance across various feature sets, with the highest accuracy of 81% for the measurements. Overall, these findings suggest that wrist width is the most predictive feature for splint size classification, with additional features providing minimal enhancement. Conclusions Artificial intelligence, combined with 3D scanning, can accurately predict wrist splint size from a single image acquisition, enabling contactless, personalized fitting.This approach can improve patient outcomes by enhancing the fit of prefabricated splints.

Robust quantitative X-ray phase diagnostic for carbon composite characterisation in the context of lightning induced risk

Getting complementary physical information from a single image acquisition is particularly valuable for materials analysis. Grating based X-ray Phase Contrast Imaging (XPCI) methods allow decoupling attenuation, phase and scattering information. However, the phase and scattering extraction processes can easily suffer from artefacts, which is detrimental to implement this imaging technique in societal applications. In this paper, we demonstrate that grating based XPCI can provide a robust phase measurement in complex materials such as damaged composites. The technique allows the phase to be analysed using a self-assessment method that first identifies the artefacts from the imaging setup, and then can be used as an indicator to interpret the signal from a material. We focus on carbon fibre reinforced polymers which we subjected to laboratory-controlled lightning strikes. We evidence that the combined information from phase and attenuation allow identifying the type of defect induced by the lightning current. The phase information is converted into relative mass density variation within the sample and depicts areas with a loss in density up to 40%. We ensure that these results are valid by comparing them with an X-ray attenuation contrast tomographic reconstruction.

Enlarge the dynamic range of Shack-Hartmann wavefront sensor based on biplanar image acquisition and segmentation method

In present paper, a simple and robust method to expand the SHWS dynamic range is proposed. The intensity patterns are obtained with biplanar image acquisition and segmentation. The process involves calculating the spot centroids of two images and then matching the centroid of the spots of light with the center of a micro-lens array. This also resolves the issue of mandating the determination of centroids exclusively within the corresponding detection area. It is performed a comparative analysis between our proposed method and the conventional method for measuring large wavefronts, utilizing both numerical simulations and experiments. Additionally, a statistical analysis of the dynamic range of the method for wavefront measurement was conducted. This study demonstrates that the biplanar image acquisition and segmentation method provided a larger dynamic range while ensuring accuracy relative to the single image acquisition of conventional algorithm

A new paradigm in electron microscopy: Automated microstructure analysis utilizing a dynamic segmentation convolutional neutral network

Over the past half century, the transmission electron microscope enabled insight into the fundamental arrangements and structures of materials. State-of-the-art electron microscopes can acquire large image datasets across multiple imaging modalities. However, the manual annotation process for feature or defect quantification may not be feasible with the modern microscope. Convolutional neural networks emerged to characterize individual microstructural features from an image in a cost-effective, consistent manner. However, many of these neural network approaches rely on thousands to hundreds of thousands of manual annotations of each feature type across hundreds of images to train the network for adequate performance. This work focused on the development and application of a pixel-wise defect detection machine-learning dynamic segmentation convolutional neural network with associated automated acquisition and postprocessing to identify microstructural features rapidly and quantitatively from a small initial dataset incorporating multiple imaging modes. The approach was demonstrated for characterization of superalloy 718 from both single image acquisition on multiple detectors to in-situ evolution captured with a single detector on a standard desktop computer to demonstrate the low barrier to entry required for widespread adoption. Pixel-by-pixel class identification was excellent with strong identification of chemically distinct phases, structurally distinct phases, and defect structures, thus demonstrating the new paradigm of machine learning-assisted characterization.

Determination of Stokes Vector from a Single Image Acquisition

AbstractFour Stokes parameters (1852) define the polarization state of light. Measured changes of the Stokes vector of light traversing an inhomogeneous sample are linked to the local anisotropies of absorption and refraction and are harnessed over an increasing range of applications in photonics, material, and space/earth observation. Several independent polarization sensitive measurements are usually required for determination of the all four Stokes parameters, which makes such characterization procedure time‐consuming or requires complex setups. Here, a single‐snapshot approach to Stokes polarimetry in transmission is introduced by use of a four‐polarization camera with the on‐chip integrated polarizers. A quarter‐waveplate is added in front of the sample and is illuminated by a linearly polarized light. This approach is demonstrated by measuring birefringence of spider silk of only m‐diameter using microscopy, however, due to its generic nature, it is transferable to other spectral ranges and imaging applications, e.g., imaging from a fast moving satellite or drone or monitoring fast changing events such as phase transitions.

Embedded Blur-Free Single-Image Acquisition Pipeline for Droplet Microfluidic Imaging Flow Cytometry (IFC)

Embedded Blur-Free Single-Image Acquisition Pipeline for Droplet Microfluidic Imaging Flow Cytometry (IFC)

Comprehensive MR imaging QA of 0.35 T MR-Linac using a multi-purpose large FOV phantom: A single-institution experience.

Magnetic resonance-guided radiotherapy (MRgRT) is desired for the treatment of diseases in the abdominothoracic region, which has a broad imaging area and continuous motion. To ensure accurate treatment delivery, an effective image quality assurance (QA) program, with a phantom that covers the field of view (FOV) similar to a human torso, is required. However, routine image QA for a large FOV is not readily available at many MRgRT centers. In this work, we present the clinical experience of the large FOV MRgRT Insight phantom for periodic daily and monthly comprehensive magnetic resonance imaging (MRI)-QA and its feasibility compared to the existing institutional routine MRI-QA procedures in 0.35 T MRgRT. Three phantoms; ViewRay cylindrical water phantom, Fluke 76-907 uniformity and linearity phantom, and Modus QA large FOV MRgRT Insight phantom, were imaged on the 0.35 T MR-Linac. The measurements were made in MRI mode with the true fast imaging with steady-state free precession (TRUFI) sequence. The ViewRay cylindrical water phantom was imaged in a single-position setup whereas the Fluke phantom and Insight phantom were imaged in three different orientations: axial, sagittal, and coronal. Additionally, the phased array coil QA was performed using the horizontal base plate of the Insight phantom by placing the desired coil around the base section which was compared to an in-house built Polyurethane foam phantom for reference. The Insight phantom captured image artifacts across the entire planar field of view, up to 400mm, in a single image acquisition, which is beyond the FOV of the conventional phantoms. The geometric distortion test showed a similar distortion of 0.45±0.01 and 0.41±0.01mm near the isocenter, that is, within 300mm lengths for Fluke and Insight phantoms, respectively, but showed higher geometric distortion of 0.8±0.4mm in the peripheral region between 300 and 400mm of the imaging slice for the Insight phantom. The Insight phantom with multiple image quality features and its accompanying software utilized the modulation transform function (MTF) to evaluate the image spatial resolution. The average MTF values were 0.35±0.01, 0.35±0.01, and 0.34±0.03 for axial, coronal, and sagittal images, respectively. The plane alignment and spatial accuracy of the ViewRay water phantom were measured manually. The phased array coil test for both the Insight phantom and the Polyurethane foam phantoms ensured the proper functionality of each coil element. The multifunctional large FOV Insight phantom helps in tracking MR imaging quality of the system to a larger extent compared to the routine daily and monthly QA phantoms currently used in our institute. Also, the Insight phantom is found to be more feasible for routine QA with easy setup.

Multiparametric dynamic whole-body PSMA PET/CT using [68Ga]Ga-PSMA-11 and [18F]PSMA-1007

BackgroundRoutine prostate-specific membrane antigen (PSMA) positron emission tomography (PET) performed for primary staging or restaging of prostate cancer patients is usually done as a single static image acquisition 60 min after tracer administration. In this study, we employ dynamic whole-body (D-WB) PET imaging to compare the pharmacokinetics of [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 in various tissues and lesions, and to assess whether Patlak parametric images are quantitative and improve lesion detection and image readability.MethodsTwenty male patients with prostate cancer were examined using a D-WB PSMA PET protocol. Ten patients were scanned with [68Ga]Ga-PSMA-11 and ten with [18F]PSMA-1007. Kinetic analyses were made using time-activity curves (TACs) extracted from organs (liver, spleen, bone, and muscle) and lesions. For each patient, three images were produced: SUV + Patlak parametric images (Ki and DV). All images were reviewed visually to compare lesion detection, image readability was quantified using target-to-background ratios (TBR), and Ki and DV values were compared.ResultsThe two PSMA tracers exhibited markedly different pharmacokinetics in organs: reversible for [68Ga]Ga-PSMA-11 and irreversible for [18F]PSMA-1007. For both tracers, lesions kinetics were best described by an irreversible model. All parametric images were of good visual quality using both radiotracers. In general, Ki images were characterized by reduced vascular signal and increased lesion TBR compared with SUV images. No additional malignant lesions were identified on the parametric images.ConclusionD-WB PET/CT is feasible for both PSMA tracers allowing for direct reconstruction of parametric Ki images. The use of multiparametric PSMA images increased TBR but did not lead to the detection of more lesions. For quantitative whole-body Ki imaging, [18F]PSMA-1007 should be preferred over [68Ga]Ga-PSMA-11 due to its irreversible kinetics in organs and lesions.

Phase-quadrature quantum imaging with undetected photons.

Sensing with undetected photons allows access to spectral regions with simultaneous detection of photons of another region and is based on nonlinear interferometry. To obtain the full information of a sample, the corresponding interferogram has to be analyzed in terms of amplitude and phase, which has been realized so far by multiple measurements followed by phase variation. Here, we present a polarization-optics-based phase-quadrature implementation in a nonlinear interferometer for imaging with undetected photons in the infrared region. This allows us to obtain phase and visibility with a single image acquisition without the need of varying optical paths or phases, thus enabling the detection of dynamic processes. We demonstrate the usefulness of our method on a static phase mask opaque to the detected photons as well as on dynamic measurement tasks as the drying of an isopropanol film and the stretching of an adhesive tape.

Near-infrared hyperspectral imaging evaluation of Fusarium damage and DON in single wheat kernels

Fusarium is a DON producing filamentous fungi which commonly infects small grain cereals. Near-Infrared Hyperspectral Imaging (HSI-NIR) is considered for its potential to manage this contamination, as it uses spatial recognition, which may be able to deal with the heterogeneity inside the batches for cereal sorting implementation. The focus of this study was the application of HSI-NIR for Fusarium Damaged Kernels (FDK) detection and DON prediction and discrimination of wheat kernels over EU limits. After the HSI scanning of 300 individual grains, the reference values were obtained attributing categories for typical fungal symptoms and analyzing DON from individual grains by HPLC. Several spectral preprocessing methods selected valuable information before model calibration. Externally validated PLS predictions showed RMSEP of 6.65 mg/kg, an R 2 of 0.88 and an RPD of 3.21. However, the classification models managed wheat contaminations more appropriately, obtaining discrimination accuracies of 85.8% and 76.9% for fungal symptoms and DON at the EU limit, respectively. These findings suggest that HSI-NIR can be a suitable tool to sort DON contaminated kernels at EU limits. • This study was developed for single wheat kernels hyperspectral image acquisition. • HSI-NIR was able to classify 85.8% of kernels according to fungal symptomatology. • HSI-NIR was able to classify 76.9% of kernels according to the DON EU limit (1250 μg/kg). • DON prediction performance presented an R 2 of 0.88 and an RMSEP of 6.65 mg/kg.

Imaging flow cytometry: a primer.

Imaging flow cytometry combines the high throughput nature of flow cytometry with the advantages of single cell image acquisition associated with microscopy. The measurement of large numbers of features from the resulting images provides rich datasets which have resulted in a wide range of novel biomedical applications. In this primer we discuss the typical imaging flow instrumentation, the form of data acquired and the typical analysis tools that can be applied to this data. Using examples from the literature we discuss the progression of the analysis methods that have been applied to imaging flow cytometry data. These methods start from the use of simple single image features and multiple channel gating strategies, followed by the design and use of custom features for phenotype classification, through to powerful machine and deep learning methods. For each of these methods, we outline the processes involved in analyzing typical datasets and provide details of example applications. Finally we discuss the current limitations of imaging flow cytometry and the innovations which are addressing these challenges.

Cross-grating phase microscopy (CGM): In silico experiment (insilex) algorithm, noise and accuracy

Cross-grating phase microscopy (CGM) is a quantitative phase microscopy technique based on the association of a 2-dimensional diffraction grating (aka cross-grating) and a regular camera sensor, separated by a millimetric distance. This simple association enables the high-resolution imaging of the complex electric field amplitude of a light beam (intensity and phase) from a single image acquisition. While CGM has been used for metrology applications in cell biology and nanophotonics this last decade, there has been few studies on its basics, especially for the microscopy community. In this article, we provide a numerical algorithm that enables the in silico (i.e. computer-simulated) data acquisition, to easily vary and observe the effects of all the CGM experimental parameters using computer means. In the frame on this article, we illustrate the interest of this numerical algorithm by using it to explain and quantify the effects of several important CGM parameters (grating-camera distance, pixel size, light intensity, numerical apertures, etc.) on the noise, precision and trueness of CGM measurements. This work is aimed to push the limits of CGM toward advanced applications in biomicroscopy and nanophotonics.

3D Reconstruction of cellular images from microfabricated imagers using fully-adaptive deep neural networks

Millimeter-scale multi-cellular level imagers enable various applications, ranging from intraoperative surgical navigation to implantable sensors. However, the tradeoffs for miniaturization compromise resolution, making extracting 3D cell locations challenging—critical for tumor margin assessment and therapy monitoring. This work presents three machine-learning-based modules that extract spatial information from single image acquisitions using custom-made millimeter-scale imagers. The neural networks were trained on synthetically-generated (using Perlin noise) cell images. The first network is a convolutional neural network estimating the depth of a single layer of cells, the second is a deblurring module correcting for the point spread function (PSF). The final module extracts spatial information from a single image acquisition of a 3D specimen and reconstructs cross-sections, by providing a layered “map” of cell locations. The maximum depth error of the first module is 100 µm, with 87% test accuracy. The second module’s PSF correction achieves a least-square-error of only 4%. The third module generates a binary “cell” or “no cell” per-pixel labeling with an accuracy ranging from 89% to 85%. This work demonstrates the synergy between ultra-small silicon-based imagers that enable in vivo imaging but face a trade-off in spatial resolution, and the processing power of neural networks to achieve enhancements beyond conventional linear optimization techniques.

CT-Urography study protocol: Split-Bolus technique

CTU represents the natural technical and instrumental evolution of urography. The multidetector technology, withthe possibility of retro-reconstruction of the images, has allowed the direct representation of the excretory tract witha significant reduction in acquisition times, decreasing motion artifacts and increasing the definition of the processedimages. Split-Bolus CT dynamic study allows us to obtain, in a single image acquisition, both the nephrographic andthe renal excretory phases; at the same time, we can obtain information of the parenchymal organs in the abdominalcavity as in the portal/nephrographic phase of a standard CT protocol. The main advantage of Split-Bolus CTUis undoubtedly the significant saving of the radiation dose administered to the patient, related to the reduction inthe number of phases acquired, with a reported diagnostic efficacy comparable to traditional protocols in terms ofimaging quality. The Split Bolus technique has been used in several clinical contexts, such as in the characterizationof focal liver lesions, in acute pulmonary embolism and in polytrauma patients.

CT-Urography study protocol: Split-Bolus technique

CTU represents the natural technical and instrumental evolution of urography. The multidetector technology, with the possibility of retro-reconstruction of the images, has allowed the direct representation of the excretory tract with a significant reduction in acquisition times, decreasing motion artifacts and increasing the definition of the processed images. Split-Bolus CT dynamic study allows us to obtain, in a single image acquisition, both the nephrographic and the renal excretory phases; at the same time, we can obtain information of the parenchymal organs in the abdominal cavity as in the portal/nephrographic phase of a standard CT protocol. The main advantage of Split-Bolus CTU is undoubtedly the significant saving of the radiation dose administered to the patient, related to the reduction in the number of phases acquired, with a reported diagnostic efficacy comparable to traditional protocols in terms of imaging quality. The Split Bolus technique has been used in several clinical contexts, such as in the characterization of focal liver lesions, in acute pulmonary embolism and in polytrauma patients.

Multi-View 3D Transesophageal Echocardiography Registration and Volume Compounding for Mitral Valve Procedure Planning

Three-dimensional ultrasound mosaicing can increase image quality and expand the field of view. However, limited work has been done applying these compounded approaches for cardiac procedures focused on the mitral valve. For procedures targeting the mitral valve, transesophageal echocardiography (TEE) is the primary imaging modality used as it provides clear 3D images of the valve and surrounding tissues. However, TEE suffers from image artefacts and signal dropout, particularly for structures lying below the valve, including chordae tendineae, making it necessary to acquire alternative echo views to visualize these structures. Due to the limited field of view obtainable, the entire ventricle cannot be directly visualized in sufficient detail from a single image acquisition in 3D. We propose applying an image compounding technique to TEE volumes acquired from a mid-esophageal position and several transgastric positions in order to reconstruct a high-detail volume of the mitral valve and sub-valvular structures. This compounding technique utilizes both fully and semi-simultaneous group-wise registration to align the multiple 3D volumes, followed by a weighted intensity compounding step based on the monogenic signal. This compounding technique is validated using images acquired from two excised porcine mitral valve units and three patient data sets. We demonstrate that this compounding technique accurately captures the physical structures present, including the mitral valve, chordae tendineae and papillary muscles. The chordae length measurement error between the compounded ultrasound and ground-truth CT for two porcine valves is reported as 0.7 ± 0.6 mm and 0.6 ± 0.6 mm.

Quantitative in vivo micro-computed tomography for monitoring disease activity and treatment response in a collagen-induced arthritis mouse model

A painful, chronic condition, Rheumatoid Arthritis, is marked by bone erosion and soft tissue swelling at the joint. As treatments are investigated in pre-clinical models, characterizing disease progression is integral to assessing treatment efficacy. Here, in vivo and ex vivo micro-computed tomography (µCT) are used in parallel with traditional caliper score measurement to quantify physiological changes in the tarsal region in a murine, collagen-induced arthritis model. In vivo imaging methods, which are validated here through comparison to ex vivo and caliper methods, afford longitudinal analysis of both bone and soft tissue through a single image acquisition. This method removes the subjectivity of swelling quantification which is inherently associated with traditional caliper measurements. Histopathology offers an additional assessment of bone erosion and inflammation by providing a microscopic characterization of disease activity. In comparison to untreated animals, daily prednisolone (glucocorticoid) treatment is shown to restore bone volume, as reflected through in vivo and ex vivo µCT images, as well as histopathology. Prednisolone-associated reduction in inflammation is shown through in vivo µCT soft tissue volume measurements, paw caliper measurements, and histopathology. The findings reported here provide a comprehensive validation of in vivo µCT with a sensitivity that enables characterization of pre-clinical disease assessment in response to treatment in a murine, collagen-induced arthritis model.

Apple image fusion algorithm based on binocular acquisition system

To solve the problem that single natural scene image acquisition information in an orchard cannot meet the requirements of accurate fruit recognition and target positioning, a new apple image fusion algorithm based on the binocular acquisition system named New Non-sub-sampled Contourlet Transform algorithm is proposed to obtain a high-quality fusion image. The binocular acquisition system is constructed with the Time of Flight industrial camera and the colour camera. In order to achieve a better fusion effect, a parameter optimisation algorithm based on an Artificial Bee Colony algorithm with discard strategy for brightness saliency function is proposed to optimise the low-frequency component parameters of the new fusion coefficient rule. The experiments were taken on series of apple images under three sunlight conditions in the orchard. The experimental results show that the six evaluation indicators obtained by the new algorithm achieve the expected fusion image effect under three different types of sunlight conditions.

Role of Vesical Imaging-Reporting and Data System in predicting muscle-invasive bladder cancer: A diagnostic meta-analysis.

The objective of this study is to systematically evaluate the diagnostic performance of the Vesical Imaging-Reporting and Data System for predicting muscle-invasive bladder cancer. Embase, PubMed and Web of Science were systematically searched from 1 September 2018 to 30 July 2021 to include proper studies. We included studies that included data on Vesical Imaging-Reporting and Data System and their associated pathological findings, and we assessed their quality using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The pooled sensitivity and specificity were calculated and plotted using hierarchical summary receiver operating characterisijutic modeling. Meta-regression analysis was carried out to detect heterogeneity. A total of 20 studies with 2725 patients were included. When the cut-off point was 3, the pooled sensitivity and specificity were 0.92 (0.89-0.94) and 0.85 (0.78-0.90), respectively, and 0.82 (0.75-0.88) and 0.95 (0.91-0.97), respectively, when the cut-off point was 4. The area under the curve was 0.95 and 0.95, respectively. Heterogeneity was substantially considerable in sensitivity and specificity. All subgroup variables, including patient number, study design, magnetic resonance imaging field strength, number of radiologists, surgery pattern, diffusion-weighted imaging, and dynamic contrast-enhanced magnetic resonance imaging, contributed to sensitivity heterogeneity when the cut-off point was 3 and specificity heterogeneity when the cut-off point was 4. Multiple image acquisition plane of diffusion-weighted imaging achieved a higher sensitivity than single image acquisition plane of diffusion-weighted imaging in both the Vesical Imaging-Reporting and Data System 3 and 4 groups, and higher specificity in the Vesical Imaging-Reporting and Data System 4 group. Another significant source of heterogeneity was the cut-off point. The diagnostic performance of the Vesical Imaging-Reporting and Data System for predicting muscle-invasive bladder cancer was excellent in both cut-off points of the Vesical Imaging-Reporting and Data System 3 and 4. Multiple image acquisition planes of diffusion-weighted imaging should be given more attention in the Vesical Imaging-Reporting and Data System.

Video encryption/compression using compressive coded rotating mirror camera

Compressive coded rotating mirror (CCRM) camera is a novel high-speed imaging system that operates under amplitude optical encoding and frame sweeping modalities in a passive imaging mode that is capable of reconstructing 1400 frames from a single shot image acquisition and achieves the highest compression ratio of 368 compared to the other compressive sensing (CS) based single-shot imaging modalities. The integrated optical encoding and compression adds a strong layer of encryption on the observed data and facilitates the integration of the CCRM camera with the imaging applications that require highly efficient data encryption and compression due to capturing highly sensitive data or limited transmission and storage capacities. CCRM uses amplitude encoding that significantly extends the key space where the probability of having the exact encoder pattern is estimated as Pleft( Aright) = 1/{10}^{122,500}, hence drastically reducing the possibility of data recovery in a brute force manner. Data reconstruction is achieved under CS based algorithms where the obtained amplitude-based pattern from optical encoder operates as the key in the recovery process. Reconstruction on the experimental as well as the synthetic data at various compression ratios demonstrate that the estimated key with less than 95% matching elements were unable to recover the data where the achieved averaged structural similarity (SSIM) of 0.25 before 95% encoder similarity and 0.85 SSIM at 100% encoder similarity demonstrates the high-sensitivity of the proposed optical encryption technique.