Local Region Of Interest Research Articles

Contrast-to-noise ratio comparison between X-ray fluorescence emission tomography and computed tomography.

We provide a comparison of X-ray fluorescence emission tomography (XFET) and computed tomography (CT) for detecting low concentrations of gold nanoparticles (GNPs) in soft tissue and characterize the conditions under which XFET outperforms energy-integrating CT (EICT) and photon-counting CT (PCCT). We compared dose-matched Monte Carlo XFET simulations and analytical fan-beam EICT and PCCT simulations. Each modality was used to image a numerical mouse phantom and contrast-depth phantom containing GNPs ranging from 0.05% to 4% by weight in soft tissue. Contrast-to-noise ratios (CNRs) of gold regions were compared among the three modalities, and XFET's detection limit was quantified based on the Rose criterion. A partial field-of-view (FOV) image was acquired for the phantom region containing 0.05% GNPs. For the mouse phantom, XFET produced superior CNR values ( , 21.6, and 3.4) compared with CT images obtained with both energy-integrating ( , 4.6, and 1.5) and photon-counting ( , 7.7, and 2.0) detection systems. More generally, XFET outperformed CT for superficial imaging depths ( ) for gold concentrations at and above 0.5%. XFET's surface detection limit was quantified as 0.44% for an average phantom dose of 16mGy compatible with in vivo imaging. XFET's ability to image partial FOVs was demonstrated, and 0.05% gold was easily detected with an estimated dose of to a localized region of interest. We demonstrate a proof of XFET's benefit for imaging low concentrations of gold at superficial depths and the feasibility of XFET for in vivo metal mapping in preclinical imaging tasks.

Investigating high-frequency quasi-periodic oscillations in the 6374 Å red coronal line observed during the total solar eclipse on August 21, 2017

Context. We present the results of the search for high-frequency quasi-periodic oscillations (HFQPOs) in the 6374-Å red line emission from the solar corona during the 2017 total solar eclipse (TSE). Aims. The existence of HFQPOs of coronal intensity remains unclear. Motivated by previous observations, this paper focuses on searching for the HFQPOs (> 0.1 Hz) during the 2017 TSE. Methods. Wavelet analysis tools were used to analyze the radiation intensity oscillations in different height layers, local regions of interest (such as the east coronal loop, west cavity, etc.), and coronal feature points as well as changes in oscillations along coronal feature structures and the kinematic wobble of the coronal magnetic features. Results. We have observed oscillatory signals at multiple spatial locations, which reveal the existence of quasi-periodic slow magnetoacoustic waves. These signals display periods ranging from approximately 3 to 9 seconds, with a notable focus on periods around 4 seconds. Conclusions. High-frequency quasi-periodic slow magnetoacoustic oscillations (with periods less than 9.63 seconds) have been identified in the inner corona (at heights less than 1.4 R⊙) in the 6374 Å red coronal line radiation.

Finite element mesh transition for local–global modeling of composite structures

This study presents an automatic mesh generation algorithm designed to address computational challenges in simulating small-scale defects within large composite structures. The algorithm seamlessly transitions from a coarse mesh, corresponding to the global structure, to a highly refined mesh in targeted local regions of interest. The transition element number and shape can be adjusted by the specified parameters. Tailored to complement this method for non-homogeneous composite models, which include multiple materials such as cohesive layers representing interlayer properties, a volume fraction calculator is integrated to automatically assign the mixture material property in each transition element. Entire processes are fully automated using a MATLAB script, eliminating the need to open the FEA software interface. The validation studies of the reconstructed two-dimensional models, assembled with the wrinkle-defect model, demonstrate their feasibility. The performance of the model is examined in terms of strain and displacement at the connecting boundaries, load–displacement curve, and interlayer failure prediction. The mesh transition model achieves agreeable results compared to a fully fine mesh model, and a 92% reduction in computational time in stress analysis, showing the efficiency of the mesh transition for local–global modeling of composite structures.

Attention-driven visual emphasis for medical volumetric image visualization

AbstractDirect volume rendering (DVR) is a commonly utilized technique for three-dimensional visualization of volumetric medical images. A key goal of DVR is to enable users to visually emphasize regions of interest (ROIs) which may be occluded by other structures. Conventional methods for ROIs visual emphasis require extensive user involvement for the adjustment of rendering parameters to reduce the occlusion, dependent on the user’s viewing direction. Several works have been proposed to automatically preserve the view of the ROIs by eliminating the occluding structures of lower importance in a view-dependent manner. However, they require pre-segmentation labeling and manual importance assignment on the images. An alternative to ROIs segmentation is to use ‘saliency’ to identify important regions. This however lacks semantic information and thus leads to the inclusion of false positive regions. In this study, we propose an attention-driven visual emphasis method for volumetric medical image visualization. We developed a deep learning attention model, termed as focused-class attention map (F-CAM), trained with only image-wise labels for automated ROIs localization and importance estimation. Our F-CAM transfers the semantic information from the classification task for use in the localization of ROIs, with a focus on small ROIs that characterize medical images. Additionally, we propose an attention compositing module that integrates the generated attention map with transfer function within the DVR pipeline to automate the view-dependent visual emphasis of the ROIs. We demonstrate the superiority of our method compared to existing methods on a multi-modality PET-CT dataset and an MRI dataset.

Multidimensional Analysis of the Adult Human Heart in Health and Disease Using Hierarchical Phase-Contrast Tomography.

Background Current clinical imaging modalities such as CT and MRI provide resolution adequate to diagnose cardiovascular diseases but cannot depict detailed structural features in the heart across length scales. Hierarchical phase-contrast tomography (HiP-CT) uses fourth-generation synchrotron sources with improved x-ray brilliance and high energies to provide micron-resolution imaging of intact adult organs with unprecedented detail. Purpose To evaluate the capability of HiP-CT to depict the macro- to microanatomy of structurally normal and abnormal adult human hearts ex vivo. Materials and Methods Between February 2021 and September 2023, two adult human donor hearts were obtained, fixed in formalin, and prepared using a mixture of crushed agar in a 70% ethanol solution. One heart was from a 63-year-old White male without known cardiac disease, and the other was from an 87-year-old White female with a history of multiple known cardiovascular pathologies including ischemic heart disease, hypertension, and atrial fibrillation. Nondestructive ex vivo imaging of these hearts without exogenous contrast agent was performed using HiP-CT at the European Synchrotron Radiation Facility. Results HiP-CT demonstrated the capacity for high-spatial-resolution, multiscale cardiac imaging ex vivo, revealing histologic-level detail of the myocardium, valves, coronary arteries, and cardiac conduction system across length scales. Virtual sectioning of the cardiac conduction system provided information on fatty infiltration, vascular supply, and pathways between the cardiac nodes and adjacent structures. HiP-CT achieved resolutions ranging from gross (isotropic voxels of approximately 20 µm) to microscopic (approximately 6.4-µm voxel size) to cellular (approximately 2.3-µm voxel size) in scale. The potential for quantitative assessment of features in health and disease was demonstrated. Conclusion HiP-CT provided high-spatial-resolution, three-dimensional images of structurally normal and diseased ex vivo adult human hearts. Whole-heart image volumes were obtained with isotropic voxels of approximately 20 µm, and local regions of interest were obtained with resolution down to 2.3-6.4 µm without the need for sectioning, destructive techniques, or exogenous contrast agents. Published under a CC BY 4.0 license Supplemental material is available for this article. See also the editorial by Bluemke and Pourmorteza in this issue.

Psudo: Exploring Multi-Channel Biomedical Image Data with Spatially and Perceptually Optimized Pseudocoloring.

Over the past century, multichannel fluorescence imaging has been pivotal in myriad scientific breakthroughs by enabling the spatial visualization of proteins within a biological sample. With the shift to digital methods and visualization software, experts can now flexibly pseudocolor and combine image channels, each corresponding to a different protein, to explore their spatial relationships. We thus propose psudo, an interactive system that allows users to create optimal color palettes for multichannel spatial data. In psudo, a novel optimization method generates palettes that maximize the perceptual differences between channels while mitigating confusing color blending in overlapping channels. We integrate this method into a system that allows users to explore multi-channel image data and compare and evaluate color palettes for their data. An interactive lensing approach provides on-demand feedback on channel overlap and a color confusion metric while giving context to the underlying channel values. Color palettes can be applied globally or, using the lens, to local regions of interest. We evaluate our palette optimization approach using three graphical perception tasks in a crowdsourced user study with 150 participants, showing that users are more accurate at discerning and comparing the underlying data using our approach. Additionally, we showcase psudo in a case study exploring the complex immune responses in cancer tissue data with a biologist.

Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology.

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

Breast Cancer-Related Lymphedema Assessed via Tissue Dielectric Constant Measurements.

This review describes the use of tissue dielectric constant (TDC) measurements mainly in the assessment of breast cancer-related lymphedema (BCRL). PubMed, Web of Science, and EMBASE databases were initially searched using criteria that included the terms "dielectric" and "lymphedema." The initial search yielded a total of 131 titles. After removing studies not focused on upper extremity lymphedema, 56 articles remained. These articles, together withrelevant articles from their bibliographies, formed the basis of the review. The findings show the potential utility and applications of TDC measurements to help detect and track BCRL, whether present in limbs, breasts, or trunks. It is reported as a non-invasive, simple-to-use method, with each measurement requiring less than 10 seconds, suggesting its practicality and useability as an in-office or in-clinic screening and tracking method. Although there are various ways to quantitatively evaluate lymphedema, most, if not all, are restricted to measurements on limbs. Thus, one significant advantage of the TDC approach is that almost any local region of interest can be effectively measured and tracked, which, for BCRL, could include specific regions of arms or hands, breasts, and truncal areas.

3D magnetic seed localization for augmented reality in surgery

PurposeFor tumor resection, surgeons need to localize the tumor. For this purpose, a magnetic seed can be inserted into the tumor by a radiologist and, during surgery, a magnetic detection probe informs the distance to the seed for localization. In this case, the surgeon still needs to mentally reconstruct the position of the tumor from the probe’s information. The purpose of this study is to develop and assess a method for 3D localization and visualization of the seed, facilitating the localization of the tumor.MethodsWe propose a method for 3D localization of the magnetic seed by extending the magnetic detection probe with a tracking-based localization. We attach a position sensor (QR-code or optical marker) to the probe in order to track its 3D pose (respectively, using a head-mounted display with a camera or optical tracker). Following an acquisition protocol, the 3D probe tip and seed position are subsequently obtained by solving a system of equations based on the distances and the 3D probe poses.ResultsThe method was evaluated with an optical tracking system. An experimental setup using QR-code tracking (resp. using an optical marker) achieves an average of 1.6 mm (resp. 0.8 mm) 3D distance between the localized seed and the ground truth. Using a breast phantom setup, the average 3D distance is 4.7 mm with a QR-code and 2.1 mm with an optical marker.ConclusionTracking the magnetic detection probe allows 3D localization of a magnetic seed, which opens doors for augmented reality target visualization during surgery. Such an approach should enhance the perception of the localized region of interest during the intervention, especially for breast tumor resection where magnetic seeds can already be used in the protocol.

HSG-MGAF Net: Heterogeneous subgraph-guided multiscale graph attention fusion network for interpretable prediction of whole-slide image

Background and objectivePathological whole slide image (WSI) prediction and region of interest (ROI) localization are important issues in computer-aided diagnosis and postoperative analysis in clinical applications. Existing computer-aided methods for predicting WSI are mainly based on multiple instance learning (MIL) and its variants. However, most of the methods are based on instance independence and identical distribution assumption and performed at a single scale, which not fully exploit the hierarchical multiscale heterogeneous information contained in WSI. MethodsHeterogeneous Subgraph-Guided Multiscale Graph Attention Fusion Network (HSG-MGAF Net) is proposed to build the topology of critical image patches at two scales for adaptive WSI prediction and lesion localization. The HSG-MGAF Net simulates the hierarchical heterogeneous information of WSI through graph and hypergraph at two scales, respectively. This framework not only fully exploits the low-order and potential high-order correlations of image patches at each scale, but also leverages the heterogeneous information of the two scales for adaptive WSI prediction. ResultsWe validate the superiority of the proposed method on the CAMELYON16 and the TCGA- NSCLC, and the results show that HSG-MGAF Net outperforms the state-of-the-art method on both datasets. The average ACC, AUC and F1 score of HSG-MGAF Net can reach 92.7 %/0.951/0.892 and 92.2 %/0.957/0.919, respectively. The obtained heatmaps can also localize the positive regions more accurately, which have great consistency with the pixel-level labels. ConclusionsThe results demonstrate that HSG-MGAF Net outperforms existing weakly supervised learning methods by introducing critical heterogeneous information between the two scales. This approach paves the way for further research on light weighted heterogeneous graph-based WSI prediction and ROI localization.

Enhanced YOLOv5s + DeepSORT method for highway vehicle speed detection and multi-sensor verification

Addressing the need for vehicle speed measurement in traffic surveillance, this study introduces an enhanced scheme combining YOLOv5s detection with Deep SORT tracking. Tailored to the characteristics of highway traffic and vehicle features, the dataset data augmentation process was initially optimized. To improve the detector’s recognition capabilities, the Swin Transformer Block module was incorporated, enhancing the model’s ability to capture local regions of interest. CIoU loss was employed as the loss function for the vehicle detection network, accelerating model convergence and achieving higher regression accuracy. The Mish activation function was utilized to reduce computational overhead and enhance convergence speed. The structure of the Deep SORT appearance feature extraction network was modified, and it was retrained on a vehicle re-identification dataset to mitigate identity switches due to obstructions. Subsequently, using known references in the image such as lane markers and contour labels, the transformation from image pixel coordinates to actual coordinates was accomplished. Finally, vehicle speed was measured by computing the average of instantaneous speeds across multiple frames. Through radar and video Multi-Sensor Verification, the experimental results show that the mean Average Precision (mAP) for target detection consistently exceeds 90%. The effective measurement distance for speed measurement is around 140 m, with the absolute speed error generally within 1–8 km/h, meeting the accuracy requirements for speed measurement. The proposed model is reliable and fully applicable to highway scenarios.

Liver fat volume fraction measurements based on multi-material decomposition algorithm in patients with nonalcoholic fatty liver disease: the influences of blood vessel, location, and iodine contrast

BackgroundIn recent years, spectral CT-derived liver fat quantification method named multi-material decomposition (MMD) is playing an increasingly important role as an imaging biomarker of hepatic steatosis. However, there are various measurement ways with various results among different researches, and the impact of measurement methods on the research results is unknown. The aim of this study is to evaluate the reproducibility of liver fat volume fraction (FVF) using MMD algorithm in nonalcoholic fatty liver disease (NAFLD) patients when taking blood vessel, location, and iodine contrast into account during measurement.MethodsThis retrospective study was approved by the institutional ethics committee, and the requirement for informed consent was waived because of the retrospective nature of the study. 101 patients with NAFLD were enrolled in this study. Participants underwent non-contrast phase (NCP) and two-phase enhanced CT scanning (late arterial phase (LAP) and portal vein phase (PVP)) with spectral mode. Regions of interest (ROIs) were placed at right posterior lobe (RPL), right anterior lobe (RAL) and left lateral lobe (LLL) to obtain FVF values on liver fat images without and with the reference of enhanced CT images. The differences of FVF values measured under different conditions (ROI locations, with/without enhancement reference, NCP and enhanced phases) were compared. Friedman test was used to compare FVF values among three phases for each lobe, while the consistency of FVF values was assessed between each two phases using Bland–Altman analysis.ResultsSignificant difference was found between FVF values obtained without and with the reference of enhanced CT images. There was no significant difference about FVF values obtained from NCP images under the reference of enhanced CT images between any two lobes or among three lobes. The FVF value increased after the contrast injection, and there were significant differences in the FVF values among three scanning phases. Poor consistencies of FVF values between each two phases were found in each lobe by Bland–Altman analysis.ConclusionMMD algorithm quantifying hepatic fat was reproducible among different lobes, while was influenced by blood vessel and iodine contrast.

Spatial-temporal characterization of photoemission in a streak-mode dynamic transmission electron microscope.

A long-standing motivation driving high-speed electron microscopy development is to capture phase transformations and material dynamics in real time with high spatial and temporal resolution. Current dynamic transmission electron microscopes (DTEMs) are limited to nanosecond temporal resolution and the ability to capture only a few frames of a transient event. With the motivation to overcome these limitations, we present our progress in developing a streak-mode DTEM (SM-DTEM) and demonstrate the recovery of picosecond images with high frame sequence depth. We first demonstrate that a zero-dimensional (0D) SM-DTEM can provide temporal information on any local region of interest with a 0.37 μm diameter, a 20-GHz sampling rate, and 1200 data points in the recorded trace. We use this method to characterize the temporal profile of the photoemitted electron pulse, finding that it deviates from the incident ultraviolet laser pulse and contains an unexpected peak near its onset. Then, we demonstrate a two-dimensional (2D) SM-DTEM, which uses compressed-sensing-based tomographic imaging to recover a full spatiotemporal photoemission profile over a 1.85-μm-diameter field of view with nanoscale spatial resolution, 370-ps inter-frame interval, and 140-frame sequence depth in a 50-ns time window. Finally, a perspective is given on the instrumental modifications necessary to further develop this promising technique with the goal of decreasing the time to capture a 2D SM-DTEM dataset.

Deep-DM: Deep-driven deformable model for 3D image segmentation using limited data.

Objective - Medical image segmentation is essential for several clinical tasks, including diagnosis, surgical and treatment planning, and image-guided interventions. Deep Learning (DL) methods have become the state-of-the-art for several image segmentation scenarios. However, a large and well-annotated dataset is required to effectively train a DL model, which is usually difficult to obtain in clinical practice, especially for 3D images. Methods - In this paper, we proposed Deep-DM, a learning-guided deformable model framework for 3D medical imaging segmentation using limited training data. In the proposed method, an energy function is learned by a Convolutional Neural Network (CNN) and integrated into an explicit deformable model to drive the evolution of an initial surface towards the object to segment. Specifically, the learning-based energy function is iteratively retrieved from localized anatomical representations of the image containing the image information around the evolving surface at each iteration. By focusing on localized regions of interest, this representation excludes irrelevant image information, facilitating the learning process. Results and conclusion - The performance of the proposed method is demonstrated for the tasks of left ventricle and fetal head segmentation in ultrasound, left atrium segmentation in Magnetic Resonance, and bladder segmentation in Computed Tomography, using different numbers of training volumes in each study. The results obtained showed the feasibility of the proposed method to segment different anatomical structures in different imaging modalities. Moreover, the results also showed that the proposed approach is less dependent on the size of the training dataset in comparison with state-of-the-art DL-based segmentation methods, outperforming them for all tasks when a low number of samples is available. Significance - Overall, by offering a more robust and less data-intensive approach to accurately segmenting anatomical structures, the proposed method has the potential to enhance clinical tasks that require image segmentation strategies.

MATLAB-Based Algorithm and Software for Analysis of Wavy Collagen Fibers.

Knowledge of soft tissue fiber structure is necessary for accurate characterization and modeling of their mechanical response. Fiber configuration and structure informs both our understanding of healthy tissue physiology and of pathological processes resulting from diseased states. This study develops an automatic algorithm to simultaneously estimate fiber global orientation, abundance, and waviness in an investigated image. To our best knowledge, this is the first validated algorithm which can reliably separate fiber waviness from its global orientation for considerably wavy fibers. This is much needed feature for biological tissue characterization. The algorithm is based on incremental movement of local regions of interest (ROI) and analyzes two-dimensional images. Pixels belonging to the fiber are identified in the ROI, and ROI movement is determined according to local orientation of fiber within the ROI. The algorithm is validated with artificial images and ten images of porcine trachea containing wavy fibers. In each image, 80-120 fibers were tracked manually to serve as verification. The coefficient of determination R2 between curve lengths and histograms documenting the fiber waviness and global orientation were used as metrics for analysis. Verification-confirmed results were independent of image rotation and degree of fiber waviness, with curve length accuracy demonstrated to be below 1% of fiber curved length. Validation-confirmed median and interquartile range of R2, respectively, were 0.90 and 0.05 for curved length, 0.92 and 0.07 for waviness, and 0.96 and 0.04 for global orientation histograms. Software constructed from the proposed algorithm was able to track one fiber in about 1.1 s using a typical office computer. The proposed algorithm can reliably and accurately estimate fiber waviness, curve length, and global orientation simultaneously, moving beyond the limitations of prior methods.

Artificial intelligence for the detection of sacroiliitis on magnetic resonance imaging in patients with axial spondyloarthritis.

Magnetic resonance imaging (MRI) is important for the early detection of axial spondyloarthritis (axSpA). We developed an artificial intelligence (AI) model for detecting sacroiliitis in patients with axSpA using MRI. This study included MRI examinations of patients who underwent semi-coronal MRI scans of the sacroiliac joints owing to chronic back pain with short tau inversion recovery (STIR) sequences between January 2010 and December 2021. Sacroiliitis was defined as a positive MRI finding according to the ASAS classification criteria for axSpA. We developed a two-stage framework. First, the Faster R-CNN network extracted regions of interest (ROIs) to localize the sacroiliac joints. Maximum intensity projection (MIP) of three consecutive slices was used to mimic the reading of two adjacent slices. Second, the VGG-19 network determined the presence of sacroiliitis in localized ROIs. We augmented the positive dataset six-fold. The sacroiliitis classification performance was measured using the sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). The prediction models were evaluated using three-round three-fold cross-validation. A total of 296 participants with 4,746 MRI slices were included in the study. Sacroiliitis was identified in 864 MRI slices of 119 participants. The mean sensitivity, specificity, and AUROC for the detection of sacroiliitis were 0.725 (95% CI, 0.705-0.745), 0.936 (95% CI, 0.924-0.947), and 0.830 (95%CI, 0.792-0.868), respectively, at the image level and 0.947 (95% CI, 0.912-0.982), 0.691 (95% CI, 0.603-0.779), and 0.816 (95% CI, 0.776-0.856), respectively, at the patient level. In the original model, without using MIP and dataset augmentation, the mean sensitivity, specificity, and AUROC were 0.517 (95% CI, 0.493-0.780), 0.944 (95% CI, 0.933-0.955), and 0.731 (95% CI, 0.681-0.780), respectively, at the image level and 0.806 (95% CI, 0.729-0.883), 0.617 (95% CI, 0.523-0.711), and 0.711 (95% CI, 0.660-0.763), respectively, at the patient level. The performance was improved by MIP techniques and data augmentation. An AI model was developed for the detection of sacroiliitis using MRI, compatible with the ASAS criteria for axSpA, with the potential to aid MRI application in a wider clinical setting.

Assessment of CBCT gray value in different regions-of-interest and fields-of-view compared to Hounsfield unit.

Different factors can affect the discrepancy between the gray value (GV) measurements obtained from CBCT and the Hounsfield unit (HU) derived from multidetector CT (MDCT), which is considered the gold-standard density scale. This study aimed to explore the impact of region of interest (ROI) location and field of view (FOV) size on the difference between these two scales as a potential source of error. Three phantoms, each consisting of a water-filled plastic bin containing a dry dentate human skull, were prepared. CBCT scans were conducted using the NewTom VGi evo system, while MDCT scans were performed using Philips system. Three different FOV sizes (8 × 8 cm, 8 × 12 cm, and 12 × 15 cm) were used, and the GVs obtained from eight distinct ROIs were compared with the HUs from the MDCT scans. The ROIs included dental and bony regions within the anterior and posterior areas of both jaws. Statistical analyses were performed using SPSS v. 26. The GVs derived from CBCT images were significantly influenced by both ROI location and FOV size (p < 0.05 for both factors). Following the comparison between GVs and HUs, the anterior mandibular bone ROI represented the minimum error, while the posterior mandibular teeth exhibited the maximum error. Moreover, the 8 × 8 cm and 12 × 15 cm FOVs resulted in the lowest and highest degrees of GV error, respectively. The ROI location and the FOV size can significantly affect the GVs obtained from CBCT images. It is not recommended to use the GV scale within the posterior mandibular teeth region due to the potential for error. Additionally, selecting smaller FOV sizes, such as 8 × 8 cm, can provide GVs closer to the gold-standard numbers.

Generalized weld bead region of interest localization and improved faster R-CNN for weld defect recognition

Pipeline is the main transportation. In order to ensure the safety of pipeline transportation, the research on automatic recognition of defect features in X-ray film digital images has become an important research interest. Deep learning is highly favored via its powerful feature of self-extraction ability, which avoids the complexity and uncertainty associated with manual extraction in traditional algorithms. Nevertheless, in weld seam X-ray images, the weld bead only occupies a small portion of the entire image, and the welding defects exclusively exist within the weld bead. If the weld bead area can be determined first, followed by defect extraction within the weld bead, which will undoubtedly improve the accuracy of defect detection. Therefore, this paper first proposes a simple and general two-stage weld bead ROI (region of interest) extraction algorithm, which roughly determines weld bead ROI based on the distribution of the weld bead center and accurately locates the boundaries of the weld bead ROI based on the vertical distance curve. Then, to address the issues of Faster R-CNN (region-based convolutional neural networks) only utilizing the highest-level features and the poor adaptability of prior boxes setting, FPN (feature pyramid network) and CBAM (convolutional attention mechanism module) are incorporated to the feature extraction module and K-means clustering is employed to modify the setting of prior boxes. Experimental results conducted on two weld seam datasets demonstrate the effectiveness of the two-stage weld bead ROI extraction algorithm compared with the Otsu algorithm. The mAP (mean average precision) of defect recognition based on Faster R-CNN is 80.1%, which is greatly higher than the mAP achieved without extracting weld ROI (48.7%). In addition, experimental verification is performed on the Improved Faster R-CNN algorithm for identifying weld defects, and the cumulative improvement in mAP reached 6.8%, demonstrating the effectiveness and applicability of the proposed method.

Minimal resin embedding of SBF-SEM samples reduces charging and facilitates finding a surface-linked region of interest

BackgroundFor decoding the mechanism of how cells and organs function information on their ultrastructure is essential. High-resolution 3D imaging has revolutionized morphology. Serial block face scanning electron microscopy (SBF-SEM) offers non-laborious, automated imaging in 3D of up to ~ 1 mm3 large biological objects at nanometer-scale resolution. For many samples there are obstacles. Quality imaging is often hampered by charging effects, which originate in the nonconductive resin used for embedding. Especially, if the imaged region of interest (ROI) includes the surface of the sample and neighbours the empty resin, which insulates the object. This extra resin also obscures the sample’s morphology, thus making navigation to the ROI difficult.ResultsUsing the example of small arthropods and a fish roe we describe a workflow to prepare samples for SBF-SEM using the minimal resin (MR) embedding method. We show that for imaging of surface structures this simple approach conveniently tackles and solves both of the two major problems—charging and ROI localization—that complicate imaging of SBF-SEM samples embedded in an excess of overlying resin. As the surface ROI is not masked by the resin, samples can be precisely trimmed before they are placed into the imaging chamber. The initial approaching step is fast and easy. No extra trimming inside the microscope is necessary. Importantly, charging is absent or greatly reduced meaning that imaging can be accomplished under good vacuum conditions, typically at the optimal high vacuum. This leads to better resolution, better signal to noise ratio, and faster image acquisition.ConclusionsIn MR embedded samples charging is minimized and ROI easily targeted. MR embedding does not require any special equipment or skills. It saves effort, microscope time and eventually leads to high quality data. Studies on surface-linked ROIs, or any samples normally surrounded by the excess of resin, would benefit from adopting the technique.

Boundary Value Caching for Walk on Spheres

Grid-free Monte Carlo methods such as walk on spheres can be used to solve elliptic partial differential equations without mesh generation or global solves. However, such methods independently estimate the solution at every point, and hence do not take advantage of the high spatial regularity of solutions to elliptic problems. We propose a fast caching strategy which first estimates solution values and derivatives at randomly sampled points along the boundary of the domain (or a local region of interest). These cached values then provide cheap, output-sensitive evaluation of the solution (or its gradient) at interior points, via a boundary integral formulation. Unlike classic boundary integral methods, our caching scheme introduces zero statistical bias and does not require a dense global solve. Moreover we can handle imperfect geometry (e.g., with self-intersections) and detailed boundary/source terms without repairing or resampling the boundary representation. Overall, our scheme is similar in spirit to virtual point light methods from photorealistic rendering: it suppresses the typical salt-and-pepper noise characteristic of independent Monte Carlo estimates, while still retaining the many advantages of Monte Carlo solvers: progressive evaluation, trivial parallelization, geometric robustness, etc. We validate our approach using test problems from visual and geometric computing.