Anisotropic Resolution Research Articles

Deformable dose prediction network based on hybrid 2D and 3D convolution for nasopharyngeal carcinoma radiotherapy.

Radiotherapy is recognized as the primary treatment for nasopharyngeal carcinoma (NPC). Rapid and accurate dose prediction is crucial for enhancing the quality and efficiency of radiotherapy planning. However, the current dose prediction model based on 2D architecture cannot effectively learn the spatial information among slices. Although some studies have explored the incorporation of interslice features through 3D architecture, the resolution properties of medical image anisotropy significantly limit the predictive performance. To address the issues, we propose a novel deformable dose prediction network based on hybrid 2D and 3D convolution for NPC radiotherapy. Specifically, the proposed model innovatively incorporates a 2.5D architecture based on hybrid 2D and 3D convolution, and effectively utilizes the directional information within anisotropic resolutions to achieve cross-scale feature extraction. Additionally, deformable convolution is introduced into the model to enhance the receptive field and effectively handle multi-scale spatial transformations. To improve channel correlation and reduce redundant features, we design a Residual Deformable Squeeze-and-Excitation Module. We conduct extensive experiments on an internal dataset, and the results show that the proposed model outperforms other existing methods in most dosimetric criteria. The proposed model has superior dose prediction performance in NPC radiotherapy, and has important clinical significance for assisting physicists to optimize the treatment plan and improve standardization of radiotherapy planning. The source code is available at https://github.com/CDUTJ102/2.5D-Deformable-UNet .

CryoVesNet: A dedicated framework for synaptic vesicle segmentation in cryo-electron tomograms.

Cryo-electron tomography (cryo-ET) has the potential to reveal cell structure down to atomic resolution. Nevertheless, cellular cryo-ET data is highly complex, requiring image segmentation for visualization and quantification of subcellular structures. Due to noise and anisotropic resolution in cryo-ET data, automatic segmentation based on classical computer vision approaches usually does not perform satisfactorily. Communication between neurons relies on neurotransmitter-filled synaptic vesicle (SV) exocytosis. Cryo-ET study of the spatial organization of SVs and their interconnections allows a better understanding of the mechanisms of exocytosis regulation. Accurate SV segmentation is a prerequisite to obtaining a faithful connectivity representation. Hundreds of SVs are present in a synapse, and their manual segmentation is a bottleneck. We addressed this by designing a workflow consisting of a convolutional network followed by post-processing steps. Alongside, we provide an interactive tool for accurately segmenting spherical vesicles. Our pipeline can in principle segment spherical vesicles in any cell type as well as extracellular and in vitro spherical vesicles.

Evaluation of Myocarditis with a Free-breathing 3D Isotropic Whole-Heart Joint T1 and T2 Mapping Sequence

BackgroundThe diagnosis of myocarditis by CMR requires the use of T2 and T1 weighted imaging, ideally incorporating parametric mapping. Current 2D mapping sequences are acquired sequentially and involve multiple breath-holds resulting in prolonged scan times and anisotropic image resolution. We developed an isotropic free-breathing 3D whole-heart sequence which allows simultaneous T1 and T2 mapping and validated it in patients with suspected acute myocarditis. MethodsEighteen healthy volunteers and 28 patients with suspected myocarditis underwent conventional 2D T1 and T2 mapping with whole heart coverage and 3D joint T1/T2 mapping on a 1.5T scanner. Acquisition time, image quality, and diagnostic performance were compared. Qualitative analysis was performed using a 4-point Likert scale. Bland-Altman plots were used to assess the quantitative agreement between 2D and 3D sequences. ResultsThe 3D T1/T2 sequence was acquired in 8mins 26s under free breathing, whereas 2D T1 and T2 sequences were acquired with breath holds in 11mins 44s (p=0.0001). All 2D images were diagnostic. For 3D images, 89% of T1 and 96% of T2 images were diagnostic with no significant difference in the proportion of diagnostic images for the 3D and 2D T1 (p=0.2482) and T2 maps (p=1.0000). Systematic bias in T1 was noted with biases of 102ms, 115ms, and 152ms for basal-apical segments, with a larger bias for higher T1 values. Good agreement between T2 values for 3D and 2D techniques was found (bias of 1.8ms, 3.9ms, and 3.6ms for basal-apical segments). The sensitivity and specificity of the 3D sequence for diagnosing acute myocarditis was 74% (95% confidence interval [CI] 49-91%) and 83% (36-100%) respectively, with an estimated c-statistic (95% CI) of 0.85 (0.79-0.91) and no statistically significant difference between the 2D and 3D sequences for the detection of acute myocarditis for T1 (p=0.2207) or T2 (p=1.0000). ConclusionFree-breathing whole heart 3D joint T1/T2 mapping was comparable to 2D mapping sequences with respect to diagnostic performance, but with the added advantages of free-breathing, and shorter scan times. Further work is required to address the bias noted at high T1 values, but this did not significantly impact on diagnostic accuracy.

Simulating plate and shell structures with anisotropic resolution using adaptive smoothed particle hydrodynamics

When simulating plate and shell structures characterized by large aspect ratios, reduced-dimensional models are frequently employed due to their notable reduction in computational overhead in contrast to traditional isotropic full-dimensional models. However, in scenarios involving variations in the thickness direction, where adequate resolution in this dimension is required, reduced-dimensional models exhibit limitations. To capture variations in the thickness direction while simultaneously mitigating computational costs, an anisotropic full-dimensional model, integrated with an adaptive smoothed particle hydrodynamics method (ASPH), is developed for simulating behaviors of plate and shell structures in this study. The correction matrix, which is applied to ensure the first-order consistency, is modified accordingly by incorporating the nonisotropic kernel into it within the total Lagrangian framework of ASPH. A series of numerical examples, along with a specific application concerning the deformation of a porous film due to nonuniform internal fluid pressure in the thickness direction, are conducted to assess the computational accuracy and efficiency of the proposed ASPH method. Comparative analyses of our results against reference data and traditional isotropic SPH solutions demonstrate close agreements, affirming the suitability of the present ASPH method across various scenarios.

Modeling Ligands into Maps Derived from Electron Cryomicroscopy.

Deciphering the protein-ligand interactions in a macromolecular complex is crucial for understanding the molecular mechanism, underlying biological processes, and drug development. In recent years, cryogenic sample electron microscopy (cryoEM) has emerged as a powerful technique to determine the structures of macromolecules and to investigate the mode of ligand binding at near-atomic resolution. Identifying and modeling non-protein molecules in cryoEM maps is often challenging due to anisotropic resolution across the molecule of interest and inherent noise in the data. In this article, the readers are introduced to various software and methods currently used for ligand identification, model building, and refinement of atomic coordinates using selected macromolecules. One of the simplest ways to identify the presence of a ligand, as illustrated with the enolase enzyme, is to subtract the two maps obtained with and without the ligand. The extra density of the ligand is likely to stand out in the difference map even at a higher threshold. There are instances, as shown in the case of metabotropic Glutamate receptor mGlu5, when such simple difference maps cannot be generated. The recently introduced method of deriving the Fo-Fc omit map can serve as a tool for validating and demonstrating the presence of the ligand. Finally, using the well-studied β-galactosidase as an example, the effect of resolution on modeling the ligands and solvent molecules in cryoEM maps is analyzed, and an outlook on how cryoEM can be used in drug discovery is presented.

Super resolution using sparse sampling at portable ultra-low field MR

Ultra-low field (ULF) magnetic resonance imaging (MRI) holds the potential to make MRI more accessible, given its cost-effectiveness, reduced power requirements, and portability. However, signal-to-noise ratio (SNR) drops with field strength, necessitating imaging with lower resolution and longer scan times. This study introduces a novel Fourier-based Super Resolution (FouSR) approach, designed to enhance the resolution of ULF MRI images with minimal increase in total scan time. FouSR combines spatial frequencies from two orthogonal ULF images of anisotropic resolution to create an isotropic T2-weighted fluid-attenuated inversion recovery (FLAIR) image. We hypothesized that FouSR could effectively recover information from under-sampled slice directions, thereby improving the delineation of multiple sclerosis (MS) lesions and other significant anatomical features. Importantly, the FouSR algorithm can be implemented on the scanner with changes to the k-space trajectory. Paired ULF (Hyperfine SWOOP, 0.064 tesla) and high field (Siemens, Skyra, 3 Tesla) FLAIR scans were collected on the same day from a phantom and a cohort of 10 participants with MS or suspected MS (6 female; mean ± SD age: 44.1 ± 4.1). ULF scans were acquired along both coronal and axial planes, featuring an in-plane resolution of 1.7 mm × 1.7 mm with a slice thickness of 5 mm. FouSR was evaluated against registered ULF coronal and axial scans, their average (ULF average) and a gold standard SR (ANTs SR). FouSR exhibited higher SNR (47.96 ± 12.6) compared to ULF coronal (36.7 ± 12.2) and higher lesion conspicuity (0.12 ± 0.06) compared to ULF axial (0.13 ± 0.07) but did not exhibit any significant differences contrast-to-noise-ratio (CNR) compared to other methods in patient scans. However, FouSR demonstrated superior image sharpness (0.025 ± 0.0040) compared to all other techniques (ULF coronal 0.021 ± 0.0037, q = 5.9, p-adj. = 0.011; ULF axial 0.018 ± 0.0026, q = 11.1, p-adj. = 0.0001; ULF average 0.019 ± 0.0034, q = 24.2, p-adj. < 0.0001) and higher lesion sharpness (−0.97 ± 0.31) when compared to the ULF average (−1.02 ± 0.37, t(543) = −10.174, p = <0.0001). Average blinded qualitative assessment by three experienced MS neurologists showed no significant difference in WML and sulci or gyri visualization between FouSR and other methods. FouSR can, in principle, be implemented on the scanner to produce clinically useful FLAIR images at higher resolution on the fly, providing a valuable tool for visualizing lesions and other anatomical structures in MS.

HCA-DAN: hierarchical class-aware domain adaptive network for gastric tumor segmentation in 3D CT images

BackgroundAccurate segmentation of gastric tumors from CT scans provides useful image information for guiding the diagnosis and treatment of gastric cancer. However, automated gastric tumor segmentation from 3D CT images faces several challenges. The large variation of anisotropic spatial resolution limits the ability of 3D convolutional neural networks (CNNs) to learn features from different views. The background texture of gastric tumor is complex, and its size, shape and intensity distribution are highly variable, which makes it more difficult for deep learning methods to capture the boundary. In particular, while multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity.MethodsIn this study, we propose a new cross-center 3D tumor segmentation method named Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale context features from the CT images with anisotropic resolution, and a hierarchical class-aware domain alignment (HCADA) module for adaptively aligning multi-scale context features across two domains by integrating a class attention map with class-specific information. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers and validate its segmentation performance in both in-center and cross-center test scenarios.ResultsOur baseline segmentation network (i.e., AsTr) achieves best results compared to other 3D segmentation models, with a mean dice similarity coefficient (DSC) of 59.26%, 55.97%, 48.83% and 67.28% in four in-center test tasks, and with a DSC of 56.42%, 55.94%, 46.54% and 60.62% in four cross-center test tasks. In addition, the proposed cross-center segmentation network (i.e., HCA-DAN) obtains excellent results compared to other unsupervised domain adaptation methods, with a DSC of 58.36%, 56.72%, 49.25%, and 62.20% in four cross-center test tasks.ConclusionsComprehensive experimental results demonstrate that the proposed method outperforms compared methods on this multi-center database and is promising for routine clinical workflows.

Hybrid dual mean-teacher network with double-uncertainty guidance for semi-supervised segmentation of magnetic resonance images

Semi-supervised learning has made significant progress in medical image segmentation. However, existing methods primarily utilize information from a single dimensionality, resulting in sub-optimal performance on challenging magnetic resonance imaging (MRI) data with multiple segmentation objects and anisotropic resolution. To address this issue, we present a Hybrid Dual Mean-Teacher (HD-Teacher) model with hybrid, semi-supervised, and multi-task learning to achieve effective semi-supervised segmentation. HD-Teacher employs a 2D and a 3D mean-teacher network to produce segmentation labels and signed distance fields from the hybrid information captured in both dimensionalities. This hybrid mechanism allows HD-Teacher to utilize features from 2D, 3D, or both dimensions as needed. Outputs from 2D and 3D teacher models are dynamically combined based on confidence scores, forming a single hybrid prediction with estimated uncertainty. We propose a hybrid regularization module to encourage both student models to produce results close to the uncertainty-weighted hybrid prediction to further improve their feature extraction capability. Extensive experiments of binary and multi-class segmentation conducted on three MRI datasets demonstrated that the proposed framework could (1) significantly outperform state-of-the-art semi-supervised methods (2) surpass a fully-supervised VNet trained on substantially more annotated data, and (3) perform on par with human raters on muscle and bone segmentation task. Code will be available at https://github.com/ThisGame42/Hybrid-Teacher.

SAH-NET: Structure-Aware Hierarchical Network for Clustered Microcalcification Classification in Digital Breast Tomosynthesis.

Benign and malignant classification of clustered microcalcifications (MCs) in digital breast tomosynthesis (DBT) is an essential task in computer-aided diagnosis. However, due to the anisotropic resolution of DBT, three-dimensional (3-D) convolutional neural network (CNN)-based methods cannot extract hierarchical features efficiently. Moreover, the sparse distribution of MC points in the cluster makes it difficult for the CNN to extract discriminative structural information for classification. To comprehensively address these challenges, we propose a novel structure-aware hierarchical network (SAH-Net) for benign and malignant classification of clustered MC in a DBT volume. Specifically, the two-dimensional (2-D) group convolution is used to extract intraslice features. The one-to-one correspondence between group convolutions and slices ensures the independence of hierarchical feature extraction. Then, a partial deformable Transformer-based 3-D structural feature learning module is proposed to capture the long-range dependency between MC points in the cluster. We evaluate the proposed method on an in-house dataset with 495 clustered MCs collected from 462 DBT images. Experimental results confirm the validity of our proposed modules. The results also show that the proposed SAH-Net outperforms several other representative methods on this topic, and achieves the best classification result, with an area under the receiver operation curve (AUC) of 86.87%. The implementation of the proposed model is available at https://github.com/sunhaotian130911/SAHNet.

Combination of time domain-system matrix and x-space methods to reconstruct magnetic particle images with isotropic resolution

Objective. Imaging of superparamagnetic iron oxide nanoparticles based on their non-linear response to alternating magnetic fields shows promise for imaging cells and vasculature in healthy and diseased tissue. Such imaging can be achieved through x-space reconstruction typically along a unidirectional Cartesian trajectory, which rapidly convolutes the particle distribution with a ‘anisotropic blurring’ point spread function (PSF), leading to images with anisotropic resolution. Approach. Here we propose combining the time domine-system matrix and x-space reconstruction methods into a forward model, where the output of the forward model is the PSF-blurred x-space reconstructed image. We then treat the blur as an inverse problem solved by Kaczmarz iteration. Main results. After we have proposed the method optimization, the normal resolution of simulation and device images has been increased from 3.5 mm and 5.25 mm to 1.5 mm and 3.25 mm, which has reached the level in the tangential resolution. Quantitative indicators of image quality such as PSNR and SSIM have also been greatly improved. Significance. Simulation and imaging of real phantoms indicate that our approach provides better isotropic resolution and image quality than the x-space method alone or other methods for removing PSF blur. Using our proposed method to optimize the image quality of x-space reconstructed images using unidirectional Cartesian trajectories, it will promote the clinical application of MPI in the future.

Overcoming resolution attenuation during tilted cryo-EM data collection

Structural biology efforts using cryogenic electron microscopy are frequently stifled by specimens adopting “preferred orientations” on grids, leading to anisotropic map resolution and impeding structure determination. Tilting the specimen stage during data collection is a generalizable solution but has historically led to substantial resolution attenuation. Here, we develop updated data collection and image processing workflows and demonstrate, using multiple specimens, that resolution attenuation is negligible or significantly reduced across tilt angles. Reconstructions with and without the stage tilted as high as 60° are virtually indistinguishable. These strategies allowed the reconstruction to 3 Å resolution of a bacterial RNA polymerase with preferred orientation, containing an unnatural nucleotide for studying novel base pair recognition. Furthermore, we present a quantitative framework that allows cryo-EM practitioners to define an optimal tilt angle during data acquisition. These results reinforce the utility of employing stage tilt for data collection and provide quantitative metrics to obtain isotropic maps.

AI-driven projection tomography with multicore fibre-optic cell rotation

Optical tomography has emerged as a non-invasive imaging method, providing three-dimensional insights into subcellular structures and thereby enabling a deeper understanding of cellular functions, interactions, and processes. Conventional optical tomography methods are constrained by a limited illumination scanning range, leading to anisotropic resolution and incomplete imaging of cellular structures. To overcome this problem, we employ a compact multi-core fibre-optic cell rotator system that facilitates precise optical manipulation of cells within a microfluidic chip, achieving full-angle projection tomography with isotropic resolution. Moreover, we demonstrate an AI-driven tomographic reconstruction workflow, which can be a paradigm shift from conventional computational methods, often demanding manual processing, to a fully autonomous process. The performance of the proposed cell rotation tomography approach is validated through the three-dimensional reconstruction of cell phantoms and HL60 human cancer cells. The versatility of this learning-based tomographic reconstruction workflow paves the way for its broad application across diverse tomographic imaging modalities, including but not limited to flow cytometry tomography and acoustic rotation tomography. Therefore, this AI-driven approach can propel advancements in cell biology, aiding in the inception of pioneering therapeutics, and augmenting early-stage cancer diagnostics.

Effect of detector placement on joint estimation in X-ray fluorescence emission tomography.

Imaging the spatial distribution of low concentrations of metal is a growing problem of interest with applications in medical and material sciences. X-ray fluorescence emission tomography (XFET) is an emerging metal mapping imaging modality with potential sensitivity improvements and practical advantages over other methods. However, XFET detector placement must first be optimized to ensure accurate metal density quantification and adequate spatial resolution. In this work, we first use singular value decomposition of the imaging model and eigendecomposition of the object-specific Fisher information matrix to study how detector arrangement affects spatial resolution and feature preservation. We then perform joint image reconstructions of a numerical gold phantom. For this phantom, we show that two parallel detectors provide metal quantification with similar accuracy to four detectors, despite the resulting anisotropic spatial resolution in the attenuation map estimate. Two orthogonal detectors provide improved spatial resolution along one axis, but underestimate the metal concentration in distant regions. Therefore, this work demonstrates the minor effect of using fewer, but strategically placed, detectors in the case where detector placement is restricted. This work is a critical investigation into the limitations and capabilities of XFET prior to its translation to preclinical and benchtop uses.

Isotropic multi-scale neuronal reconstruction from high-ratio expansion microscopy with contrastive unsupervised deep generative models

Background and objectiveCurrent methods for imaging reconstruction from high-ratio expansion microscopy (ExM) data are limited by anisotropic optical resolution and the requirement for extensive manual annotation, creating a significant bottleneck in the analysis of complex neuronal structures. MethodsWe devised an innovative approach called the IsoGAN model, which utilizes a contrastive unsupervised generative adversarial network to sidestep these constraints. This model leverages multi-scale and isotropic neuron/protein/blood vessel morphology data to generate high-fidelity 3D representations of these structures, eliminating the need for rigorous manual annotation and supervision. The IsoGAN model introduces simplified structures with idealized morphologies as shape priors to ensure high consistency in the generated neuronal profiles across all points in space and scalability for arbitrarily large volumes. ResultsThe efficacy of the IsoGAN model in accurately reconstructing complex neuronal structures was quantitatively assessed by examining the consistency between the axial and lateral views and identifying a reduction in erroneous imaging artifacts. The IsoGAN model accurately reconstructed complex neuronal structures, as evidenced by the consistency between the axial and lateral views and a reduction in erroneous imaging artifacts, and can be further applied to various biological samples. ConclusionWith its ability to generate detailed 3D neurons/proteins/blood vessel structures using significantly fewer axial view images, IsoGAN can streamline the process of imaging reconstruction while maintaining the necessary detail, offering a transformative solution to the existing limitations in high-throughput morphology analysis across different structures.

Fabrication of Monolayer Graphene-Coated Grids for Cryoelectron Microscopy.

Cryogenic electron microscopy (cryoEM) has emerged as a powerful technique for probing the atomic structure of macromolecular complexes. Sample preparation for cryoEM requires preserving specimens in a thin layer of vitreous ice, typically suspended within the holes of a fenestrated support film. However, all commonly used sample preparation approaches for cryoEM studies expose the specimen to the air-water interface, introducing a strong hydrophobic effect on the specimen that often results in denaturation, aggregation, and complex dissociation. Further, preferred hydrophobic interactions between regions of the specimen and the air-water interface impact the orientations adopted by the macromolecules, resulting in 3D reconstructions with anisotropic directional resolution. Adsorption of cryoEM specimens to a monolayer of graphene has been shown to help mitigate interactions with the air-water interface while minimizing the introduction of background noise. Graphene supports also offer the benefit of substantially lowering the required concentration of proteins required for cryoEM imaging. Despite the advantages of these supports, graphene-coated grids are not widely used by the cryoEM community due to the prohibitive expense of commercial options and the challenges associated with large-scale in-house production. This paper describes an efficient method for preparing batches of cryoEM grids that have nearly full coverage of monolayer graphene.

Cyclic stretching combined with cell-cell adhesion is sufficient for inducing cell intercalation

Although the important role of cell intercalation within a collective has long been recognized particularly for morphogenesis, the underlying mechanism remains poorly understood. Here we investigate the possibility that cellular responses to cyclic stretching play a major role in this process. By applying synchronized imaging and cyclic stretching to epithelial cells cultured on micropatterned polyacrylamide (PAA) substrates, we discovered that uniaxial cyclic stretching induces cell intercalation along with cell shape change and cell-cell interfacial remodeling. The process involved intermediate steps as previously reported for cell intercalation during embryonic morphogenesis, including the appearance of cell vertices, anisotropic vertex resolution, and directional expansion of cell-cell interface. Using mathematical modeling, we further found that cell shape change in conjunction with dynamic cell-cell adhesions was sufficient to account for the observations. Further investigation with small-molecule inhibitors indicated that disruption of myosin II activities suppressed cyclic stretching-induced intercalation while inhibiting the appearance of oriented vertices. Inhibition of Wnt signaling did not suppress stretch-induced cell shape change but disrupted cell intercalation and vertex resolution. Our results suggest that cyclic stretching, by inducing cell shape change and reorientation in the presence of dynamic cell-cell adhesions, can induce at least some aspects of cell intercalation and that this process is dependent in distinct ways on myosin II activities and Wnt signaling.

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

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

Direct Calculation of the Interfacial Free Energy between NaCl Crystal and Its Aqueous Solution at the Solubility Limit.

Salty water is the most abundant electrolyte aqueous mixture on Earth, however, very little is known about the NaCl-saturated solution interfacial free energy (γ_{s}). Here, we provide the first direct estimation of γ_{s} for several NaCl crystallographic planes by means of the mold integration technique, a highly efficient computational method to evaluate interfacial free energies with anisotropic crystal resolution. Making use of the JC-SPC/E model, one of the most benchmarked force fields for NaCl water solutions, we measure γ_{s} of four different crystal planes, (100), (110), (111), and (112[over ¯]) with the saturated solution at normal conditions. We find high anisotropy between the different crystal orientations with values ranging from 100 to 150 mJ m^{-2}, and the average value of the distinct planes being γ[over ¯]_{s}=137(20) mJ m^{-2}. This value for the coexistence interfacial free energy is in reasonable agreement with previous extrapolations from nucleation studies. Our Letter represents a milestone in the computational calculation of interfacial free energies between ionic crystals and aqueous solutions.

Rotational Distortion and Compensation in Optical Coherence Tomography with Anisotropic Pixel Resolution.

Accurate image registration is essential for eye movement compensation in optical coherence tomography (OCT) and OCT angiography (OCTA). The spatial resolution of an OCT instrument is typically anisotropic, i.e., has different resolutions in the lateral and axial dimensions. When OCT images have anisotropic pixel resolution, residual distortion (RD) and false translation (FT) are always observed after image registration for rotational movement. In this study, RD and FT were quantitively analyzed over different degrees of rotational movement and various lateral and axial pixel resolution ratio (RL/RA) values. The RD and FT provide the evaluation criteria for image registration. The theoretical analysis confirmed that the RD and FT increase significantly with the rotation degree and RL/RA. An image resizing assisting registration (RAR) strategy was proposed for accurate image registration. The performance of direct registration (DR) and RAR for retinal OCT and OCTA images were quantitatively compared. Experimental results confirmed that unnormalized RL/RA causes RD and FT; RAR can effectively improve the performance of OCT and OCTA image registration and distortion compensation.

FV-Seg-Net: Fully Volumetric Network for Accurate Segmentation of COVID-19 Lesions From Chest CT Scans

Automated and precise pneumonia segmentation of COVID-19 extends the view of medical supply chains and offers crucial medical supplies to fight the COVID-19 pandemic. Deep learning plays a vital role in improving the COVID-19 segmentation from computed tomography (CT) scans. However, the literature lacks a precise segmentation approach on small-size lesions because they often split the CT scan into 2-D slices or 3-D patches, leading to the loss of contextual and/or global information. In order to address this, this article proposes a novel fully volumetric segmentation network, called FV-Seg-Net, that effectively exploits the local and global spatial information and enables the entire CT volume processing at once. The decoder is designed using a computationally efficient recalibrated anisotropic convolution module that can acquire the 3-D semantic representation of the CT volumes with anisotropic resolution. To avoid losing information during down-sampling, we reconstruct the skip-connection using a multilevel multiscale pyramid aggregation module and ensure more effective context fusion that improves the reconstruction capability of the decoder. Finally, stacked data augmentation (StackAug) is presented to magnify the training data and improve the generalizability of FV-Seg-Net. Proof of concept experiments on two public datasets demonstrates that the FV-Seg-Net achieves excellent segmentation performance (Dice score: 85.69 and a surface-dice: 84.79%), outperforming the current cutting-edge studies.