First-principles predictions of room-temperature ferromagnetism in orthorhombic MnX2 (X = O, S) monolayers.

Two-dimensional ferromagnets with high spin-polarization at ambient temperature are of considerable interest because they might be useful for making nanoscale spintronic devices. We report that even though bulk phases of MnO2 are generally antiferromagnetic with low ordering temperatures, the corresponding MnO2 and MnS2 monolayers are ferromagnetic, and MnS2 is a high temperature half metallic ferromagnet. Based on first-principles calculations, we find that the MnO2 monolayer is an intrinsic ferromagnetic semiconductor with a Curie temperature TC of ∼300 K, while the half-metallic MnS2 monolayer has a remarkably high TC of ∼1150 K. Both compounds have substantial magnetocrystalline anisotropy, out of plane in the case of MnO2 monolayers, and in plane along the b-axis of orthorhombic MnS2 monolayer. Interestingly, a metal-insulator phase transition occurs in the MnS2 monolayer when the applied biaxial strain is beyond -2%. Tuning near this metal-insulator transition offers additional possibilities for devices. The present work shows that MnX2 (X = O, S) monolayers have the properties required for ultrathin nano-spintronic devices.

RClaNet: An explainable Alzheimer's disease diagnosis framework by joint registration and classification.

Alzheimer's disease (AD) is a degenerative mental disorder of the central nervous system that affects people's ability of daily life. Unfortunately, there is currently no known cure for AD. Thus, the early detection of AD plays a key role in preventing and controlling its progression. Magnetic resonance imaging (MRI)-based measures of cerebral atrophy are regarded as valid markers of the AD state. As one of representative methods for measuring brain atrophy, image registration technique has been widely adopted for AD diagnosis. However, AD detection is sensitive to the accuracy of image registration. To address this problem, an AD assistant diagnosis framework based on joint registration and classification is proposed. Specifically, in order to capture more local deformation information, we propose a novel patch-based joint brain image registration and classification network (RClaNet) to estimate the local dense deformation fields (DDF) and disease risk probability maps that explain high-risk areas for AD patients. RClaNet consists of a registration network and a classification network, in which the deformation field from registration network is fed into the classification network to enhance the prediction accuracy of the disease. Then, the exponential distance weighting method is used to obtain the global DDF and the global disease risk probability map, and it can remove grid-like artifacts by uniformly weighting method. Finally, the global classification network uses the global disease risk probability map for the early detection of AD. We evaluate the proposed method on the OASIS-3, AIBL and ADNI datasets, and experimental results show that the proposed RClaNet achieves superior registration performances than several state-of-the-art methods. Early diagnosis of AD using the global disease risk probability map also yielded competitive results. To demonstrate the generality, we also evaluate the proposed method on a COVID-19 dataset and achieve decent registration and classification results. These experiments prove that the deformation information in the registration process can be used to characterize subtle changes of degenerative diseases and further assist clinicians in diagnosis.

Cuprate superconducting materials above liquid nitrogen temperature from machine learning.

The superconductivity of cuprates remains a challenging topic in condensed matter physics, and the search for materials that superconduct electricity above liquid nitrogen temperature and even at room temperature is of great significance for future applications. Nowadays, with the advent of artificial intelligence, research approaches based on data science have achieved excellent results in material exploration. We investigated machine learning (ML) models by employing separately the element symbolic descriptor atomic feature set 1 (AFS-1) and a prior physics knowledge descriptor atomic feature set 2 (AFS-2). An analysis of the manifold in the hidden layer of the deep neural network (DNN) showed that cuprates still offer the greatest potential as superconducting candidates. By calculating the SHapley Additive exPlanations (SHAP) value, it is evident that the covalent bond length and hole doping concentration emerge as the crucial factors influencing the superconducting critical temperature (Tc). These findings align with our current understanding of the subject, emphasizing the significance of these specific physical quantities. In order to improve the robustness and practicability of our model, two types of descriptors were used to train the DNN. We also proposed the idea of cost-sensitive learning, predicted the sample in another dataset, and designed a virtual high-throughput search workflow.

Deep learning-based classification of breast lesions using dynamic ultrasound video.

PURPOSE: We intended to develop a deep-learning-based classification model based on breast ultrasound dynamic video, then evaluate its diagnostic performance in comparison with the classic model based on ultrasound static image and that of different radiologists. METHOD: We collected 1000 breast lesions from 888 patients from May 2020 to December 2021. Each lesion contained two static images and two dynamic videos. We divided these lesions randomly into training, validation, and test sets by the ratio of 7:2:1. Two deep learning (DL) models, namely DL-video and DL-image, were developed based on 3D Resnet-50 and 2D Resnet-50 using 2000 dynamic videos and 2000 static images, respectively. Lesions in the test set were evaluated to compare the diagnostic performance of two models and six radiologists with different seniority. RESULTS: The area under the curve of the DL-video model was significantly higher than those of the DL-image model (0.969 vs. 0.925, P = 0.0172) and six radiologists (0.969 vs. 0.779-0.912, P < 0.05). All radiologists performed better when evaluating the dynamic videos compared to the static images. Furthermore, radiologists performed better with increased seniority both in reading images and videos. CONCLUSIONS: The DL-video model can discern more detailed spatial and temporal information for accurate classification of breast lesions than the conventional DL-image model and radiologists, and its clinical application can further improve the diagnosis of breast cancer.

Deep learning based brain MRI registration driven by local-signed-distance fields of segmentation maps.

BACKGROUND: Deep learning based unsupervised registration utilizes the intensity information to align images. To avoid the influence of intensity variation and improve the registration accuracy, unsupervised and weakly-supervised registration are combined, namely, dually-supervised registration. However, the estimated dense deformation fields (DDFs) will focus on the edges among adjacent tissues when the segmentation labels are directly used to drive the registration progress, which will decrease the plausibility of brain MRI registration. PURPOSE: In order to increase the accuracy of registration and ensure the plausibility of registration at the same time, we combine the local-signed-distance fields (LSDFs) and intensity images to dually supervise the registration progress. The proposed method not only uses the intensity and segmentation information but also uses the voxelwise geometric distance information to the edges. Hence, the accurate voxelwise correspondence relationships are guaranteed both inside and outside the edges. METHODS: The proposed dually-supervised registration method mainly includes three enhancement strategies. Firstly, we leverage the segmentation labels to construct their LSDFs to provide more geometrical information for guiding the registration process. Secondly, to calculate LSDFs, we construct an LSDF-Net, which is composed of 3D dilation layers and erosion layers. Finally, we design the dually-supervised registration network (VMLSDF ) by combining the unsupervised VoxelMorph (VM) registration network and the weakly-supervised LSDF-Net, to utilize intensity and LSDF information, respectively. RESULTS: In this paper, experiments were then carried out on four public brain image datasets: LPBA40, HBN, OASIS1, and OASIS3. The experimental results show that the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD) of VMLSDF are higher than those of the original unsupervised VM and the dually-supervised registration network (VMseg ) using intensity images and segmentation labels. At the same time, the percentage of negative Jacobian determinant (NJD) of VMLSDF is lower than VMseg . Our code is freely available at https://github.com/1209684549/LSDF. CONCLUSIONS: The experimental results show that LSDFs can improve the registration accuracy compared with VM and VMseg , and enhance the plausibility of the DDFs compared with VMseg .

The Successive Next Network as Augmented Regularization for Deformable Brain MR Image Registration.

Deep-learning-based registration methods can not only save time but also automatically extract deep features from images. In order to obtain better registration performance, many scholars use cascade networks to realize a coarse-to-fine registration progress. However, such cascade networks will increase network parameters by an n-times multiplication factor and entail long training and testing stages. In this paper, we only use a cascade network in the training stage. Unlike others, the role of the second network is to improve the registration performance of the first network and function as an augmented regularization term in the whole process. In the training stage, the mean squared error loss function between the dense deformation field (DDF) with which the second network has been trained and the zero field is added to constrain the learned DDF such that it tends to 0 at each position and to compel the first network to conceive of a better deformation field and improve the network's registration performance. In the testing stage, only the first network is used to estimate a better DDF; the second network is not used again. The advantages of this kind of design are reflected in two aspects: (1) it retains the good registration performance of the cascade network; (2) it retains the time efficiency of the single network in the testing stage. The experimental results show that the proposed method effectively improves the network's registration performance compared to other state-of-the-art methods.

Research on Optimization Scheme for Blocking Artifacts after Patch-Based Medical Image Reconstruction.

Due to limitations of computer resources, when utilizing a neural network to process an image with a high resolution, the typical processing approach is to slice the original image. However, because of the influence of zero-padding in the edge component during the convolution process, the central part of the patch often has more accurate feature information than the edge part, resulting in image blocking artifacts after patch stitching. We studied this problem in this paper and proposed a fusion method that assigns a weight to each pixel in a patch using a truncated Gaussian function as the weighting function. In this method, we used the weighting function to transform the Euclidean-distance between a point in the overlapping part and the central point of the patch where the point was located into a weight coefficient. With increasing distance, the value of the weight coefficient decreased. Finally, the reconstructed image was obtained by weighting. We employed the bias correction model to evaluate our method on the simulated database BrainWeb and the real dataset HCP (Human Connectome Project). The results show that the proposed method is capable of effectively removing blocking artifacts and obtaining a smoother bias field. To verify the effectiveness of our algorithm, we employed a denoising model to test it on the IXI-Guys human dataset. Qualitative and quantitative evaluations of both models show that the fusion method proposed in this paper can effectively remove blocking artifacts and demonstrates superior performance compared to five commonly available and state-of-the-art fusion methods.

Improving Symbolic Regression for Predicting Materials Properties with Iterative Variable Selection.

Symbolic regression offers a promising avenue for describing the structure-property relationships of materials with explicit mathematical expressions, yet it meets challenges when the key variables are unclear because of the high complexity of the problems. In this work, we propose to solve the difficulty by automatically searching for important variables from a large pool of input features. A new algorithm that integrates symbolic regression with iterative variable selection (VS) was designed for optimization of the model with a large amount of input features. Using the recent method SISSO for symbolic regression and random search for variable selection, we show that the VS-assisted SISSO (VS-SISSO) can effectively manage even hundreds of input features that the SISSO alone was computationally hindered, and it fastly converges to (near) optimal solutions when the model complexity is not high. The efficiency of this approach for improving the accuracy of symbolic regression in materials science was demonstrated in the two showcase applications of learning approximate equations for the band gap of inorganic halide perovskites and the stability of single-atom alloy catalysts.

ECG_SegNet: An ECG delineation model based on the encoder-decoder structure.

With the increasing usage of wearable electrocardiogram (ECG) monitoring devices, it is necessary to develop models and algorithms that can analyze the large amounts of ECG data obtained in real-time. Accurate ECG delineation is key to assisting cardiologists in diagnosing cardiac diseases. The main objective of this study is to design a delineation model based on the encoder-decoder structure to detect different heartbeat waveforms, including P-waves, QRS complexes, T-waves, and No waves (NW), as well as the onset and offset of these waveforms. First, the introduction of a standard dilated convolution module (SDCM) into the encoder path enabled the model to extract more useful ECG signal-informative features. Subsequently, bidirectional long short-term memory (BiLSTM) was added to the encoding structure to obtain numerous temporal features. Moreover, the feature sets of the ECG signals at each level in the encoder path were connected to the decoder part for multi-scale decoding to mitigate the information loss caused by the pooling operation in the encoding process. Finally, the proposed model was trained and tested on both QT and LU databases, and it achieved accurate results compared to other state-of-the-art methods. Regarding the QT database, the average accuracy of ECG waveform classification was 96.90%, and an average classification accuracy of 95.40% was obtained on the LU database. In addition, average F1 values of 99.58% and 97.05% were achieved in the ECG delineation task of the QT and LU databases, respectively. The results show that the proposed ECG_SegNet model has good flexibility and reliability when applied to ECG delineation, and it is a reliable method for analyzing ECG signals in real-time.

TCGAN: a transformer-enhanced GAN for PET synthetic CT.

Multimodal medical images can be used in a multifaceted approach to resolve a wide range of medical diagnostic problems. However, these images are generally difficult to obtain due to various limitations, such as cost of capture and patient safety. Medical image synthesis is used in various tasks to obtain better results. Recently, various studies have attempted to use generative adversarial networks for missing modality image synthesis, making good progress. In this study, we propose a generator based on a combination of transformer network and a convolutional neural network (CNN). The proposed method can combine the advantages of transformers and CNNs to promote a better detail effect. The network is designed for positron emission tomography (PET) to computer tomography synthesis, which can be used for PET attenuation correction. We also experimented on two datasets for magnetic resonance T1- to T2-weighted image synthesis. Based on qualitative and quantitative analyses, our proposed method outperforms the existing methods.

Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration.

Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along the edge of patches for the following two reasons: firstly, in order to ensure the same size of input and output, zero-padding is used, which causes uncertainty in the edges of the output feature map during the feature extraction process; secondly, the sliding window extraction patch with different strides will result in different degrees of grid-like artifacts. In this paper, we propose an exponential-distance-weighted (EDW) method to remove grid-like artifacts. To consider the uncertainty of predictions near patch edges, we used an exponential function to convert the distance from the point in the overlapping regions to the center point of the patch into a weighting coefficient. This gave lower weights to areas near the patch edges, to decrease the uncertainty predictions. Finally, the dense displacement field was obtained by this EDW weighting method. We used the OASIS-3 dataset to evaluate the performance of our method. The experimental results show that the proposed EDW patch fusion method removed grid-like artifacts and improved the dice similarity coefficient superior to those of several state-of-the-art methods. The proposed fusion method can be used together with any patch-based registration model.

Overview of Multi-Modal Brain Tumor MR Image Segmentation.

The precise segmentation of brain tumor images is a vital step towards accurate diagnosis and effective treatment of brain tumors. Magnetic Resonance Imaging (MRI) can generate brain images without tissue damage or skull artifacts, providing important discriminant information for clinicians in the study of brain tumors and other brain diseases. In this paper, we survey the field of brain tumor MRI images segmentation. Firstly, we present the commonly used databases. Then, we summarize multi-modal brain tumor MRI image segmentation methods, which are divided into three categories: conventional segmentation methods, segmentation methods based on classical machine learning methods, and segmentation methods based on deep learning methods. The principles, structures, advantages and disadvantages of typical algorithms in each method are summarized. Finally, we analyze the challenges, and suggest a prospect for future development trends.

Denoising of 3D Brain MR Images with Parallel Residual Learning of Convolutional Neural Network Using Global and Local Feature Extraction.

Magnetic resonance (MR) images often suffer from random noise pollution during image acquisition and transmission, which impairs disease diagnosis by doctors or automated systems. In recent years, many noise removal algorithms with impressive performances have been proposed. In this work, inspired by the idea of deep learning, we propose a denoising method named 3D-Parallel-RicianNet, which will combine global and local information to remove noise in MR images. Specifically, we introduce a powerful dilated convolution residual (DCR) module to expand the receptive field of the network and to avoid the loss of global features. Then, to extract more local information and reduce the computational complexity, we design the depthwise separable convolution residual (DSCR) module to learn the channel and position information in the image, which not only reduces parameters dramatically but also improves the local denoising performance. In addition, a parallel network is constructed by fusing the features extracted from each DCR module and DSCR module to improve the efficiency and reduce the complexity for training a denoising model. Finally, a reconstruction (REC) module aims to construct the clean image through the obtained noise deviation and the given noisy image. Due to the lack of ground-truth images in the real MR dataset, the performance of the proposed model was tested qualitatively and quantitatively on one simulated T1-weighted MR image dataset and then expanded to four real datasets. The experimental results show that the proposed 3D-Parallel-RicianNet network achieves performance superior to that of several state-of-the-art methods in terms of the peak signal-to-noise ratio, structural similarity index, and entropy metric. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation.

Predicting the structural, electronic and magnetic properties of few atomic-layer polar perovskite.

Density functional theory (DFT) calculations are performed to predict the structural, electronic and magnetic properties of electrically neutral or charged few-atomic-layer (AL) oxides based on polar perovskite KTaO3. Their properties vary greatly with the number of ALs (nAL) and the stoichiometric ratio. In the few-AL limit (nAL ≤ 14), the even AL (EL) systems with the chemical formula (KTaO3)n are semiconductors, while the odd AL (OL) systems with the formula Kn+1TanO3n+1 or KnTan+1O3n+2 are half-metal except for the unique KTa2O5 case which is a semiconductor due to the large Peierls distortions. After reaching a certain critical thickness (nAL > 14), the EL systems show ferromagnetic surface states, while ferromagnetism disappears in the OL systems. These predictions from fundamental complexity of polar perovskite when approaching the two-dimensional (2D) limit may be helpful for interpreting experimental observations later.

Persistent Spin-texture and Ferroelectric Polarization in 2D Hybrid Perovskite Benzylammonium Lead-halide.

Density functional theory calculations were performed for the electronic and the ferroelectric properties of the bulk and the monolayer benzylammonium lead-halide (BA2PbCl4). Our calculations indicate that both the bulk and monolayer systems display a band gap of ∼3.3 eV (HSE06+SOC) and a spontaneous polarization of ∼5.4 µC/cm2. The similar physical properties of bulk and monolayer systems suggest a strong decoupling among the layers in this hybrid organic-inorganic perovskite. Both the ferroelectricity, through associated structure distortion, and the spin-orbit coupling, through splitting induced in the electronic bands, significantly influence the band gaps. Most importantly, we found for the first time in a two-dimensional hybrid organic-inorganic class of material, a peculiar spin texture topology such as a unidirectional spin-orbit field, which may lead to a protection against spin decoherence.

Viewpoint: Atomic-Scale Design Protocols toward Energy, Electronic, Catalysis, and Sensing Applications.

Nanostructured materials are essential building blocks for the fabrication of new devices for energy harvesting/storage, sensing, catalysis, magnetic, and optoelectronic applications. However, because of the increase of technological needs, it is essential to identify new functional materials and improve the properties of existing ones. The objective of this Viewpoint is to examine the state of the art of atomic-scale simulative and experimental protocols aimed to the design of novel functional nanostructured materials, and to present new perspectives in the relative fields. This is the result of the debates of Symposium I "Atomic-scale design protocols towards energy, electronic, catalysis, and sensing applications", which took place within the 2018 European Materials Research Society fall meeting.

Bioferroelectric Properties of Glycine Crystals.

Biological ferroelectric materials have great potential in biosensing and disease diagnosis and treatment. Glycine crystals form the simplest bioferroelectric materials, and here we investigate the polarizations of its ß- and γ-phases. Using density functional theory, we predict that glycine crystals can develop polarizations  even larger than those of conventional inorganic ferroelectrics. Further, using systematic molecular dynamics simulations utilizing polarized crystal charges, we predict the Curie temperature of γ-glycine to be 630 K, with a required coercive field to switch its polarization states of 1 V·nm-1, consistent with experimental evidence. This work sheds light on the microscopic mechanism of electric dipole ordering in biomaterials, helping in the material design of novel bioferroelectrics.

One-Dimensional Organic-Inorganic Hybrid Perovskite Incorporating Near-Infrared-Absorbing Cyanine Cations.

Hybrid perovskite crystals with organic and inorganic structural components are able to combine desirable properties from both classes of materials. Electronic interactions between the anionic inorganic framework and functional organic cations (such as chromophores or semiconductors) can give rise to unusual photophysical properties. Cyanine dyes are a well known class of cationic organic dyes with high extinction coefficients and tunable absorption maxima all over the visible and near-infrared spectrum. Here we present the synthesis and characterization of an original 1D hybrid perovskite composed of NIR-absorbing cyanine cations and polyanionic lead halide chains. This first demonstration of a cyanine-perovskite hybrid material is paving the way to a new class of compounds with great potential for applications in photonic devices.

Allotropes of tellurium from first-principles crystal structure prediction calculations under pressure.

We investigated the allotropes of tellurium under hydrostatic pressure based on density functional theory calculations and crystal structure prediction methodology. Our calculated enthalpy-pressure and energy-volume curves unveil the transition sequence from the trigonal semiconducting phase, represented by the space group P3121 in the range of 0-6 GPa, to the body centered cubic structure, space group Im3̄m, stable at 28 GPa. In between, the calculations suggest a monoclinic structure, represented by the space group C2/m and stable at 6 GPa, and the ß-Po type structure, space group R3̄m, stable at 10 GPa. The face-centered structure is found at pressure as high as 200 GPa. As the pressure is increased, the transition from the semiconducting phase to metallic phases is observed.

First-principles study of Ga-vacancy induced magnetism in ß-Ga2O3.

First principles calculations based on density functional theory were performed to study the electronic structure and magnetic properties of ß-Ga2O3 in the presence of cation vacancies. We investigated two kinds of Ga vacancies at different symmetry sites and the consequent structural distortion and defect states. We found that both the six-fold coordinated octahedral site and the four-fold coordinated tetrahedral site vacancies can lead to a spin polarized ground state. Furthermore, the calculation identified a relationship between the spin polarization and the charge states of the vacancies, which might be explained by a molecular orbital model consisting of uncompensated O2- 2p dangling bonds. The calculations for the two vacancy systems also indicated a potential long-range ferromagnetic order which is beneficial for spintronics application.