Attentional Gating Research Articles

Reconstruction of Daily MODIS/Aqua Chlorophyll-a Concentration in Turbid Estuarine Waters Based on Attention U-NET

An attention U-Net was proposed to reconstruct the missing chlorophyll-a concentration (Cchla) data. The U-Net is a lightweight full convolution neural network architecture consisting of an enccoder-decoder (i.e., down-sampling and up-sampling). The attention gates (AGs) were integrated into the U-Net. Training the U-Net with AGs could implicitly teach it to suppress irrelevant areas and highlight the salient features in the missing data areas, which would increase the network sensitivity and reconstruction accuracy. The neural network uses the satellite-derived Cchla anomalies and its variance as the input, and the reconstructed fields along with their variances as outputs. The trained network was applied to long-term daily MODIS/Aqua Cchla products in the Pearl River estuary (PRE) and adjacent continental shelf area. The model performance was evaluated by using an independent test dataset from both satellite-derived and in-situ measurements. The results showed that the proposed neural network not only had good performance in the reconstruction of valid pixels, but also provided a more reasonable reconstruction compared to the standard U-Net without AGs. This study provided a feasible method for the reconstruction task in the field of ocean color, which should be helpful in producing a creditable dataset to study the ecological effects of extreme weather conditions such as typhoons on the upper ocean in the PRE waters. Based on the reconstructed Cchla products, the footprints of the typhoons were studied. An increase in surface Cchla near the typhoons’ track and a decrease in estuary were found. The composite results illustrated that the Cchla increases occurred for almost the entire area within a radius of 100 km. The time series analysis showed that the Cchla peak appeared on the fifth day after the typhoon’s passage.

AGIM-net based subject-sensitive hashing algorithm for integrity authentication of HRRS images

The premise of effective use of high-resolution remote sensing (HRRS) images is that the data integrity and authenticity of HRRS images must be guaranteed. This paper proposes a new subject-sensitive hashing algorithm for the integrity authentication of HRRS images. This algorithm takes AGIM-net (Attention Gate-based improved M-net) proposed in this paper to extract the subject-sensitive features of the HRRS images, and uses Principal Component Analysis (PCA) based method to compress and encode the extracted features. AGIM-net is an improved U-net based on attention mechanism, adding multi-scale input in the encoder stage to extract rich image features; adding multi-scale output in the decoder stage, and suppressing the features irrelevant to the subject through Attention Gate to improve the robustness of the algorithm. Experiments show that the proposed algorithm has improved robustness compared with existing algorithms, and the tamper sensitivity and security are basically equivalent to the existing algorithms.

Developing A Contextual Combinational Approach for Predictive Analysis of Users Mobile Phone Trajectory Data in LBSNs

Today, smartphones, due to their ubiquity, have become indispensable in human daily life. Progress in the technology of mobile phones has recently resulted in the emergence of several popular services such as location-based social networks (LBSNs) and predicting the next Point of Interest (POI), which is an important task in these services. The gathered trajectory data in LBSNs include various contextual information such as geographical and temporal contextual information (GTCI) that play a crucial role in the next POI recommendations. Various methods, including collaborating filtering (CF) and recurrent neural networks, incorporated the contextual information of the user’ trajectory data to predict the next POIs. CF methods do not consider the effect of sequential data on modeling, while the next POI prediction problem is inherently a time sequence problem. Although recurrent models have been proposed for sequential data modeling, they have limitations such as similarly considering the effect of contextual information. Nonetheless, they have a separate impact as well. In the current study, a geographical temporal contextual information-extended attention gated recurrent unit (GTCI-EAGRU) architecture was proposed to separately consider the influence of geographical and temporal contextual information on the next POI recommendations. In this research, the GRU model was developed using three separate attention gates to consider the contextual information of the user trajectory data in the recurrent layer GTCI-EAGRU architecture, including timestamp, geographical, and temporal contextual attention gates. Inspired by the assumption of the matrix factorization method in CF approaches, a ranked list of POI recommendations was provided for each user. Moreover, a comprehensive evaluation was conducted by utilizing large-scale real-world datasets based on three LBSNs, including Gowalla, Brightkite, and Foursquare. The results revealed that the performance of GTCI-EAGRU was higher than that of competitive baseline methods in terms of Acc@10, on average, by 42.11% in three datasets.

Mulvernet: Nucleus Segmentation and Classification of Pathology Images Using the HoVer-Net and Multiple Filter Units

Nucleus segmentation and classification are crucial in pathology image analysis. Automated nuclear classification and segmentation methods support analysis and understanding of cell characteristics and functions, and allow the analysis of large-scale nuclear forms in the diagnosis and treatment of diseases. Common problems in these tasks arise from the inconsistent sizes and shapes of the cells in each pathology image. This study aims to develop a new method to address these problems based primarily on the horizontal and vertical distance network (HoVer-Net), multiple filter units, and attention gate mechanisms. The results of the study will significantly impact cell segmentation and classification by showing that a multiple filter unit improves the performance of the original HoVer-Net model. In addition, our experimental results show that the Mulvernet achieves outperforming results in both nuclei segmentation and classification compared to several methods. The ability to segment and classify different types of nuclei automatically has a direct influence on further pathological analysis, offering great potential not only to accelerate the diagnostic process in clinics but also for enhancing our understanding of tissue and cell properties to improve patient care and management.

EA-UNet Based Segmentation Method for OCT Image of Uterine Cavity

Optical coherence tomography (OCT) image processing can provide information about the uterine cavity structure, such as endometrial surface roughness, which is important for the diagnosis of uterine cavity lesions. The accurate segmentation of uterine cavity OCT images is a key step of OCT image processing. We proposed an EA-UNet-based image segmentation model that uses a U-Net network structure with a multi-scale attention mechanism to improve the segmentation accuracy of uterine cavity OCT images. The E(ECA-C) module introduces a convolutional layer combined with the ECA attention mechanism instead of max pool, reduces the loss of feature information, enables the model to focus on features in the region to be segmented, and suppresses irrelevant features to enhance the network’s feature-extraction capability and learning potential. We also introduce the A (Attention Gates) module to improve the model’s segmentation accuracy by using global contextual information. Our experimental results show that the proposed EA-UNet can enhance the model’s feature-extraction ability; furthermore, its MIoU, Sensitivity, and Specificity indexes are 0.9379, 0.9457, and 0.9908, respectively, indicating that the model can effectively improve uterine cavity OCT image segmentation and has better segmentation performance.

TAGU-Net: Transformer Convolution Hybrid-Based U-Net With Attention Gate for Atypical Meningioma Segmentation

Meningioma is derived from the cap cells that reside on the arachnoid membrane. The atypical meninges of Grade II, a classification established by the World Health Organization, are included in one of the grades of meningioma. It has been discovered that early surgical resection significantly reduces the recurrence rate and mortality of tumors. Accurate segmentation of magnetic resonance images of brain tumors is crucial for diagnosing and treating atypical meningiomas. However, the traditional automatic segmentation framework heavily relies on convolution. The convolution-based segmentation network has limitations such as the size of the convolution kernels, a restricted receptive field, and a lack of spatial aggregation ability. To overcome these limitations, this paper presents a novel hybrid architecture named TAGU-Net, which combines Transformer and convolution based on U-Net with an attention gate. The TAGU-Net architecture extracts features of different resolution feature scales using convolutional neural network and Transformer. This approach effectively captures the image’s long-distance dependency and global characteristics in the encoder stage, relying on the global self-attention mechanism of the Transformer. Additionally, the inductive bias of the convolution neural network is combined to enhance the local modeling information and improve the model’s overall modeling ability. In the decoder phase, the attention gate is introduced to adaptively learn the skip connection information and up-sampling information in the network. This information is weighted and fused to highlight important features and suppress irrelevant features. To obtain better model training and avoid the vanishing gradient, deep supervision technology is used in the training process. Supplementary loss is added in some stages to supervise the training and achieve the best effect of atypical meningioma segmentation. The proposed method is evaluated on both the private atypical meningioma dataset and the publicly available BraTs2018 dataset.TAGU-Net has achieved Dice Scores of 97.67% and 97.62% and Jaccard index of 96.35% and 95.35% on the private atypical meningioma dataset and BraTs2018 dataset respectively, which is a state-of-the-art segmentation result beyond existing methods. According to the research results, the TAGU-Net model significantly improves atypical meningioma segmentation and can effectively assist doctors in processing MRI images.

WRA-Net: Wide Receptive Field Attention Network for Motion Deblurring in Crop and Weed Image.

Automatically segmenting crops and weeds in the image input from cameras accurately is essential in various agricultural technology fields, such as herbicide spraying by farming robots based on crop and weed segmentation information. However, crop and weed images taken with a camera have motion blur due to various causes (e.g., vibration or shaking of a camera on farming robots, shaking of crops and weeds), which reduces the accuracy of crop and weed segmentation. Therefore, robust crop and weed segmentation for motion-blurred images is essential. However, previous crop and weed segmentation studies were performed without considering motion-blurred images. To solve this problem, this study proposed a new motion-blur image restoration method based on a wide receptive field attention network (WRA-Net), based on which we investigated improving crop and weed segmentation accuracy in motion-blurred images. WRA-Net comprises a main block called a lite wide receptive field attention residual block, which comprises modified depthwise separable convolutional blocks, an attention gate, and a learnable skip connection. We conducted experiments using the proposed method with 3 open databases: BoniRob, crop/weed field image, and rice seedling and weed datasets. According to the results, the crop and weed segmentation accuracy based on mean intersection over union was 0.7444, 0.7741, and 0.7149, respectively, demonstrating that this method outperformed the state-of-the-art methods.

Recognition of field roads based on improved U-Net++ Network

Unmanned driving of agricultural machinery has garnered significant attention in recent years, especially with the development of precision farming and sensor technologies. To achieve high performance and low cost, perception tasks are of great importance. In this study, a low-cost and high-safety method was proposed for field road recognition in unmanned agricultural machinery. The approach of this study utilized point clouds, with low-resolution lidar point clouds as inputs, generating high-resolution point clouds and Bird's Eye View (BEV) images that were encoded with several basic statistics. Using a BEV representation, road detection was reduced to a single-scale problem that could be addressed with an improved U-Net++ neural network. Three enhancements were proposed for U-Net++: 1) replacing the convolutional kernel in the original U-Net++ with an Asymmetric Convolution Block (ACBlock); 2) adding a multi-branch Asymmetric Dilated Convolutional Block (MADC) in the highest semantic information layer; 3) adding an Attention Gate (AG) model to the long-skip-connection in the decoding stage. The results of experiments of this study showed that our algorithm achieved a Mean Intersection Over Union of 96.54% on the 16-channel point clouds, which was 7.35 percentage points higher than U-Net++. Furthermore, the average processing time of the model was about 70 ms, meeting the time requirements of unmanned driving in agricultural machinery. The proposed method of this study can be applied to enhance the perception ability of unmanned agricultural machinery thereby increasing the safety of field road driving. Keywords: image segmentation, unmanned agricultural machinery, field roads, point cloud super-resolution, point cloud bird's eye view DOI: 10.25165/j.ijabe.20231602.7941 Citation: Yang L L, Li Y B, Chang M S, Xu Y Y, Hu B B, Wang X X, et al. Recognition of field roads based on improved U-Net++ Network. Int J Agric & Biol Eng, 2023; 16(2): 171-178.

DeepErythema: A Study on the Consistent Evaluation Method of UV SPF Index Through Deep Learning

This study presents a deep learning-based approach for consistent Sun Protection Factor (SPF) grading by quantifying skin erythema. Despite strict international standards, the current human-based Minimum Erythema Dose (MED) determination method for SPF evaluation suffers from inconsistency due to subjective criteria and the visual characteristics of erythema’s large variance. We propose DeepErythema, a novel method that uses erythema quantification for MED determination. The proposed method comprises pre-processing methods, a deep learning segmentation model, and post-processing methods. The UV irradiation area pointing is a pre-processing method that accurately detects the inspection area as a UV irradiated port, while Median Gradation Reduction eliminates the gradation that arises due to the digital image collection environment. The deep learning segmentation model parts introduce a methodology for improving performance using various feature extractors and methodologies like SeLu, Reverse Attention Gate, and MixedLoss. For post-processing, Perspective Transform Rectangle Restoration restores a distorted inspection area, and Relative Density Evaluation calculates a density score to consider skin characteristics and tone. We verified that utilizing the DeepErythema score in the UV SPF MED Evaluation (USME) dataset reduced the distribution of human-based MED decisions from 36 to 9 in the experimental results. This reduction in MED decision scope leads to improved consistency in SPF Index grading. Overall, the study contributes to the development of an objective and consistent evaluation method for SPF grading.

Novel Framework of Segmentation 3D MRI of Brain Tumors

Medical image segmentation is a crucial process for computer-aided diagnosis and surgery. Medical image segmentation refers to portioning the images into small, disjointed parts for simplifying the processes of analysis and examination. Rician and speckle noise are different types of noise in magnetic resonance imaging (MRI) that affect the accuracy of the segmentation process negatively. Therefore, image enhancement has a significant role in MRI segmentation. This paper proposes a novel framework that uses 3D MRI images from Kaggle and applies different diverse models to remove Rician and speckle noise using the best possible noise-free image. The proposed techniques consider the values of Peak Signal to Noise Ratio (PSNR) and the level of noise as inputs to the attention-U-Net model for segmentation of the tumor. The framework has been divided into three stages: removing speckle and Rician noise, the segmentation stage, and the feature extraction stage. The framework presents solutions for each problem at a different stage of the segmentation. In the first stage, the framework uses Vibrational Mode Decomposition (VMD) along with Block-matching and 3D filtering (Bm3D) algorithms to remove the Rician. Afterwards, the most significant Rician noise-free images are passed to the three different methods: Deep Residual Network (DeRNet), Dilated Convolution Auto-encoder Denoising Network (Di-Conv-AE-Net), and Denoising Generative Adversarial Network (DGAN-Net) for removing the speckle noise. VMD and Bm3D have achieved PSNR values for levels of noise (0, 0.25, 0.5, 0.75) for reducing the Rician noise by (35.243, 32.135, 28.214, 24.124) and (36.11, 31.212, 26.215, 24.123) respectively. The framework also achieved PSNR values for removing the speckle noise process for each level as follows: (34.146, 30.313, 28.125, 24.001), (33.112, 29.103, 27.110, 24.194), and (32.113, 28.017, 26.193, 23.121) for DeRNet, Di-Conv-AE-Net, and DGAN-Net, respectively. The experiments that have been conducted have proved the efficiency of the proposed framework against classical filters such as Bilateral, Frost, Kuan, and Lee according to different levels of noise. The attention gate U-Net achieved 94.66 and 95.03 in the segmentation of free noise images in dice and accuracy, respectively.

RayMVSNet++: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33 mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. This improves the performance on datasets with more challenging examples (e.g., low-quality images caused by poor lighting conditions or motion blur). RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

STAM: A SpatioTemporal Attention Based Memory for Video Prediction

Video prediction has always been a very challenging problem in video representation learning due to the complexity in spatial structure and temporal variation. However, existing methods mainly predict videos by employing language-based memory structures from the traditional Long Short-Term Memories (LSTMs) or Gated Recurrent Units (GRUs), which may not be powerful enough to model the long-term dependencies in videos, consisting of much more complex spatiotemporal dynamics than sentences. In this paper, we propose a SpatioTemporal Attention based Memory (STAM), which can efficiently improve the long-term spatiotemporal memorizing capacity by incorporating the global spatiotemporal information in videos. In the temporal domain, the proposed STAM aims to observe temporal states from a wider temporal receptive field to capture accurate global motion information. In the spatial domain, the proposed STAM aims to jointly utilize both the high-level semantic spatial state and the low-level texture spatial states to model a more reliable global spatial representation for videos. In particular, the global spatiotemporal information is extracted with the help of an Efficient SpatioTemporal Attention Gate (ESTAG), which can adaptively apply different levels of attention scores to different spatiotemporal states according to their importance. Moreover, the proposed STAM are built with 3D convolutional layers due to their advantages in modeling spatiotemporal dynamics for videos. Experimental results show that the proposed STAM can achieve state-of-the-art performance on widely used datasets by leveraging the proposed spatiotemporal representations for videos.

Incorporating dynamic attention gating mechanism and pre-trained embedding for Chinese clinical named entity recognition

Clinical Named Entity Recognition (CNER) serves as a cornerstone in clinical research and healthcare informatics, with its primary goal being the discernment and categorization of clinical terminologies present within Electronic Medical Records (EMRs). While deep learning has significantly improved CNER's performance, these models still face challenges in identifying rare or unseen entities. Our study unveils an innovative DAGM-BiLSTM-CRF model that seamlessly integrates data-driven deep learning strategies with human knowledge to surmount this limitation. The distinctive features of this model lie in its integration of a pre-trained character embedding layer, adept at encapsulating nuanced semantic variations at the granularity of individual characters. Furthermore, it incorporates a bidirectional Long Short-Term Memory (BiLSTM) layer, proficient in deriving contextually relevant information by traversing the sequence from both endpoints. The most noteworthy aspect of our model is the inclusion of a Dynamic Attention Gating Mechanism (DAGM) that dynamically recalibrates attention weights based on the traits of the input sequence and a Conditional Random Fields (CRF) layer that considers interdependencies among output labels within a sequence. The evaluation was carried out on the CCKS-2017 CNER benchmark dataset to underscore the superiority of our model over existing cutting-edge methods, thereby validating its proficiency in deciphering the intricacies of Chinese electronic medical records.

De-Aliasing and Accelerated Sparse Magnetic Resonance Image Reconstruction Using Fully Dense CNN with Attention Gates.

When sparsely sampled data are used to accelerate magnetic resonance imaging (MRI), conventional reconstruction approaches produce significant artifacts that obscure the content of the image. To remove aliasing artifacts, we propose an advanced convolutional neural network (CNN) called fully dense attention CNN (FDA-CNN). We updated the Unet model with the fully dense connectivity and attention mechanism for MRI reconstruction. The main benefit of FDA-CNN is that an attention gate in each decoder layer increases the learning process by focusing on the relevant image features and provides a better generalization of the network by reducing irrelevant activations. Moreover, densely interconnected convolutional layers reuse the feature maps and prevent the vanishing gradient problem. Additionally, we also implement a new, proficient under-sampling pattern in the phase direction that takes low and high frequencies from the k-space both randomly and non-randomly. The performance of FDA-CNN was evaluated quantitatively and qualitatively with three different sub-sampling masks and datasets. Compared with five current deep learning-based and two compressed sensing MRI reconstruction techniques, the proposed method performed better as it reconstructed smoother and brighter images. Furthermore, FDA-CNN improved the mean PSNR by 2 dB, SSIM by 0.35, and VIFP by 0.37 compared with Unet for the acceleration factor of 5.

A dense residual U-net for multiple sclerosis lesions segmentation from multi-sequence 3D MR images

Multiple Sclerosis (MS) is an autoimmune disease that causes brain and spinal cord lesions, which magnetic resonance imaging (MRI) can detect and characterize. Recently, deep learning methods have achieved remarkable results in the automated segmentation of MS lesions from MRI data. Hence, this study proposes a novel dense residual U-Net model that combines attention gate (AG), efficient channel attention (ECA), and Atrous Spatial Pyramid Pooling (ASPP) to enhance the performance of the automatic MS lesion segmentation using 3D MRI sequences. First, convolution layers in each block of the U-Net architecture are replaced by residual blocks and connected densely. Then, AGs are exploited to capture salient features passed through the skip connections. The ECA module is appended at the end of each residual block and each downsampling block of U-Net. Later, the bottleneck of U-Net is replaced with the ASSP module to extract multi-scale contextual information. Furthermore, 3D MR images of Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted (T1-w), and T2-weighted (T2-w) are exploited jointly to perform better MS lesion segmentation. The proposed model is validated on the publicly available ISBI2015 and MSSEG2016 challenge datasets. This model produced an ISBI score of 92.75, a mean Dice score of 66.88%, a mean positive predictive value (PPV) of 86.50%, and a mean lesion-wise true positive rate (LTPR) of 60.64% on the ISBI2015 testing set. Also, it achieved a mean Dice score of 67.27%, a mean PPV of 65.19%, and a mean sensitivity of 74.40% on the MSSEG2016 testing set. The results show that the proposed model performs better than the results of some experts and some of the other state-of-the-art methods realized related to this particular subject. Specifically, the best Dice score and the best LTPR are obtained on the ISBI2015 testing set by using the proposed model to segment MS lesions.

Modified UNet with attention gate and dense skip connection for flow field information prediction with porous media

Porous media flow phenomena are commonly found in nature and industry. Understanding the patterns can improve industrial production and efficiency. Traditional numerical methods can predict flow field information within porous media exactly, even on pore scale. However, once the pore structures of porous media are changed, the traditional numerical methods have to start over again, which implies poor extension and low efficiency for realistic application. To address the challenge, we propose a new deep learning method for image segmentation based on convolutional neural networks that can quickly predict the saturation variation and flow velocity profile of multiphase flow directly from the structure of porous media. In the present method, the UNet network structure is improved by replacing parallel splicing with different levels of dense skip connection to extract flow information at different depths. When processing flow topological information, the introduction of attention mechanism allows effective focus on adjusting the flow field edges and front shapes to improve accuracy. Depending on the pore structures information, the saturation of the porous media also can be evaluated. This result shows that the flow field information (saturation and velocity) of porous media can be quickly predicted by deep learning methods. Compared with the computational fluid dynamics (CFD) method, this approach has a better prediction efficiency for porous media. The machine learning method is a good prediction tool for porous media with different porosities and pore structures.

RAAGR2-Net: A brain tumor segmentation network using parallel processing of multiple spatial frames

Brain tumors are one of the most fatal cancers. Magnetic Resonance Imaging (MRI) is a non-invasive method that provides multi-modal images containing important information regarding the tumor. Many contemporary techniques employ four modalities: T1-weighted (T1), T1-weighted with contrast (T1c), T2-weighted (T2), and fluid-attenuation-inversion-recovery (FLAIR), each of which provides unique and important characteristics for the location of each tumor. Although several modern procedures provide decent segmentation results on the multimodal brain tumor image segmentation benchmark (BraTS) dataset, they lack performance when evaluated simultaneously on all the regions of MRI images. Furthermore, there is still room for improvement due to parameter limitations and computational complexity. Therefore, in this work, a novel encoder–decoder-based architecture is proposed for the effective segmentation of brain tumor regions. Data pre-processing is performed by applying N4 bias field correction, z-score, and 0 to 1 resampling to facilitate model training. To minimize the loss of location information in different modules, a residual spatial pyramid pooling (RASPP) module is proposed. RASPP is a set of parallel layers using dilated convolution. In addition, an attention gate (AG) module is used to efficiently emphasize and restore the segmented output from extracted feature maps. The proposed modules attempt to acquire rich feature representations by combining knowledge from diverse feature maps and retaining their local information. The performance of the proposed deep network based on RASPP, AG, and recursive residual (R2) block termed RAAGR2-Net is evaluated on the BraTS benchmarks. The experimental results show that the suggested network outperforms existing networks that exhibit the usefulness of the proposed modules for “fine” segmentation. The code for this work is made available online at: https://github.com/Rehman1995/RAAGR2-Net.

Attention-based U-Net for image demoiréing

Image demoiréing is a particular example of a picture restoration problem. Moiré is an interference pattern generated by overlaying similar but slightly offset templates.In this paper, we present a deep learning based algorithm to reduce moiré disruptions. The proposed solution contains an explanation of the cross-sampling procedure – the training dataset management method which was optimized according to limited computing resources.Suggested neural network architecture is based on Attention U-Net structure. It is an exceptionally effective model which was not proposed before in image demoiréing systems. The greatest improvement of this model in comparison to U-Net network is the implementation of attention gates. These additional computing operations make the algorithm more focused on target structures.We also examined three MSE and SSIM based loss functions. The SSIM index is used to predict the perceived quality of digital images and videos. A similar approach was applied in various computer vision areas.The author’s main contributions to the image demoiréing problem contain the use of the novel architecture for this task, innovative two-part loss function, and the untypical use of the cross-sampling training procedure.

AWUNet: leaf area segmentation based on attention gate and wavelet pooling mechanism

AWUNet: leaf area segmentation based on attention gate and wavelet pooling mechanism

DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians.

Accurate parcellation of cortical regions is crucial for distinguishing morphometric changes in aged brains, particularly in degenerative brain diseases. Normal aging and neurodegeneration precipitate brain structural changes, leading to distinct tissue contrast and shape in people aged >60 years. Manual parcellation by trained radiologists can yield a highly accurate outline of the brain; however, analyzing large datasets is laborious and expensive. Alternatively, newly-developed computational models can quickly and accurately conduct brain parcellation, although thus far only for the brains of Caucasian individuals. To develop a computational model for the brain parcellation of older East Asians, we trained magnetic resonance images of dimensions 256 × 256 × 256 on 5,035 brains of older East Asians (Gwangju Alzheimer's and Related Dementia) and 2,535 brains of Caucasians. The novel N-way strategy combining three memory reduction techniques inception blocks, dilated convolutions, and attention gates was adopted for our model to overcome the intrinsic memory requirement problem. Our method proved to be compatible with the commonly used parcellation model for Caucasians and showed higher similarity and robust reliability in older aged and East Asian groups. In addition, several brain regions showing the superiority of the parcellation suggest that DeepParcellation has a great potential for applications in neurodegenerative diseases such as Alzheimer's disease.