RESUMEN

Underwater image enhancement technology is crucial for the human exploration and exploitation of marine resources. The visibility of underwater images is affected by visible light attenuation. This paper proposes an image reconstruction method based on the decomposition-fusion of multi-channel luminance data to enhance the visibility of underwater images. The proposed method is a single-image approach to cope with the condition that underwater paired images are difficult to obtain. The original image is first divided into its three RGB channels. To reduce artifacts and inconsistencies in the fused images, a multi-resolution fusion process based on the Laplace-Gaussian pyramid guided by a weight map is employed. Image saliency analysis and mask sharpening methods are also introduced to color-correct the fused images. The results indicate that the method presented in this paper effectively enhances the visibility of dark regions in the original image and globally improves its color, contrast, and sharpness compared to current state-of-the-art methods. Our method can enhance underwater images in engineering practice, laying the foundation for in-depth research on underwater images.

RESUMEN

Computer-aided diagnosis (CAD) system assists ophthalmologists in early diabetic retinopathy (DR) detection by automating the analysis of retinal images, enabling timely intervention and treatment. This paper introduces a novel CAD system based on the global and multi-resolution analysis of retinal images. As a first step, we enhance the quality of the retinal images by applying a sequence of preprocessing techniques, which include the median filter, contrast limited adaptive histogram equalization (CLAHE), and the unsharp filter. These preprocessing steps effectively eliminate noise and enhance the contrast in the retinal images. Further, these images are represented at multi-scales using discrete wavelet transform (DWT), and center symmetric local binary pattern (CSLBP) features are extracted from each scale. The extracted CSLBP features from decomposed images capture the fine and coarse details of the retinal fundus images. Also, statistical features are extracted to capture the global characteristics and provide a comprehensive representation of retinal fundus images. The detection performances of these features are evaluated on a benchmark dataset using two machine learning models, i.e., SVM and k-NN, and found that the performance of the proposed work is considerably more encouraging than other existing methods. Furthermore, the results demonstrate that when wavelet-based CSLBP features are combined with statistical features, they yield notably improved detection performance compared to using these features individually.

RESUMEN

Super-resolution semantic segmentation (SRSS) is a technique that aims to obtain high-resolution semantic segmentation results based on resolution-reduced input images. SRSS can significantly reduce computational cost and enable efficient, high-resolution semantic segmentation on mobile devices with limited resources. Some of the existing methods require modifications of the original semantic segmentation network structure or add additional and complicated processing modules, which limits the flexibility of actual deployment. Furthermore, the lack of detailed information in the low-resolution input image renders existing methods susceptible to misdetection at the semantic edges. To address the above problems, we propose a simple but effective framework called multi-resolution learning and semantic edge enhancement-based super-resolution semantic segmentation (MS-SRSS) which can be applied to any existing encoder-decoder based semantic segmentation network. Specifically, a multi-resolution learning mechanism (MRL) is proposed that enables the feature encoder of the semantic segmentation network to improve its feature extraction ability. Furthermore, we introduce a semantic edge enhancement loss (SEE) to alleviate the false detection at the semantic edges. We conduct extensive experiments on the three challenging benchmarks, Cityscapes, Pascal Context, and Pascal VOC 2012, to verify the effectiveness of our proposed MS-SRSS method. The experimental results show that, compared with the existing methods, our method can obtain the new state-of-the-art semantic segmentation performance.

RESUMEN

In the evaluation of cervical spine disorders, precise positioning of anatomo-physiological hallmarks is fundamental for calculating diverse measurement metrics. Despite the fact that deep learning has achieved impressive results in the field of keypoint localization, there are still many limitations when facing medical image. First, these methods often encounter limitations when faced with the inherent variability in cervical spine datasets, arising from imaging factors. Second, predicting keypoints for only 4% of the entire X-ray image surface area poses a significant challenge. To tackle these issues, we propose a deep neural network architecture, NF-DEKR, specifically tailored for predicting keypoints in cervical spine physiological anatomy. Leveraging neural memory ordinary differential equation with its distinctive memory learning separation and convergence to a singular global attractor characteristic, our design effectively mitigates inherent data variability. Simultaneously, we introduce a Multi-Resolution Focus module to preprocess feature maps before entering the disentangled regression branch and the heatmap branch. Employing a differentiated strategy for feature maps of varying scales, this approach yields more accurate predictions of densely localized keypoints. We construct a medical dataset, SCUSpineXray, comprising X-ray images annotated by orthopedic specialists and conduct similar experiments on the publicly available UWSpineCT dataset. Experimental results demonstrate that compared to the baseline DEKR network, our proposed method enhances average precision by 2% to 3%, accompanied by a marginal increase in model parameters and the floating-point operations (FLOPs). The code (https://github.com/Zhxyi/NF-DEKR) is available.

RESUMEN

Effectively monitoring pest-infested areas by computer vision is essential in precision agriculture in order to minimize yield losses and create early scientific preventative solutions. However, the scale variation, complex background, and dense distribution of pests bring challenges to accurate detection when utilizing vision technology. Simultaneously, supervised learning-based object detection heavily depends on abundant labeled data, which poses practical difficulties. To overcome these obstacles, in this paper, we put forward innovative semi-supervised pest detection, PestTeacher. The framework effectively mitigates the issues of confirmation bias and instability among detection results across different iterations. To address the issue of leakage caused by the weak features of pests, we propose the Spatial-aware Multi-Resolution Feature Extraction (SMFE) module. Furthermore, we introduce a Region Proposal Network (RPN) module with a cascading architecture. This module is specifically designed to generate higher-quality anchors, which are crucial for accurate object detection. We evaluated the performance of our method on two datasets: the corn borer dataset and the Pest24 dataset. The corn borer dataset encompasses data from various corn growth cycles, while the Pest24 dataset is a large-scale, multi-pest image dataset consisting of 24 classes and 25k images. Experimental results demonstrate that the enhanced model achieves approximately 80% effectiveness with only 20% of the training set supervised in both the corn borer dataset and Pest24 dataset. Compared to the baseline model SoftTeacher, our model improves mAP @0.5 (mean Average Precision) at 7.3 compared to that of SoftTeacher at 4.6. This method offers theoretical research and technical references for automated pest identification and management.

RESUMEN

Recently, multi-resolution pyramid-based techniques have emerged as the prevailing research approach for image super-resolution. However, these methods typically rely on a single mode of information transmission between levels. In our approach, a wavelet pyramid recursive neural network (WPRNN) based on wavelet energy entropy (WEE) constraint is proposed. This network transmits previous-level wavelet coefficients and additional shallow coefficient features to capture local details. Besides, the parameter of low- and high-frequency wavelet coefficients within each pyramid level and across pyramid levels is shared. A multi-resolution wavelet pyramid fusion (WPF) module is devised to facilitate information transfer across network pyramid levels. Additionally, a wavelet energy entropy loss is proposed to constrain the reconstruction of wavelet coefficients from the perspective of signal energy distribution. Finally, our method achieves the competitive reconstruction performance with the minimal parameters through an extensive series of experiments conducted on publicly available datasets, which demonstrates its practical utility.

Asunto(s)

RESUMEN

Accurately segmenting cancer lesions is essential for effective personalized treatment and enhanced patient outcomes. We propose a multi-resolution selective segmentation (MurSS) model to accurately segment breast cancer lesions from hematoxylin and eosin (H&E) stained whole-slide images (WSIs). We used The Cancer Genome Atlas breast invasive carcinoma (BRCA) public dataset for training and validation. We used the Korea University Medical Center, Guro Hospital, BRCA dataset for the final test evaluation. MurSS utilizes both low- and high-resolution patches to leverage multi-resolution features using adaptive instance normalization. This enhances segmentation performance while employing a selective segmentation method to automatically reject ambiguous tissue regions, ensuring stable training. MurSS rejects 5% of WSI regions and achieves a pixel-level accuracy of 96.88% (95% confidence interval (CI): 95.97-97.62%) and mean Intersection over Union of 0.7283 (95% CI: 0.6865-0.7640). In our study, MurSS exhibits superior performance over other deep learning models, showcasing its ability to reject ambiguous areas identified by expert annotations while using multi-resolution inputs.

RESUMEN

Utilization of optimization technique is a must in the design of contemporary antenna systems. Often, global search methods are necessary, which are associated with high computational costs when conducted at the level of full-wave electromagnetic (EM) models. In this study, we introduce an innovative method for globally optimizing reflection responses of multi-band antennas. Our approach uses surrogates constructed based on response features, smoothing the objective function landscape processed by the algorithm. We begin with initial parameter space screening and surrogate model construction using coarse-discretization EM analysis. Subsequently, the surrogate evolves iteratively into a co-kriging model, refining itself using accumulated high-fidelity EM simulation results, with the infill criterion focusing on minimizing the predicted objective function. Employing a particle swarm optimizer (PSO) as the underlying search routine, extensive verification case studies showcase the efficiency and superiority of our procedure over benchmarks. The average optimization cost translates to just around ninety high-fidelity EM antenna analyses, showcasing excellent solution repeatability. Leveraging variable-resolution simulations achieves up to a seventy percent speedup compared to the single-fidelity algorithm.

RESUMEN

This work presents a multi-resolution physics-informed recurrent neural network (MR PI-RNN), for simultaneous prediction of musculoskeletal (MSK) motion and parameter identification of the MSK systems. The MSK application was selected as the model problem due to its challenging nature in mapping the high-frequency surface electromyography (sEMG) signals to the low-frequency body joint motion controlled by the MSK and muscle contraction dynamics. The proposed method utilizes the fast wavelet transform to decompose the mixed frequency input sEMG and output joint motion signals into nested multi-resolution signals. The prediction model is subsequently trained on coarser-scale input-output signals using a gated recurrent unit (GRU), and then the trained parameters are transferred to the next level of training with finer-scale signals. These training processes are repeated recursively under a transfer-learning fashion until the full-scale training (i.e., with unfiltered signals) is achieved, while satisfying the underlying dynamic equilibrium. Numerical examples on recorded subject data demonstrate the effectiveness of the proposed framework in generating a physics-informed forward-dynamics surrogate, which yields higher accuracy in motion predictions of elbow flexion-extension of an MSK system compared to the case with single-scale training. The framework is also capable of identifying muscle parameters that are physiologically consistent with the subject's kinematics data.

RESUMEN

Objective. In this paper, we propose positron emission tomography image reconstruction using a multi-resolution triangular mesh. The mesh can be adapted based on patient specific anatomical information that can be in the form of a computed tomography or magnetic resonance imaging image in the hybrid imaging systems. The triangular mesh can be adapted to high resolution in localized anatomical regions of interest (ROI) and made coarser in other regions, leading to an imaging model with high resolution in the ROI with clearly reduced number of degrees of freedom compared to a conventional uniformly dense imaging model.Approach.We compare maximum likelihood expectation maximization reconstructions with the multi-resolution model to reconstructions using a uniformly dense mesh, a sparse mesh and regular rectangular pixel mesh. Two simulated cases are used in the comparison, with the first one using the NEMA image quality phantom and the second the XCAT human phantom.Main results.When compared to the results with the uniform imaging models, the locally refined multi-resolution mesh retains the accuracy of the dense mesh reconstruction in the ROI while being faster to compute than the reconstructions with the uniformly dense mesh. The locally dense multi-resolution model leads also to more accurate reconstruction than the pixel-based mesh or the sparse triangular mesh.Significance.The findings suggest that triangular multi-resolution mesh, which can be made patient and application specific, is a potential alternative for pixel-based reconstruction.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: High-resolution (HR) MR images provide rich structural detail to assist physicians in clinical diagnosis and treatment plan. However, it is arduous to acquire HR MRI due to equipment limitations, scanning time or patient comfort. Instead, HR MRI could be obtained through a number of computer assisted post-processing methods that have proven to be effective and reliable. This paper aims to develop a convolutional neural network (CNN) based super-resolution reconstruction framework for low-resolution (LR) T2w images. METHOD: In this paper, we propose a novel multi-modal HR MRI generation framework based on deep learning techniques. Specifically, we construct a CNN based on multi-resolution analysis to learn an end-to-end mapping between LR T2w and HR T2w, where HR T1w is fed into the network to offer detailed a priori information to help generate HR T2w. Furthermore, a low-frequency filtering module is introduced to filter out the interference from HR-T1w during high-frequency information extraction. Based on the idea of multi-resolution analysis, detailed features extracted from HR T1w and LR T2w are fused at two scales in the network and then HR T2w is reconstructed by upsampling and dense connectivity module. RESULTS: Extensive quantitative and qualitative evaluations demonstrate that the proposed method enhances the recovered HR T2w details and outperforms other state-of-the-art methods. In addition, the experimental results also suggest that our network has a lightweight structure and favorable generalization performance. CONCLUSION: The results show that the proposed method is capable of reconstructing HR T2w with higher accuracy. Meanwhile, the super-resolution reconstruction results on other dataset illustrate the excellent generalization ability of the method.

Asunto(s)

RESUMEN

For molecular classification of endometrial carcinoma, testing for mismatch repair (MMR) status is becoming a routine process. Mismatch repair deficiency (MMR-D) is caused by loss of expression in one or more of the 4 major MMR proteins: MLH1, MSH2, MSH6, PHS2. Over 30% of patients with endometrial cancer have MMR-D. Determining the MMR status holds significance as individuals with MMR-D are potential candidates for immunotherapy. Pathological whole slide image (WSI) of endometrial cancer with immunohistochemistry results of MMR proteins were gathered. Color normalization was applied to the tiles using a CycleGAN-based network. The WSI was divided into tiles at three different magnifications (2.5 × , 5 × , and 10 ×). Three distinct networks of the same architecture were employed to include features from all three magnification levels and were stacked for ensemble learning. Three architectures, InceptionResNetV2, EfficientNetB2, and EfficientNetB3 were employed and subjected to comparison. The per-tile results were gathered to classify MMR status in the WSI, and prediction accuracy was evaluated using the following performance metrics: AUC, accuracy, sensitivity, and specificity. The EfficientNetB2 was able to make predictions with an AUC of 0.821, highest among the three architectures, and an overall AUC range of 0.767 - 0.821 was reported across the three architectures. In summary, our study successfully predicted MMR classification from pathological WSIs in endometrial cancer through a multi-resolution ensemble learning approach, which holds the potential to facilitate swift decisions on tailored treatment, such as immunotherapy, in clinical settings.

Asunto(s)

RESUMEN

The discrete Fourier transform (DFT) is the most commonly used signal processing method in modern digital sensor design for signal study and analysis. It is often implemented in hardware, such as a field programmable gate array (FPGA), using the fast Fourier transform (FFT) algorithm. The frequency resolution (i.e., frequency bin size) is determined by the number of time samples used in the DFT, when the digital sensor's bandwidth is fixed. One can vary the sensitivity of a radio frequency receiver by changing the number of time samples used in the DFT. As the number of samples increases, the frequency bin width decreases, and the digital receiver sensitivity increases. In some applications, it is useful to compute an ensemble of FFT lengths; e.g., 2P-j for j=0, 1, 2, …, J, where j is defined as the spectrum level with frequency resolution 2j·Δf. Here Δf is the frequency resolution at j=0. However, calculating all of these spectra one by one using the conventional FFT method would be prohibitively time-consuming, even on a modern FPGA. This is especially true for large values of P; e.g., P≥20. The goal of this communication is to introduce a new method that can produce multi-resolution spectrum lines corresponding to sample lengths 2P-j for all J+1 levels, concurrently, while one long 2P-length FFT is being calculated. That is, the lower resolution spectra are generated naturally as by-products during the computation of the 2P-length FFT, so there is no need to perform additional calculations in order to obtain them.

RESUMEN

This article describes a comprehensive Synthetic Aperture Radar (SAR) satellite based ships dataset for use in state of the art object detection algorithms. The dataset comprises 11,590 image tiles containing 27,885 ships examples. Each image tile has spatial dimensions of 512 × 512 pixels and is exported in JPEG format. The dataset contains a wide variety of inshore and offshore scenes under varying background settings and sea conditions to generate an all-inclusive understanding of the ship detection task in SAR satellite images. The dataset is generated using images from six different satellite sensors covering a wide range of electromagnetic spectrum including C, L and X band radar imaging frequencies. All the sensors have different resolutions and imaging modes. The dataset is randomly distributed into training, validation and test sets in the ratio of 70:20:10, respectively, for ease of comparison and bench-marking. The dataset was conceptualized, processed, labeled and verified at the Artificial Intelligence and Computer Vision (iVision) Lab at the Institute of Space Technology, Pakistan. To the best of our knowledge, this is the most diverse satellite based SAR ships dataset available in the public domain in terms of satellite sensors, radar imaging frequencies and background settings. The dataset can be used to train and optimize deep learning based object detection algorithms to develop generic models with high detection performance for any SAR sensor and background condition.

RESUMEN

In recent years, the transformer-based methods such as TransUNet and SwinUNet have been successfully applied in the research of medical image segmentation. However, these methods are all high-to-low resolution network by recovering high-resolution feature representations from low-resolution. This kind of structure led to loss of low-level semantic information in encoder stage. In this paper, we propose a new framework named MR-Trans to maintain high-resolution and low-resolution feature representations simultaneously. MR-Trans consists of three modules, namely a branch partition module, an encoder module and a decoder module. We construct multi-resolution branches with different resolutions in branch partition stage. In encoder module, we adopt Swin Transformer method to extract long-range dependencies on each branch and propose a new feature fusion strategy to fuse features with different scales between branches. A novel decoder network is proposed in MR-Trans by combining the PSPNet and FPNet at the same time to improve the recognition ability at different scales. Extensive experiments on two different datasets demonstrate that our method achieves better performance than other previous state-of-the-art methods for medical image segmentation.

Asunto(s)

RESUMEN

Pan-sharpening is a fundamental and crucial task in the remote sensing image processing field, which generates a high-resolution multi-spectral image by fusing a low-resolution multi-spectral image and a high-resolution panchromatic image. Recently, deep learning techniques have shown competitive results in pan-sharpening. However, diverse features in the multi-spectral and panchromatic images are not fully extracted and exploited in existing deep learning methods, which leads to information loss in the pan-sharpening process. To solve this problem, a novel pan-sharpening method based on multi-resolution transformer and two-stage feature fusion is proposed in this article. Specifically, a transformer-based multi-resolution feature extractor is designed to extract diverse image features. Then, to fully exploit features with different content and characteristics, a two-stage feature fusion strategy is adopted. In the first stage, a multi-resolution fusion module is proposed to fuse multi-spectral and panchromatic features at each scale. In the second stage, a shallow-deep fusion module is proposed to fuse shallow and deep features for detail generation. Experiments over QuickBird and WorldView-3 datasets demonstrate that the proposed method outperforms current state-of-the-art approaches visually and quantitatively with fewer parameters. Moreover, the ablation study and feature map analysis also prove the effectiveness of the transformer-based multi-resolution feature extractor and the two-stage fusion scheme.

RESUMEN

In the context of web augmented reality (AR), 3D rendering that maintains visual quality and frame rate requirements remains a challenge. The lack of a dedicated and efficient 3D format often results in the degraded visual quality of the original data and compromises the user experience. This paper examines the integration of web-streamable view-dependent representations of large-sized and high-resolution 3D models in web AR applications. The developed cross-platform prototype exploits the batched multi-resolution structures of the Nexus.js library as a dedicated lightweight web AR format and tests it against common formats and compression techniques. Built with AR.js and Three.js open-source libraries, it allows the overlay of the multi-resolution models by interactively adjusting the position, rotation and scale parameters. The proposed method includes real-time view-dependent rendering, geometric instancing and 3D pose regression for two types of AR: natural feature tracking (NFT) and location-based positioning for large and textured 3D overlays. The prototype achieves up to a 46% speedup in rendering time compared to optimized glTF models, while a 34 M vertices 3D model is visible in less than 4 s without degraded visual quality in slow 3D networks. The evaluation under various scenes and devices offers insights into how a multi-resolution scheme can be adopted in web AR for high-quality visualization and real-time performance.

RESUMEN

In recent years, deep learning super-resolution models for progressive reconstruction have achieved great success. However, these models which refer to multi-resolution analysis basically ignore the information contained in the lower subspaces and do not explore the correlation between features in the wavelet and spatial domain, resulting in not fully utilizing the auxiliary information brought by multi-resolution analysis with multiple domains. Therefore, we propose a super-resolution network based on the wavelet multi-resolution framework (WMRSR) to capture the auxiliary information contained in multiple subspaces and to be aware of the interdependencies between spatial domain and wavelet domain features. Initially, the wavelet multi-resolution input (WMRI) is generated by combining wavelet sub-bands obtained from each subspace through wavelet multi-resolution analysis and the corresponding spatial domain image content, which serves as input to the network. Then, the WMRSR captures the corresponding features from the WMRI in the wavelet domain and spatial domain, respectively, and fuses them adaptively, thus learning fully explored features in multi-resolution and multi-domain. Finally, the high-resolution images are gradually reconstructed in the wavelet multi-resolution framework by our convolution-based wavelet transform module which is suitable for deep neural networks. Extensive experiments conducted on two public datasets demonstrate that our method outperforms other state-of-the-art methods in terms of objective and visual qualities.

Asunto(s)

RESUMEN

Digital tomosynthesis (DTS) technology has attracted much attention in the field of nondestructive testing of printed circuit boards (PCB) due to its high resolution and suitability to thin slab objects. However, the traditional DTS iterative algorithm is computationally demanding, and its real-time processing of high-resolution and large volume reconstruction is infeasible. To address this issue, we in this study propose a multiple multi-resolution algorithm, including two multi-resolution strategies: volume domain multi-resolution and projection domain multi-resolution. The first multi-resolution scheme employs a LeNet-based classification network to divide the roughly reconstructed low-resolution volume into two sub-volumes namely, (1) the region of interest (ROI) with welding layers that necessitates high-resolution reconstruction, and (2) the remaining volume with unimportant information which can be reconstructed in low-resolution. When X-rays in adjacent projection angles pass through many identical voxels, information redundancy is prevalent between the adjacent image projections. Therefore, the second multi-resolution scheme divides the projections into non-overlapping subsets, using only one subset for each iteration. The proposed algorithm is evaluated using both the simulated and real image data. The results demonstrate that the proposed algorithm is approximately 6.5 times faster than the full-resolution DTS iterative reconstruction algorithm without compromising image reconstruction quality.

Asunto(s)

RESUMEN

The development of automatic chest X-ray (CXR) disease classification algorithms is significant for diagnosing thoracic diseases. Owing to the characteristics of lesions in CXR images, including high similarity in appearance of the disease, varied sizes, and different occurrence locations, most existing convolutional neural network-based methods have insufficient feature extraction for thoracic lesions and struggle to adapt to changes in lesion size and location. To address these issues, this study proposes a high-resolution classification network with dynamic convolution and coordinate attention (HRCC-Net). In the method, this study suggests a parallel multi-resolution network in which a high-resolution branch acquires essential detailed features of the lesion and multi-resolution feature swapping and fusion to obtain multiple receptive fields to extract complicated disease features adequately. Furthermore, this study proposes dynamic convolution to enhance the network's ability to represent multi-scale information to accommodate lesions of diverse scales. In addition, this study introduces a coordinate attention mechanism, which enables automatic focus on pathologically relevant regions and capturing the variations in lesion location. The proposed method is evaluated on ChestX-ray14 and CheXpert datasets. The average AUC (area under ROC curve) values reach 0.845 and 0.913, respectively, indicating this method's advantages compared with the currently available methods. Meanwhile, with its specificity and sensitivity to measure the performance of medical diagnostic systems, the network can improve diagnostic efficiency while reducing the rate of misdiagnosis. The proposed algorithm has great potential for thoracic disease diagnosis and treatment.