Non-local Means Research Articles

Probabilistic volumetric speckle suppression in OCT using deep learning.

We present a deep learning framework for volumetric speckle reduction in optical coherence tomography (OCT) based on a conditional generative adversarial network (cGAN) that leverages the volumetric nature of OCT data. In order to utilize the volumetric nature of OCT data, our network takes partial OCT volumes as input, resulting in artifact-free despeckled volumes that exhibit excellent speckle reduction and resolution preservation in all three dimensions. Furthermore, we address the ongoing challenge of generating ground truth data for supervised speckle suppression deep learning frameworks by using volumetric non-local means despeckling-TNode- to generate training data. We show that, while TNode processing is computationally demanding, it serves as a convenient, accessible gold-standard source for training data; our cGAN replicates efficient suppression of speckle while preserving tissue structures with dimensions approaching the system resolution of non-local means despeckling while being two orders of magnitude faster than TNode. We demonstrate fast, effective, and high-quality despeckling of the proposed network in different tissue types that are not part of the training. This was achieved with training data composed of just three OCT volumes and demonstrated in three different OCT systems. The open-source nature of our work facilitates re-training and deployment in any OCT system with an all-software implementation, working around the challenge of generating high-quality, speckle-free training data.

Enhancing vascular network visualization in 3D photoacoustic imaging: in vivo experiments with a vasculature filter.

Filter-based vessel enhancement algorithms facilitate the extraction of vascular networks from medical images. Traditional filter-based algorithms struggle with high noise levels in images with false vessel extraction, and a low standard deviation (σ) value may introduce gaps at the centers of wide vessels. In this paper, a robust technique with less sensitivity to parameter tuning and better noise suppression than other filter-based methods for two-dimensional and three-dimensional images is implemented. In this study, we propose a filter that employs non-local means (NLM) for denoising, applying the vesselness function to suppress blob-like structures and filling the gaps in wide vessels without compromising edge quality or details. Acoustic resolution photoacoustic microscopy (AR-PAM) systems generate high-resolution volumetric photoacoustic images, but their vascular structure imaging suffers from out-of-focal signal-to-noise ratio (SNR) and lateral resolution loss. Implementing a synthetic aperture focusing technique (SAFT) based on a virtual detector (VD) improves out-of-focal region resolution and SNR. Combining the proposed filter with the SAFT algorithm enhances vascular structural imaging in AR-PAM systems. The proposed method is robust and applicable for animal tissues with less error of vasculature structure extraction in comparison to traditional fliter-based methods like Frangi and Sato filter. Also, the method is faster in terms of processing speed and less tuning parameters. We applied the method to a digital phantom to validate our approach and conducted in vivo experiments to demonstrate its superiority for real volumetric tissue imaging.

Advancing potential field data analysis: the Modified Horizontal Gradient Amplitude method (MHGA)

Enhancing the detection accuracy of the edges of the geological features within the subsurface remains a significant objective in geophysical data interpretation. Despite numerous advancements, approaches stemming from the directional gradients of gravity and magnetic fields still grapple with challenges such as low-resolution outcomes and susceptibility to noise contamination. In this study, we introduce a novel filtering framework based on the total horizontal gradient and its derivatives, designed to yield more precise and coherent edges free from false boundaries or disruptive artifacts. Validation using synthetic Bishop complex magnetic and gravity datasets, alongside Tuangiao aeromagnetic data from Vietnam, substantiates the robustness and applicability of our modified approach. Furthermore, recognizing the inherent susceptibility of edge detection filters to noise contamination resulting from directional derivatives, we employ the recently developed modified non-local means (MNLM) algorithm to alleviate noise effects prior to the analysis of noisy synthetic and real datasets. Our findings confirm the efficacy of the proposed method in reducing false artifacts and identifying edges with heightened precision, positioning MHGA as a valuable alternative for processing potential field data.

Mitigating adversarial threats in deep CT image diagnosis models via a dual-stage inference-time defense

Artificial intelligence (AI), particularly deep learning (DL) and machine learning (ML) have revolutionized disease diagnosis using complex medical images such as X-rays and CT scans, significantly improving accuracy in identifying various medical conditions. However, concerns arise regarding the trustworthiness of these models due to their vulnerability to adversarial attacks, potentially leading to inaccurate predictions. In response, we propose an innovative pipeline defensive approach that integrates denoising techniques like Total Variation Minimization (TVM) and Non-local (NL) means, followed by a fuzzy logic-based image transformer called Fuzzy Image Transformations (FIT). Deployed during the inferencing phase as a preprocessing module, this strategy aims to fortify DL medical diagnosis models, addressing adversarial vulnerabilities and ensuring their reliability in critical healthcare applications. Our focus is narrowed down to COVID-19 diagnosis, where we initially developed a model for accurately classifying lung CT images, covering both normal and COVID-19 pneumonia cases. Our experimental procedures, employing the Stratified K-Fold cross-validation method with K=5, systematically evaluate the model’s susceptibility to benchmark adversarial attacks such as the Fast Gradient Sign Method (FGSM), revealing a significant drop in aggregate average metrics across all folds under adversarial conditions. Specifically, precision (P), recall (R), accuracy (A), and F1-score (F) metrics decrease from 95.86 %, 96.16 %, 95.85 %, and 96.00–12.54 %, 13.13 %, 12.63 %, and 12.83 %, respectively. Notably, our proposed pipeline defense approach demonstrates substantial efficacy in enhancing diagnostic models, with average P, R, A, and F metrics improving impressively to 92.65 %, 92.39 %, 92.65 %, and 92.51 %, respectively, when applied to the same adversarial images. These promising results underscore the potential of our proposed pipeline defense techniques to enhance the resilience and reliability of AI-based diagnostic systems.

DRPSO:A multi-strategy fusion particle swarm optimization algorithm with a replacement mechanisms for colon cancer pathology image segmentation

Colon adenocarcinoma (COAD) is a type of colon cancers with a high mortality rate. Its early symptoms are not obvious, and its late stage is accompanied by various complications that seriously endanger patients' lives. To assist in the early diagnosis of COAD and improve the detection efficiency of COAD, this paper proposes a multi-level threshold image segmentation (MIS) method based on an enhanced particle swarm algorithm for segmenting COAD images. Firstly, this paper proposes a multi-strategy fusion particle swarm optimization algorithm (DRPSO) with a replacement mechanism. The non-linear inertia weight and sine-cosine learning factors in DRPSO help balance the exploration and exploitation phases of the algorithm. The population reorganization strategy incorporating MGO enhances population diversity and effectively prevents the algorithm from stagnating prematurely. The mutation-based final replacement mechanism enhances the algorithm's ability to escape local optima and helps the algorithm to obtain highly accurate solutions. In addition, comparison experiments on the CEC2020 and CEC2022 test sets show that DRPSO outperforms other state-of-the-art algorithms in terms of convergence accuracy and speed. Secondly, by combining the non-local mean 2D histogram and 2D Renyi entropy, this paper proposes a DRPSO algorithm based MIS method, which is successfully applied to the segments the COAD pathology image problem. The results of segmentation experiments show that the above method obtains relatively higher quality segmented images with superior performance metrics: PSNR = 23.556, SSIM = 0.825, and FSIM = 0.922. In conclusion, the MIS method based on the DRPSO algorithm shows great potential in assisting COAD diagnosis and in pathology image segmentation.

Pipeline Leak Detection: A Comprehensive Deep Learning Model Using CWT Image Analysis and an Optimized DBN-GA-LSSVM Framework.

Detecting pipeline leaks is an essential factor in maintaining the integrity of fluid transport systems. This paper introduces an advanced deep learning framework that uses continuous wavelet transform (CWT) images for precise detection of such leaks. Transforming acoustic signals from pipelines under various conditions into CWT scalograms, followed by signal processing by non-local means and adaptive histogram equalization, results in new enhanced leak-induced scalograms (ELIS) that capture detailed energy fluctuations across time-frequency scales. The fundamental approach takes advantage of a deep belief network (DBN) fine-tuned with a genetic algorithm (GA) and unified with a least squares support vector machine (LSSVM) to improve feature extraction and classification accuracy. The DBN-GA framework precisely extracts informative features, while the LSSVM classifier precisely distinguishes between leaky and non-leak conditions. By concentrating solely on the advanced capabilities of ELIS processed through an optimized DBN-GA-LSSVM model, this research achieves high detection accuracy and reliability, making a significant contribution to pipeline monitoring and maintenance. This innovative approach to capturing complex signal patterns can be applied to real-time leak detection and critical infrastructure safety in several industrial applications.

Sunflower Origin Identification Based on Multi-Source Information Fusion Technique of Kernel Extreme Learning Machine

This study constructs a model for the rapid identification of the origins of edible sunflower (Helianthus) using Kernel Extreme Learning Machine (KELM) with multi-source information fusion technology. Near-infrared spectroscopy (NIRS) and nuclear magnetic resonance spectroscopy (NMRS) were utilized to analyze 180 sunflower samples from the Xinjiang, Heilongjiang, and Inner Mongolia regions. Initially, the identification models for the origin of sunflowers using NIR and NMR data were compared between two algorithms: the Extreme Learning Machine (ELM) and KELM, combined with various spectral preprocessing methods. The experiment found that the NIR spectral model preprocessed with standard normal variate (SNV) using the KELM algorithm was the most accurate, achieving accuracies of 98.7% in the training set and 97.2% in the test set. The spin-echo NMR spectral model preprocessed with non-local means (NLMs) using the KELM algorithm was the second best, with accuracies of 98.4% in the training set and 96.4% in the test set. To further improve the accuracy of the identification models, innovative sunflower origin identification models were developed based on data layer fusion and feature layer fusion using NIRS and NMRS. In the data layer fusion model, the KELM algorithm model was optimal, achieving a test set accuracy and F1 score of 98.2% and 98.18%, respectively, an improvement of 1.0% over the best single data source model. In the feature layer fusion model, four types of feature-layer information-fusion identification models were established using two feature extraction algorithms, Competitive Adaptive Reweighted Sampling (CARS) and Variable Importance Projection (VIP), combined with joint feature and simple merging feature strategies. The CARS-KELM algorithm combined with the joint feature method was found to be the best, achieving 100% accuracy in both the training and test sets, an improvement of 2.8% over the best single data source model. Identifying the origin of edible sunflower using NIRS and NMRS is demonstrated as feasible by the results. The best single-spectrum sunflower origin identification model was achieved using the KELM algorithm with SNV preprocessing. The feature layer fusion method combining NIRS and NMRS data is suitable for handling the task of sunflower origin identification. This method significantly improves the recognition accuracy of the model compared to a single model, achieving fast and accurate origin identification of edible sunflowers. The research results provide a new method for rapid identification of sunflower origin.

Computational fluid dynamics in carbonate rock wormholes using magnetic resonance images as structural information

Computational fluid dynamics (CFD) is an essential tool with growing applications in many fields. In petrophysics, it is common to use computed tomography in those simulations, but in medicine, magnetic resonance imaging (MRI) is also being used as a basis for structural information. Wormholes are high-permeability structures created by the acidification of carbonate reservoirs and can impact reservoir production. CFD combined with MRI can benefit the study of wormholes in petrophysics, but combining both techniques is still a challenge. The objective of this study is to develop a pipeline for performing CFD in wormholes with MRI data. Using three samples of carbonate rocks acidified with 1.5% hydrochloric acid at 0.1, 1, and 10 ml/min, we acquired 300μm resolution T2-weighted images and experimental measurements of pressure data within flow rates of 5 to 50 ml/min. We applied cropping, bias field correction, non-local means denoising, and segmentation in the image processing step. For the 3D reconstruction, we used marching cubes to generate the surface mesh, the Taubin filter for surface smoothing, and boundary modeling with Blender. Finally, for the CFD, we generated volumetric meshes with cfMesh and used the OpenFOAM simpleFoam solver to simulate an incompressible, stationary, and laminar flow. We analyzed the effect of surface smoothing, estimating edge displacements, and measured the simulation pressure at the same flow rates as the experiments. Surface smoothing had a negligible impact on the overall edge position. For most flow rates, the simulation and experimental pressure measurements matched. A possible reason for the discrepancies is that we did not consider the surrounding porous media in the simulations. In summary, our work had satisfactory results, demonstrating CFD’s feasibility in studying wormholes using MRI.

Femur bone volumetric estimation for osteoporosis classification based on deep learning with tuna jellyfish optimization using X-ray images

Osteoporosis is a disorder, that leads to fractures and fatal problems in bones. It is believed that more than 200 million individuals are affected globally. Furthermore, osteoporosis is caused by micro-architectural degeneration of bone tissues, which increases the risk of bone fragility and fractures. Moreover, the osteoporosis categorization is essential for the medical industry, which classifies the skeleton problems of individuals caused by ageing. This work presented the prediction of femur bone volume for osteoporosis classification. Moreover, the femur bone X-ray image is utilized for the classification. The preprocessing phase is employed to neglect the noise contained in input bone images through a non-local means filter. In the image segmentation process, the SegNet is utilized to isolate the specific portion. Moreover, the template search approach based on femoral geometric estimation is carried out and the feature extraction phase is essential for a significant feature extraction process. The proposed tuna jellyfish optimization based deep batch-normalized eLU AlexNet (DbneAlexNet) is utilized in the osteoporosis classification process. Furthermore, accuracy, Positive Predictive Value (PPV), Negative Predictive Value (NPV), True Positive Rate (TPR) and True Negative Rate (TNR) are the metrics to validate the model and the superior values 0.913, 0.906, 0.896, 0.923 and 0.932 are achieved.

3D visualization in turbid water using optimal photon counting and a GAT-based peplography method

Peplography is a three-dimensional (3D) approach for the visualization of targets in environments characterized by heavy scattering. It detects ballistic photons and subsequently generates a 3D image using integral imaging, where the expected number of ballistic photons is set arbitrarily. However, it affects the robustness of the method and accuracy in the analysis of results. Therefore, we propose a method to determine the optimal number of ballistic photons based on the maximum entropy of the photon counting image. Because accuracy in visualizing 3D targets may be compromised due to extraneous photons and fluctuations in photon intensity, we also address this challenge by integrating the generalized Anscombe transformation (GAT) with the conventional peplography technique. The noise caused by an image sensor during image acquisition can be modeled as a Poisson–Gaussian noise, and the photon counting process can be modeled as a Poisson process. Addressing such noise indirectly involves applying the GAT to the reconstructed image to stabilize its variance, denoising the stabilized data with a Gaussian denoising algorithm (i.e., non-local means filtering), and subsequently applying an exact unbiased inverse GAT to the denoised data. Experimental validation is conducted through experiments, with comparisons to conventional peplography, wavelet peplography, and a few standard dehazing and machine learning methods. Various image quality metrics such as correlation, structural similarity, the peak signal-to-noise ratio, and the natural image quality evaluator are used to demonstrate the superiority of the proposed method over conventional ones.

Enabling Low-Dose In Vivo Benchtop X-ray Fluorescence Computed Tomography through Deep-Learning-Based Denoising.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing high-resolution molecular-level data. However, increased sensitivity with current benchtop X-ray sources comes at the cost of high radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for background noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized Swin-Conv-UNet (SCUNet) model for background noise reduction in X-ray fluorescence (XRF) images at low tracer concentrations. Our method's effectiveness is evaluated against higher-dose images, while various denoising techniques exist for X-ray and computed tomography (CT) techniques, only a few address XFCT. The DL model is trained and assessed using augmented data, focusing on background noise reduction. Image quality is measured using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), comparing outcomes with 100% X-ray-dose images. Results demonstrate that the proposed algorithm yields high-quality images from low-dose inputs, with maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms block-matching and 3D filtering (BM3D), block-matching and 4D filtering (BM4D), non-local means (NLM), denoising convolutional neural network (DnCNN), and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

Deep learning generation of preclinical positron emission tomography (PET) images from low-count PET with task-based performance assessment.

Preclinical low-count positron emission tomography (LC-PET) imaging offers numerous advantages such as facilitating imaging logistics, enabling longitudinal studies of long- and short-lived isotopes as well as increasing scanner throughput. However, LC-PET is characterized by reduced photon-count levels resulting in low signal-to-noise ratio (SNR), segmentation difficulties, and quantification uncertainties. We developed and evaluated a novel deep-learning (DL) architecture-Attention based Residual-Dilated Net (ARD-Net)-to generate standard-count PET (SC-PET) images from LC-PET images. The performance of the ARD-Net framework was evaluated for numerous low count realizations using fidelity-based qualitative metrics, task-based segmentation, and quantitative metrics. Patient Derived tumor Xenograft (PDX) with tumors implanted in the mammary fat-pad were subjected to preclinical [18F]-Fluorodeoxyglucose (FDG)-PET/CT imaging. SC-PET images were derived from a 10min static FDG-PET acquisition, 50min post administration of FDG, and were resampled to generate four distinct LC-PET realizations corresponding to 10%, 5%, 1.6%, and 0.8% of SC-PET count-level. ARD-Net was trained and optimized using 48 preclinical FDG-PET datasets, while 16 datasets were utilized to assess performance. Further, the performance of ARD-Net was benchmarked against two leading DL-based methods (Residual UNet, RU-Net; and Dilated Network, D-Net) and non-DL methods (Non-Local Means, NLM; and Block Matching 3D Filtering, BM3D). The performance of the framework was evaluated using traditional fidelity-based image quality metrics such as Structural Similarity Index Metric (SSIM) and Normalized Root Mean Square Error (NRMSE), as well as human observer-based tumor segmentation performance (Dice Score and volume bias) and quantitative analysis of Standardized Uptake Value (SUV) measurements. Additionally, radiomics-derived features were utilized as a measure of quality assurance (QA) in comparison to true SC-PET. Finally, a performance ensemble score (EPS) was developed by integrating fidelity-based and task-based metrics. Concordance Correlation Coefficient (CCC) was utilized to determine concordance between measures. The non-parametric Friedman Test with Bonferroni correction was used to compare the performance of ARD-Net against benchmarked methods with significance at adjusted p-value ≤0.01. ARD-Net-generated SC-PET images exhibited significantly better (p ≤ 0.01 post Bonferroni correction) overall image fidelity scores in terms of SSIM and NRMSE at majority of photon-count levels compared to benchmarked DL and non-DL methods. In terms of task-based quantitative accuracy evaluated by SUVMeanand SUVPeak, ARD-Net exhibited less than 5% median absolute bias for SUVMean compared to true SC-PET and lower degree of variability compared to benchmarked DL and non-DL based methods in generating SC-PET. Additionally, ARD-Net-generated SC-PET images displayed higher degree of concordance to SC-PET images in terms of radiomics features compared to non-DL and other DL approaches. Finally, the ensemble score suggested that ARD-Net exhibited significantly superior performance compared to benchmarked algorithms (p ≤ 0.01 post Bonferroni correction). ARD-Net provides a robust framework to generate SC-PET from LC-PET images. ARD-Net generated SC-PET images exhibited superior performance compared other DL and non-DL approaches in terms of image-fidelity based metrics, task-based segmentation metrics, and minimal bias in terms of task-based quantification performance for preclinical PET imaging.

A comparative study of pre-processing methods to improve glioma segmentation performance in brain MRI using deep learning

Background: Glioma is the most common brain tumor in adult patients and requires accurate treatment. The delineation of tumor boundaries must be accurate and precise, which is crucial for treatment planning. Currently, delineating boundaries for tumors is a tedious, time-consuming task and may be prone to human error among oncologists. Therefore, artificial intelligence plays a vital role in reducing these problems. Objective: This study aims to find a relationship between improving image enhancement and evaluating the performance of deep learning models for segmenting glioma image data on brain MRI images. Materials and methods: The BraTs2023 dataset was used in this study. The image dataset was converted from three dimensions to two dimensions and then subjected to pre-processing via four image enhancement techniques, including contrast-limited adaptive histogram equalization (CLAHE), gamma correction (GC), non-local mean filter (NLMF), and median and Wiener filter (MWF). Subsequently, it was evaluated for structural similarity index (SSIM) and mean squared error. The deep learning segmentation model was created using the U-Net architecture and assessed for dice similarity coefficient (DSC), accuracy, precision, recall, F1-score, and Jaccard index for tumor segmentation. Results: The performance of enhanced image results for CLAHE, GC, NLMF, and MWF techniques shows SSIM values of 0.912, 0.905, 0.999, and 0.911, respectively. The dice similarity coefficient (DSC) for segmentation without image enhancement was 0.817. The DSC of segmentation for CLAHE, GC, NLMF, and MWF techniques were 0.818, 0.812, 0.820, and 0.797, respectively. Conclusion: The enhanced image technique could affect the performance of tumor segmentation. by the enhanced image for use in a trained model may increase or decrease performance depending on the chosen image enhancement technique and the parameters determined by each method.

ML3CNet: Non-local means-assisted automatic framework for lung cancer subtypes classification using histopathological images

Background and objective:Lung cancer (LC) has a high fatality rate that continuously affects human lives all over the world. Early detection of LC prolongs human life and helps to prevent the disease. Histopathological inspection is a common method to diagnose LC. Visual inspection of histopathological diagnosis necessitates more inspection time, and the decision depends on the subjective perception of clinicians. Usually, machine learning techniques mostly depend on traditional feature extraction which is labor-intensive and may not be appropriate for enormous data. In this work, a convolutional neural network (CNN)-based architecture is proposed for the more effective classification of lung tissue subtypes using histopathological images. Methods:Authors have utilized the first-time nonlocal mean (NLM) filter to suppress the effect of noise from histopathological images. NLM filter efficiently eliminated noise while preserving the edges of images. Then, the obtained denoised images are given as input to the proposed multi-headed lung cancer classification convolutional neural network (ML3CNet). Furthermore, the model quantization technique is utilized to reduce the size of the proposed model for the storage of the data. Reduction in model size requires less memory and speeds up data processing. Results:The effectiveness of the proposed model is compared with the other existing state-of-the-art methods. The proposed ML3CNet achieved an average classification accuracy of 99.72%, sensitivity of 99.66%, precision of 99.64%, specificity of 99.84%, F-1 score of 0.9965, and area under the curve of 0.9978. The quantized accuracy of 98.92% is attained by the proposed model. To validate the applicability of the proposed ML3CNet, it has also been tested on the colon cancer dataset. Conclusion:The findings reveal that the proposed approach can be beneficial to automatically classify LC subtypes that might assist healthcare workers in making decisions more precisely. The proposed model can be implemented on the hardware using Raspberry Pi for practical realization.

Improved quantification in CEST-MRI by joint spatial total generalized variation.

In this work, the use of joint Total Generalized Variation (TGV) regularization to improve Multipool-Lorentzian fitting of chemical exchange saturation transfer (CEST) Spectra in terms of stability and parameter signal-to-noise ratio (SNR) was investigated. The joint TGV term was integrated into the nonlinear parameter fitting problem. To increase convergence and weight the gradients, preconditioning using a voxel-wise singular value decomposition was applied to the problem, which was then solved using the iteratively regularized Gauss-Newton method combined with a Primal-Dual splitting algorithm. The TGV method was evaluated on simulated numerical phantoms, 3T phantom data and 7T in vivo data with respect to systematic errors and robustness. Three reference methods were also implemented: The standard nonlinear fitting, a method using a nonlocal-means filter for denoising and the pyramid scheme, which uses downsampled images to acquire accurate start values. The proposed regularized fitting method showed significantly improved robustness (compared to the reference methods). In testing, over a range of SNR values the TGV fit outperformed the other methods and showed accurate results even for large amounts of added noise. Parameter values found were closer or comparable to the ground truth. For in vivo datasets, the added regularization increased the parameter map SNR and prevented instabilities. The proposed fitting method using TGV regularization leads to improved results over a range of different data-sets and noise levels. Furthermore, it can be applied to all Z-spectrum data, with different amounts of pools, where the improved SNR and stability can increase diagnostic confidence.

Cutting through the noise: A Three-Way Comparison of Median, Adaptive Median, and Non-Local Means Filter for MRI Images

Medical Imaging is an essential practice in radiology to create high-standard images of the human brain. In medical imaging, denoising techniques are essential during image processing for a meaningful view of the anatomical structure of the images. In order to overcome the denoising issues, various filtering techniques and smoothening algorithms have come forth to get an accurate image for better diagnosis while preserving the original image quality. This work utilizes three computational methods for filtering noise that could distort the factual information in MRI images. The input used as the data throughout this study are MR images in grayscale contaminated with Salt and pepper noise, the most common noise in MRI images. To de-noise, a comparative analysis of three specific filters, namely the Non-Local Means filter, Median filter, and Adaptive Median filter, is conducted to do a study that gives the best results among them at different noise densities. Peak Signal-To-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are utilized as the main components to examine the behavior of the suggested filters in this study. The results show that at every value of noise density, i.e., 0.1, 0.3, 0.6, the adaptive median filter gives the highest average PSNR of 42.04, 34.36, and 28.10 and average SSIM of 0.97, 0.95, and 0.91, respectively. Hence, it indicates that the adaptive median filter outperforms the other two filters regarding PSNR and SSIM.

Image fast reconstruction for sparse view computed tomography with reduced sampling integration time

Industrial computed tomography (CT) can detect the internal structure of objects nondestructively. Its scanning and image reconstruction are time-consuming, which limits its application in the fast detection field. In this work, we reduce the sampling integration time in sparse view CT to achieve ultra-fast scanning in only 5 s. However, this ultra-fast scanning method produces more noise and streak artifacts in the reconstructed CT images. The existing reconstruction methods cannot effectively reconstruct high quality CT images under this ultra-fast scanning. To solve this issue, a faster and higher quality CT image reconstruction method is proposed in this paper. We construct a novel objective function using multi-directional TV and adaptive non-local means (ANLM), and design a solution algorithm to solve the objective function. The multi-directional TV-norm takes into account the differences in horizontal, vertical, and 45° directional gradients to obtain more image detail information, while the ANLM-norm focuses on noise suppression. Simulation and practical experiments show that the proposed method can reconstruct higher quality CT images under faster CT scanning strategy, and the peak signal to noise ratio (PSNR) is 1.3 dB higher than the optimal baseline algorithm. On the other hand, our method converges faster and achieves a shorter CT image reconstruction time, which is 47 s shorter than the current popular iterative reconstruction methods. This reconstruction method provides a reliable scheme for faster CT scanning and image reconstruction.

Deep learning with adaptive convolutions for classification of retinal diseases via optical coherence tomography

Optical coherence tomography (OCT) uses interferometry to capture high-resolution cross-sectional images of the retina to diagnose retinal diseases. Convolutional neural networks (CNNs) have become essential for developing efficient computer-aided diagnostic algorithms, but noisy images can hinder their performance. This study introduces an innovative image preprocessing strategy that involves a new method of representing images to reduce image noise and a new adaptive convolution layer. The adaptive convolution layer aims to replace traditional convolution layers for OCT image classification by relying on local’Feature Content’. The proposed image representation is based on Zeckendorf's theorem, which states that every positive integer may be split into a unique sum of distinct, non-adjacent Fibonacci numbers. The proposed approach enables the generation of two separate images, known as the ‘base’ and ‘fine,’ where the ‘base’ image is the denoised image. We assessed our methodology by evaluating against ten filters, comprising a Low-pass filter, Gaussian filter, Wiener filter, Wavelet filter, Guided filter, Lee filter, Frost filter, Kuan filter, Detail Preserving Anisotropic Diffusion (DPAD) filter, and Non-Local Means (NLM) filter. In our study, we found that the proposed filter produced the most favorable results in five of the six no-reference parameters (Blur Percent (BP), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), Wavelet Variance (WAVV), Wavelet Variance Radial (WAVR)) used to assess the effectiveness of the proposed image enhancement technique. The OCT dataset utilized in the study was compiled by the University of California San Diego. The proposed adaptive convolution layer and its accompanying activation function were tested using seven OCT image classification CNN architectures. The test architectures comprise OctNET, NT-CNN, AOCT-NET, M-CNN, LightOCT, RetiNet, and DeepOCT. Experiments were conducted to assess the impact of the new preprocessing algorithm and the placement of the adaptive convolution layer as a substitute for the conventional convolution layer. Implementing the proposed approaches resulted in accuracy improvements ranging from 0.44% to 2.44% across architectures. Our findings highlight the efficacy of the proposed indirect noise reduction technique and a texture-sensitive adaptive convolution layer.

Precision Identification of Locally Advanced Rectal Cancer in Denoised CT Scans Using EfficientNet and Voting System Algorithms.

Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. In this retrospective study, CT images of 1070 T3-4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model's capability to predict adverse clinical outcomes was superior to those of traditional assessments. AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques.

Usefulness Evaluation for Nonlocal Means Algorithm in Low-Dose Computed Tomography with Various Iterative Reconstruction Intensities and Kernels: A Pilot Study

Usefulness Evaluation for Nonlocal Means Algorithm in Low-Dose Computed Tomography with Various Iterative Reconstruction Intensities and Kernels: A Pilot Study