Advancing Autoencoders and Non-Local Means with Particle Swarm Optimization

Non-local means (NLM) filter is one of the state-of-the-art denoising filters. It exploits the presence of similar features in an image and averages those similar features to remove noise. However, a conventional NLM filter shows somewhat inferior performance of noise reduction around edges, suffering from low efficiency of collecting similar features to be averaged. In order to overcome this phenomenon, we propose a NLM filter with double Gaussian anisotropic kernels as a substitute for the conventional homogeneous kernel to effectively remove noise from OCT images corrupted by speckle noise. The proposed filter was evaluated by comparing with various denoising filters such as conventional NLM filter, median filter, bilateral filter, and Wiener filter. The fingertip OCT images, which were processed with the different denoising filters, indicated that the proposed NLM filter provides superior denoising performance, among the filters in terms of the contrast-to-noise ratio (CNR), the equivalent number of looks (ENL), and the speckle suppression index (SSI). A human retina OCT image was also used to compare and show the performances of noise reduction among different filters. In addition, the denoising performance with the proposed NLM filter was also investigated in the synthetic images for fair comparison among the filters by calculating the peak signal-to-noise ratio (PSNR). The proposed NLM filter outperformed the conventional NLM filter as well as the other filters.

Medical image analysis is highly susceptible to noise during acquisition and transmission, significantly degrading diagnostic accuracy. This study proposes a robust Attention-Based Squeeze-Excitation Residual Autoencoder (ASE-RAE) for denoising medical images corrupted by Gaussian and Salt-and-Pepper (SP) noise. The network integrates residual skip connections in both encoder and decoder paths, combined with Squeeze-and-Excitation (SE) blocks and a Convolutional Block Attention Module (CBAM) to improve channel and spatial feature representation. The model is benchmarked against traditional denoising techniques, including Non-Local Means Filter (NLMF), Median Filter (MF), Wavelet Transform (WT), Gaussian Filter (GF), and Convolutional Neural Networks (CNNs). Quantitative evaluation using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Mean Squared Error (MSE) demonstrates that the proposed method consistently outperforms all baseline models across varying noise intensities (5%–75%) on the IQ-OTH/NCCD lung CT dataset. Furthermore, ablation studies confirm the contribution of each module (SE and CBAM) to performance gains. The proposed architecture preserves diagnostic features while suppressing both random and structured noise, and its convolutional SE implementation reduces computational overhead compared to conventional fully connected attention blocks. This work highlights a scalable, interpretable solution for image denoising in clinical workflows and sets a foundation for real-time deployment in AI-assisted diagnostics.

Digital images have progressed significantly in many areas but various types of noise still exist in real-world images such as Gaussian noise, Poisson noise, Salt-and-pepper noise so on. Although image denoising plays an important role to remove noise from images by using many techniques to preserve the important feature of an image but faces the problem of computational complexity, over smoothing. To address these limitations proposed paper introduces hybrid image denoising technique that combines the strengths of Wavelet transform and Non-Local Means (NLM) filtering, with enhanced Otsu thresholding. In proposed work, firstly the noisy image is denoised by wavelet-based Otsu thresholding and then NLM is employed to improve the enhance edge preservation of an image by eliminating the further noise. Kodak 24 dataset is used to test the images. Furthermore, we compare the proposed technique to the existing technique based on the performance metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Squared Error (RMSE). The Kodak24 dataset is used to evaluate the proposed hybrid denoising method. Experimental results show that the proposed technique outperforms existing approaches in terms of PSNR (34.86), SSIM (0.93) and RMSE (4.61) demonstrating its effectiveness in denoising and preserving structural image quality. Additionally, the FOM and VIF scores indicate the outstanding results of the hybrid strategy: both the FOM and VIF values were the best among all other assessed denoising methods, attained to 0.99 and 0.59, respectively.

Polycystic Ovary Syndrome (PCOS) is a common endocrine disorder in women that is frequently diagnosed by ultrasound imaging by examining ovarian abnormality. Ultrasound images, though, are normally contaminated with speckle noise that degrades image quality and poses difficulties for diagnosis. Conventional denoising methods like mean and median filtering are unable to eliminate noise properly while maintaining fine details. To solve this problem, this paper introduces a new Attention-based Autoencoder (AAE) for denoising PCOS ultrasound images. The model uses an attention mechanism to selectively amplify significant image areas and suppress noise, enhancing image quality for diagnosis. The introduced method was tested on a publicly available ultrasound dataset with synthetic speckle noise at various levels (variance 0.5, 0.02, and 0.001). Experimental results prove that the suggested method performs better than conventional denoising methods, with peak signal-to-noise ratio (PSNR) values of 31.33, 34.25, and 36.23, respectively. The structural similarity index measure (SSIM) also reveals notable improvements and corresponding scores of 85.21, 92.33, and 99.25. Beyond technical performance, this work supports the development of scalable, AI-driven PCOS diagnostic tools within a technopreneurship incubator model. These results indicate that AAEs can improve ultrasound image quality, facilitating more accurate PCOS diagnosis.

An ultrasound image provides the radiologist with noninvasive, low cost, and real-time images that can help them in diagnosis, planning and therapy. However, although the human eye is able to derive the meaningful information from these images, automatic processing is very difficult because of the noise and artifacts present in the image. This paper proposes different filtering techniques based on feature vector based statistical methods for the removal of speckle noise. In this work, we propose to extend the current hybrid median filter technique to deal with the speckle noise present in the Ultrasound images. Metrics like Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Root Mean Square Error (RMSE) and Structural Similarity Index Measurement (SSIM) are used to evaluate the efficiency of the proposed work. Experimental results and performance analysis shows promising results when compared with existing methods.

Speckle noise in ultrasound images compromises image quality and hinders diagnostic accuracy. Traditional ultrasound denoising methods often struggle to preserve anatomical details while effectively reducing noise, especially under high-noise conditions. In this study, we propose an innovative approach that integrates a lightweight channel attention mechanism (LCAM) within a convolutional variational autoencoder (CVAE) framework to enhance ultrasound image denoising. The proposed approach efficiently reduces speckle noise while maintaining essential anatomical features. Comprehensive evaluations across six diverse ultrasound datasets demonstrate that the LCAM-CVAE outperforms conventional denoising techniques in both subjective image quality and objective performance metrics, including peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), standard deviation in PSNR (SD-PSNR), standard deviation in SSIM (SD-SSIM), PSNR statistical relevance tests, and computational efficiency (CE). The LCAM-CVAE approach demonstrates exceptional performance, particularly under high-noise conditions, ensuring the preservation of key anatomical structures for accurate diagnosis. These results highlight the LCAM-CVAE approach as a robust and promising solution for ultrasound image denoising, with significant clinical potential to improve diagnostic quality in noisy environments.

Steganography as a practice is highly useful as it allows information to be concealed within digital images while maintaining visual quality. However, it can be a challenge to balance imperceptibility, capacity, and robustness while ensuring that embedded data remains secure against statistical and Deep Learning (DL)-based steganalysis. Therefore, we propose a new framework that utilizes the BOSSbase dataset for cover images, the USC-SIPI dataset for secreted images, and introduces adaptive image steganography, which combines fused map-based embedding with evolutionary optimization to solve existing problems. The system starts by encrypting the secret image through Blowfish cipher encryption to protect its confidentiality. The model generates a fused map through a combination of entropy and Laplacian-based noise maps from the cover image to determine the most suitable embedding areas. Next, we optimize the process of embedding location selection and ordering using Particle Swarm Optimization (PSO) to maximize both security and image quality. Next, we use priority-guided Least Significant Bits (LSB) substitution in the embedding process to generate an optimized priority map for inserting the encrypted bitstream into the image. The system can function on different cover image sizes, so at [Formula: see text] the resolution is 51-61 dB Peak Signal-to-Noise Ratio (PSNR) and 0.9972-1.0 Structural Similarity Index Measure (SSIM) for stego images at 0.1-1.0 Bits Per Pixel (BPP) with 262,144 bits while maintaining perfect secret reconstruction (SSIM = 1.000) and processing times under 0.25 seconds for embedding and extraction. Security tests demonstrate that the proposed system remains undetectable since the Area Under Curve (AUC) for [Formula: see text] reaches 0.49-0.57 across all payload levels and Regular Singular (RS) statistics remain at 0.59-0.66 between 0.1-1.0 BPP. The proposed model provides effective capacity while maintaining high visual quality and security against DL-based steganalysis, such as that using Convolutional Neural Networks (CNN).

One of the harmful diseases among females in the world is breast cancer. Breast cancer leftovers a noteworthy scientific, clinical and communal challenge. Ultrasound is high-frequency sound wave used to capture images of internal organs of a human. Failure of detection in mammogram can be seen in an ultrasound. This work proposes an efficient scheme to locate and examine mistrustful masses in breast ultrasound images by extracting some region of interest. The presence of speckle noise in ultrasound images upset edges and fine specifics which limits the contrast resolution. These aspects will intensify the difficulty in diagnosis. A relative examination was also done between the Median and Gaussian filter, and proved that median filter has the highest stuff to remove speckle noise from the ultrasound image. Another important problem with ultrasound images is low contrast. To eliminate this, contrast enhancement is done by using Adaptive Histogram Equalization. In the earlier works, breast cancer is diagnosed using various machine learning algorithms. Particle swarm optimization, K-Medoids clustering, and chaotic particle swarm optimization are the algorithms used in this work. These algorithms improve the accuracy in detecting cancer. The results of the above algorithms are compared using the dice coefficient and it is proved that CPSO algorithm has dice coefficient value of 87.35% which is closer to manual segmentation. The above algorithms produced an accuracy of 82.3134% (k-Medoids), 82.1554% (PSO), 93.5793% (CPSO). The existing watershed transformation based segmentation method produces only 84.85%) accuracy when used for solving the same problem. This proves that the CPSO algorithm is best suited for this problem compared to the earlier methods.

Conventional whole-body (WB) PET imaging using short axial field-of-view (SAFOV) scanners is constrained by low sensitivity and limited temporal resolution, particularly for dynamic and kinetic parametric imaging. This study introduces a supervised deep learning framework to enhance WB Patlak parametric images (Ki) from SAFOV scanners by leveraging high-sensitivity data from long axial field-of-view (LAFOV) uEXPLORER system. Dynamic <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">${ }^{18}$</tex> F-FDG PET scans were acquired from two cohorts: 15 subjects using the uEXPLORER and 19 subjects using the Siemens Biograph mCT (SAFOV) with a 6 -minute single-bed acquisition in the cardiac region followed by 13 WB passes via continuous bed motion. Low-quality (LQ) WB parametric images were simulated from LAFOV data using <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$15 \sec \times 13$</tex> frames with 4 -minute interval (short-frame protocol), while how-quality (HQ) parametric images were reconstructed from LAFOV standard protocol. The image data starting from 20 minutes were used to reconstruct Patlak images. A 2D conditional consistency model (denoted as cDDPM-CM) was developed, incorporating LQ Ki images and prior PET images (average of dynamic frames converted to SUV) as conditioning inputs. The model was trained via a 5 -fold cross-validation on LAFOV data (4680 slices). Results demonstrated that the cDDPM-CM significantly outperformed traditional denoising methods (Gaussian filtering, non-local means) and a baseline DDPM-CM model (without prior PET image) in enhancing LQ LAFOV images, achieving a peak signal-to-noise ratio (PSNR) of 39.08, normalized root mean square error (NRMSE) of 0.3445, and structural similarity index measure (SSIM) of 0.9433. Similar improvements were observed in SAFOV images, with enhanced clarity and reduced noise.

This paper presents a comprehensive evaluation of a novel speckle reduction framework tailored for polarimetric synthetic aperture radar (PolSAR) data. The study investigates the framework's performance across various polarization data configurations, including Full Polarimetry (Full Pol) and Single Polarization (Single Pol), operating across different frequency bands such as L, and S band. With a specific focus on T3 matrix elements (T11, T12, T13, T22, T33, and T23) and full polarimetric (full pol) data, the primary objective is to conduct an in-depth comparative analysis of the proposed framework against established speckle reduction techniques. To achieve this, the proposed framework is rigorously compared with well-known methods such as Refined Lee, Lopez, Lee Sigma, Non-Local Means, and IDAN filters across the aforementioned polarization and frequency configurations. Performance evaluation is conducted using a diverse set of metrics, including Signal-to-Noise Ratio (SNR), Equivalent Number of Looks (ENL), Coefficient of Variation (CV), Speckle Suppression Index (SSI), Speckle Suppression and Mean Preservation Index (SMPI), and Structural Similarity Index Measure (SSIM). The results of this evaluation demonstrate the superior performance of the proposed framework, with significant improvements in speckle reduction and preservation of image detail compared to existing techniques. These findings highlight the potential of the proposed framework as a valuable tool for the processing and analysis of PolSAR data across different polarization configurations and frequency bands, providing a comprehensive solution to the challenges posed by speckle noise in SAR imagery.

Despeckling of ultrasound images, as a very active topic research in medical image processing, plays an important or even indispensable role in subsequent ultrasound image processing. The non-local total variation (NLTV) method has been widely applied to denoising images corrupted by Gaussian noise, but it cannot provide satisfactory restoration results for ultrasound images corrupted by speckle noise. To address this problem, a novel non-local total variation despeckling method is proposed for speckle reduction. In the proposed method, the non-local gradient is computed on the images restored by the optimized Bayesian non-local means (OBNLM) method and it is introduced into the total variation method to suppress speckle in ultrasound images. Comparisons of the restoration performance are made among the proposed method and such state-of-the-art despeckling methods as the squeeze box filter (SBF), the non-local means (NLM) method and the OBNLM method. The quantitative comparisons based on synthetic speckled images show that the proposed method can provide higher Peak signal-to-noise ratio (PSNR) and structure similarity (SSIM) than compared despeckling methods. The subjective visual comparisons based on synthetic and real ultrasound images demonstrate that the proposed method outperforms other compared algorithms in that it can achieve better performance of noise reduction, artifact avoidance, edge and texture preservation.

Synthetic aperture radar (SAR) image segmentation usually involves two crucial issues: suitable speckle noise removing technique and effective image segmentation methodology. Here, an efficient SAR image segmentation method considering both of the two aspects is presented. As for the first issue, the famous nonlocal mean (NLM) filter is introduced in this study to suppress the multiplicative speckle noise in SAR image. Furthermore, to achieve a higher denoising accuracy, the local neighboring pixels in the searching window are projected into a lower dimensional subspace by principal component analysis (PCA). Thus, the nonlocal mean filter is implemented in the subspace. Afterwards, a multi-objective clustering algorithm is proposed using the principals of artificial immune system (AIS) and kernel-induced distance measures. The multi-objective clustering has been shown to discover the data distribution with different characteristics and the kernel methods can improve its robustness to noise and outliers. Experiments demonstrate that the proposed method is able to partition the SAR image robustly and accurately than the conventional approaches.

We propose a modified Perona-Malik diffusion (PMD) filter to enhance a coronary plaque boundary by considering the conditions peculiar to an intravascular ultrasound (IVUS) image. The IVUS image is commonly used for a diagnosis of acute coronary syndrome (ACS). The IVUS image is however very grainy due to heavy speckle noise. When the normal PMD filter is applied for speckle noise reduction in the IVUS image, the coronary plaque boundary becomes vague. For this problem, we propose a modified PMD filter which is designed in special reference to the coronary plaque boundary detection. It can then not only reduce the speckle noise but also enhance clearly the coronary plaque boundary. After applying the modified PMD filter to the IVUS image, the coronary plaque boundaries are successfully detected further by applying the Takagi-Sugeno fuzzy model. The accuracy of the proposed method has been confirmed numerically by the experiments.

In the area of musculoskeletal MR images analysis, the image denoising plays an important role in enhancing the spatial image area for further processing. Recent studies have shown that non-local means (NLM) methods appear to be more effective and robust when compared with conventional local statistical filters, including median or average filters, when Rician noise is presented. A significant limitation of NLM is the fact that thy have the tendency to suppress tiny objects, which may represent clinically important information. For this reason, we provide an extensive quantitative and objective analysis of a novel NLM algorithm, taking advantage of pixel and patch similarity information with the optimization procedure for optimal filter parameters selection to demonstrate a higher robustness and effectivity, when comparing with NLM and conventional local means methods, including average and median filters. We provide extensive testing on variable noise generators with dynamical noise intensity to objectively demonstrate the robustness of the method in a noisy environment, which simulates relevant, variable and real conditions. This work also objectively evaluates the potential and benefits of the application of NLM filters in contrast to conventional local-mean filters. The final part of the analysis is focused on the segmentation performance when an NLM filter is applied. This analysis demonstrates a better performance of tissue identification with the application of smoothing procedure under worsening image conditions.

Applications of Ultrasound in examining physical health of patient are continuously expanding over last few decades. Ultrasound imaging has assisted doctors in the diagnosis of medical health of patient in obstetrics, cardiology, gynaecology, musculoskeletal, urology and others. It has proved to be very promising and considerably advantageous over other imaging methods because of its features like non-invasive nature, use of non-ionizing radiation, portability, rapidity in performance, ease and cheap availability, real time imaging capability, high patient acceptability. Despite many advantages, it suffers from Speckle noise which results in affecting image resolution and contrast making an adverse impact on the diagnostic capability of the imaging modality. In this paper, we attempt to remove speckle noise from musculoskeletal ultrasound image for shoulder application using Anisotropic Diffusion and Non-Local Means (NLM) method. The quantitative analysis of the result is done using measurement indexes such as peak signal to noise ratio (PSNR), signal to noise ratio (SNR) and root mean square error (RMSE), whereas, visual inspection is carried out for qualitative analysis.