Deep-Learning Architecture-Based Approach for 2-D-Simulation of Microwave Plasma Interaction

Melanoma and non-melanoma skin cancers have shown a rapidly increasing incidence rate, pointing to skin cancer as a major problem for public health. When analyzing these lesions in dermoscopic images, the hairs and their shadows on the skin may occlude relevant information about the lesion at the time of diagnosis, reducing the ability of automated classification and diagnosis systems. In this work, we present a new approach for the task of hair removal on dermoscopic images based on deep learning techniques. Our proposed model relies on an encoder-decoder architecture, with convolutional neural networks, for the detection and posterior restoration of hair's pixels from the images. Moreover, we introduce a new combined loss function in the network's training phase that combines the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> distance, the total variation loss, and a loss function based on the structural similarity index metric. Currently, there are no datasets that contain the same images with and without hair, which is necessary to quantitatively evaluate our model. Thus, we simulate the presence of hair in hairless images extracted from publicly known datasets. We compare our results with six state-of-the-art algorithms based on traditional computer vision techniques by means of similarity measures that compare the reference hairless image and the one with simulated hair. Finally, the Wilcoxon signed-rank test is used to compare the methods. The results, both qualitatively and quantitatively, demonstrate the effectiveness of our model and how our loss function improves the restoration ability of the proposed model.

An effectively perceptual preprocessing filter method will reduce the sequence’s perceptually insignificant details, which can help to alleviate the video coding’s pressure and benefit the coding results. In this paper, a perceptual rate distortion optimization based preprocessing filter algorithm is presented to achieve better video compression performance. The proposed algorithm employs an adaptively temporal filter with the rate SSIM (Structure Similarity Index Metric) based optimization constraint to produces optimal filter parameters. The evaluation results confirm that the proposed video filter algorithm has achieved reliable rate-visual quality improvements with -4.35% and -2.96% SSIM based BD-Rate performance gain on JM18.3 and HM16.9, respectively. Additionally, the subjective quality comparison results show that our algorithm has reduced significant bits with negligible visual difference for both the experiments on JM18.3 and HM16.9.

Image Denoising is a consistent problem from long period of time and still a challenging task for researchers. There evolved many techniques for image denoising which involves filtering techniques in spatial domain, Transform techniques in transform domain (Sekhar et al. in IRECOS 10(10):1012–1017, 2015 [1]), and more recently evolutionary computing tools (ECT) and genetic algorithms proved more effective in denoising of images. There are many ECT available which can be applied for denoising problem (Sekhar et al. in JGIM 25(4) 2017, [2]). In this paper we made an attempt to Denoise both color and grayscale images by applying a new ECT which emerged out with more efficient results. Peak Signal to noise ratio (PSNR), Structural Similarity Index Metric (SSIM), Mean Structural Similarity Index Metric (MSSIM), etc., are considered in this paper as Image quality Assessment metrics. Comparison of proposed method is also compared with state-of-the-art techniques.

Noise Removal in medical images is a requisite pre-processing step for medical image analysis. In this paper, we present three deep learning architectures: Convolutional Auto-encoders, U-Net and a Double U-Net architecture utilizing convolution layers for medical Image De-noising. We use PSNR(Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index Metric) to compare the results of the networks.In our experiments, the variant of the U-Net architecture implemented performed better than the two architectures in terms of its SSIM.

Given the potential risk of motion artifacts, acquisition time reduction is desirable in pediatric 99m Tc-dimercaptosuccinic acid (DMSA) scintigraphy. The aim of this study was to evaluate the performance of predicted full-acquisition-time images from short-acquisition-time pediatric 99m Tc-DMSA planar images with only 1/5th acquisition time using deep learning in terms of image quality and quantitative renal uptake measurement accuracy. One hundred and fifty-five cases that underwent pediatric 99m Tc-DMSA planar imaging as dynamic data for 10min were retrospectively collected for the development of three deep learning models (DnCNN, Win5RB, and ResUnet), and the generation of full-time images from short-time images. We used the normalized mean squared error (NMSE), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM) to evaluate the accuracy of the predicted full-time images. In addition, the renal uptake of 99m Tc-DMSA was calculated, and the difference in renal uptake from the reference full-time images was assessed using scatter plots with Pearson correlation and Bland-Altman plots. The predicted full-time images from the deep learning models showed a significant improvement in image quality compared to the short-time images with respect to the reference full-time images. In particular, the predicted full-time images obtained by ResUnet showed the lowest NMSE (0.4 [0.4-0.5] %) and the highest PSNR (55.4 [54.7-56.1] dB) and SSIM (0.997 [0.995-0.997]). For renal uptake, an extremely high correlation was achieved in all short-time and three predicted full-time images (R2 >0.999 for all). The Bland-Altman plots showed the lowest bias (-0.10) of renal uptake in ResUnet, while short-time images showed the lowest variance (95% confidence interval: -0.14, 0.45) of renal uptake. Our proposed method is capable of producing images that are comparable to the original full-acquisition-time images, allowing for a reduction of acquisition time/injected dose in pediatric 99m Tc-DMSA planar imaging.

A small dataset commonly affects generalization, robustness, and overall performance of deep neural networks (DNNs) in medical imaging research. Since gathering large clinical databases is always difficult, we proposed an analytical method for producing a large realistic/diverse dataset. Clinical brain PET/CT/MR images including full-dose (FD), low-dose (LD) corresponding to only 5 % of events acquired in the FD scan, non-attenuated correction (NAC) and CT-based measured attenuation correction (MAC) PET images, CT images and T1 and T2 MR sequences of 35 patients were included. All images were registered to the Montreal Neurological Institute (MNI) template. Laplacian blending was used to make a natural presentation using information in the frequency domain of images from two separate patients, as well as the blending mask. This classical technique from the computer vision and image processing communities is still widely used and unlike modern DNNs, does not require the availability of training data. A modified ResNet DNN was implemented to evaluate four image-to-image translation tasks, including LD to FD, LD+MR to FD, NAC to MAC, and MRI to CT, with and without using the synthesized images. Quantitative analysis using established metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), and joint histogram analysis was performed for quantitative evaluation. The quantitative comparison between the registered small dataset containing 35 patients and the large dataset containing 350 synthesized plus 35 real dataset demonstrated improvement of the RMSE and SSIM by 29% and 8% for LD to FD, 40% and 7% for LD+MRI to FD, 16% and 8% for NAC to MAC, and 24% and 11% for MRI to CT mapping task, respectively. The qualitative/quantitative analysis demonstrated that the proposed model improved the performance of all four DNN models through producing images of higher quality and lower quantitative bias and variance compared to reference images.

Aims/Purpose: Our goal is to enhance the visualization of the choroid in clinical standard spectral‐domain OCT (SDOCT) scans using a deep‐learning (DL) approach that uses matching swept‐source OCT (SSOCT). We aim to improve the measurement of the sub‐foveal choroidal thickness (SFCT), total choroidal area (TCA), and choroidal vascularity index (CVI) in SDOCT images.Methods: A total of 105 350 SDOCT and SSOCT B‐scan images (Zeiss Cirrus 5000 and Zeiss PlexElite) were used to develop the DL model. The data set included B‐scans from healthy (238 eye pairs from 155 patients) and glaucoma (192 eye pairs from 122 patients) subjects. The DL model learned deep anatomical features from SSOCT scans and generated enhanced SDOCT images. The peak signal‐to‐noise ratio (PSNR) and structural similarity index metric (SSIM) were used to assess the quality of generated images. In addition, we compared the anatomical parameters derived from the generated and ground‐truth SSOCT images, including SVCT, TCA and CVI values.Results: We tested our method using 20 580 B‐scan image pairs from 84 eyes. The DL‐generated images effectively preserved the anatomical structure of the retina layers and improved the visualization of the choroid. The enhanced SDOCT images had higher image quality than the original SDOCT images, as demonstrated by the higher PSNR (31 dB vs. 18 dB) and SSIM values (3.4 times higher SSIM than the original SDOCT images). SVCT, TCA, and CVI measurements from the DL‐generated SDOCT images showed strong correlations with corresponding measurements using SSOCT with high Pearson's coefficients (0.93, 0.99, and 0.93), high intra‐class correlation indices (0.96, 0.99 and 0.96), and high coefficient of determination r2 values (0.85, 0.98 and 0.86).Conclusions: Our DL model enhances the visibility of the choroid in images, surpassing the capabilities of standard clinical SDOCT images. As a result, accurate measurement of SVCT, TCA and CVI, which were previously limited due to imaging depth constraints of SDOCT, becomes possible. This technology opens up new possibilities for utilizing affordable SDOCT devices to study the choroid in healthy and pathological conditions.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

This research paper explores the rising interest in utilising deep learning methods, specifically Convolution Neural Network (CNN), to improve the reconstruction of Compressively Sampled Magnetic Resonance Imaging (CS MRI) images from under-sampled data. By training deep learning architectures on extensive data sets of paired under sampled and fully sampled MR images, these models aim to capture intricate patterns and structures, ultimately enhancing the accuracy of MR image reconstructions. A novel deep learning model is proposed dubbed as “Deep Iterative Shrinkage Thresholding Algorithm-Compressed Sensing Network” (DISTA-CSNet), specifically designed for efficient recovery of CS MRI. Our model showcases impressive results with only 20 epochs and can be effortlessly trained on diverse datasets. To ensure robustness across different datasets, the dropouts are incorporated into the model, evident from testing results. The trained DISTA-CSNet exhibits remarkable performance in recovering CS MRI from various data sets, surpassing several advanced deep learning techniques with changing compression ratios consistently. The proposed model demonstrates significant enhancements in both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics, affirming the efficacy of our proposed model. The capability of our DISTA-CSNet in accurately reconstructing CS MRI images from 5-fold undersampled data shows promise in improving medical imaging applications and advancing the field of compressed sensing MRI.

The aim was to improve single-photon emission computed tomography (SPECT) quality for sparsely acquired 111In projections by adding deep learning generated synthetic intermediate projections (SIPs). Method: The recently constructed deep convolutional network for generating synthetic intermediate projections (CUSIP) was used for improving 20 sparsely acquired 111In-octreotide SPECTs. Reconstruction was performed with 120 (120P) or 30 (30P) projections, or 120 projections with 90 SIPs generated from 30 projections (30–120SIP). The SPECT reconstructions were performed with attenuation, scatter and collimator response corrections. Postfiltered 30P reconstructed SPECT was also analyzed. Image quality were quantitatively evaluated with root-mean-square error, peak signal-to-noise ratio and structural similarity index metrics. Result: The 30–120SIP reconstructed SPECT had statistically significant improved image quality parameters compared to 30P reconstructed SPECT with and without post filtering. The images visual appearance was similar to slightly filtered 120P SPECTs. Thereby, substantial acquisition time reduction with SIPs seems possible without image quality degradation.

Light field (LF) imaging has gained significant attention due to its recent success in microscopy, 3-dimensional (3D) displaying and rendering, augmented and virtual reality usage. Postprocessing of LF enables us to extract more information from a scene compared to traditional cameras. However, the use of LF is still a research novelty because of the current limitations in capturing high-resolution LF in all of its four dimensions. While researchers are actively improving methods of capturing high-resolution LF's, using simulation, it is possible to explore a high-quality captured LF's properties. The immediate concerns following the LF capture are its storage and processing time. A rich LF occupies a large chunk of memory ---order of multiple gigabytes per LF---. Also, most feature extraction techniques associated with LF postprocessing involve multi-dimensional integration that requires access to the whole LF and is usually time-consuming. Recent advancements in computer processing units made it possible to simulate realistic images using physical-based rendering software. In this work, at first, a transformation function is proposed for building a camera array (CA) to capture the same portion of LF from a scene that a standard plenoptic camera (SPC) can acquire. Using this transformation, LF simulation with similar properties as a plenoptic camera will become trivial in any rendering software. Artificial intelligence (AI) and machine learning (ML) algorithms ---when deployed on the new generation of GPUs--- are faster than ever. It is possible to generate and train large networks with millions of trainable parameters to learn very complex features. Here, residual convolutional neural network (RCNN) structures are employed to build complex networks for compression and feature extraction from an LF. By combining state-of-the-art image compression and RCNN, I have created a compression pipeline. The proposed pipeline's bit per pixel (bpp) ratio is 0.0047 on average. I show that with a 1% compression time cost and 18x speedup for decompression, our methods reconstructed LFs have better structural similarity index metric (SSIM) and comparable peak signal-to-noise ratio (PSNR) compared to the state-of-the-art video compression techniques used to compress LFs. In the end, using RCNN, I created a network called RefNet, for extracting a group of 16 refocused images from a raw LF. The training parameters of the 16 LFs are set to (\alpha=0.125, 0.250, 0.375, ..., 2.0) for training. I show that RefNet is 134x faster than the state-of-the-art refocusing technique. The RefNet is also superior in color prediction compared to the state-of-the-art

Lip reading, the process of interpreting speech by visually observing the movements of the lips, has emerged as a critical area of research with applications spanning communication aids for the hearing impaired, silent speech interfaces, and enhanced human-computer interaction. This paper reviews recent advancements in lip reading technologies, focusing on the integration of machine learning and computer vision techniques. We explore state-of-the-art methods including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based models that have significantly improved the accuracy and robustness of lip reading systems. The study highlights the importance of large annotated datasets, such as LipNet and LRW, which have facilitated the training of deep learning models. Additionally, we examine multimodal approaches that combine visual information with audio signals to enhance performance, especially in noisy environments. Despite substantial progress, challenges remain in addressing speaker variability, low resolution, and real-time processing. Future research directions are discussed, emphasizing the need for more diverse datasets, improved model generalization, and real-world application testing. This comprehensive review underscores the potential of advanced lip reading technologies to revolutionize communication accessibility and human-computer interaction. This paper presents the method for Vision based Lip Reading system that uses convolutional neural network (CNN) with attention-based Long Short-Term Memory (LSTM). The dataset includes video clips pronouncing words sentence. The pretrained CNN is used for extracting features from pre- processed video frames which then are processed for learning temporal characteristics by LSTM. The SoftMax layer of architecture provides the result of lip reading. In the present work experiments are performed with two pre-trained models. The system provides 80% accuracy using Tensorflow and ensemble learning. Keywords— CNN; RNN; LSTM; Tensorflow; lip reading; deep learning

A fusion-domain color image watermarking based on Haar transform and image correction

Focusing on enhancing the security and privacy of electronic medical images (EMI) which have varying properties and larger in number before they are stored or transmitted by hospitals, labs, and researchers or while they reside in third party storage. EMI should be anywhere, anytime accessible for referencing and medical diagnosis. Therefore, should be accessible in real-time through real-time applications (RTA). This research work uses a large data set having 5856 X-ray images of a total size of 1.6 GB in JPEG format each of these X-ray images vary in properties such as size and dimensions. Two methods have been implemented for enhancing security and privacy Edge-Based Steganography (EBS) and Block-Based Steganography (BBS) in the region of no interest (RONI) of the normalized cover image. Both methods are compared for enhancement concerning steganography properties such as payload capacity, imperceptibility, security, reduction in computational time, and lesser computational complexity which increases their applicability for RTA. RTA makes EMI accessible on heterogeneous devices, therefore, increasing its scalability and usage. This paper performs comparative evaluation based on standardized tests such as Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Metrics (SSIM), Coefficient of Variation (CV), and Pearson Correlation (R), etc. Results show that both methods achieved a 100% embedding rate, SSIM value close to 1, and low average MSE value of 0.005 for EBS secret images and 0.003 for BBS secret images. Results indicate both methods are capable of hiding large data sets within minutes therefore making them both suitable for RTA while the EBS method takes 2.3 minutes which is less than BBS’s 3.6 minutes encoding time for 5856 images. Therefore, the EBS method was found more suitable than the BBS method based on computational time.

The measurement and evaluation of the QoE (Quality of Experience) have become one of the main focuses in the telecommunications to provide services with the expected quality for their users. However, factors like the network parameters and codification can affect the quality of video, limiting the correlation between the objective and subjective metrics. The above increases the complexity to evaluate the real quality of video perceived by users. In this paper, a model based on artificial neural networks such as BPNNs (Backpropagation Neural Networks) and the RNNs (Random Neural Networks) is applied to evaluate the subjective quality metrics MOS (Mean Opinion Score) and the PSNR (Peak Signal Noise Ratio), SSIM (Structural Similarity Index Metric), VQM (Video Quality Metric), and QIBF (Quality Index Based Frame). The proposed model allows establishing the QoS (Quality of Service) based in the strategyDiffserv. The metrics were analyzed through Pearson’s and Spearman’s correlation coefficients, RMSE (Root Mean Square Error), and outliers rate. Correlation values greater than 90% were obtained for all the evaluated metrics.