Synthetic Images Research Articles

Denoising and analysis of synthetic aperture radar images using improved weight threshold technique in curvelet transform frequency domain

Denoising and analysis of synthetic aperture radar images using improved weight threshold technique in curvelet transform frequency domain

Multiparametric approach with synthetic MR imaging for diagnosing salivary gland lesions.

To determine whether synthetic MR imaging can distinguish between benign and malignant salivary gland lesions. The study population included 44 patients with 33 benign and 11 malignant salivary gland lesions. All MR imaging was obtained using a 3 Tesla system. The QRAPMASTER pulse sequence was used to acquire images with four TI values and two TE values, from which quantitative images of T1 and T2 relaxation times and proton density (PD) were generated. The Mann-Whitney U test was used to compare T1, T2, PD, and ADC values among the subtypes of salivary gland lesions. ROC analysis was used to evaluate diagnostic capability between malignant tumors (MTs) and either pleomorphic adenomas (PAs) or Warthin tumors (WTs). We further calculated diagnostic accuracy for distinguishing malignant from benign lesions when combining these parameters. PAs demonstrated significantly higher T1, T2, PD, and ADC values than WTs (all p < 0.001). Compared to MTs, PAs had significantly higher T1, T2, and ADC values (all p < 0.001), whereas WTs had significantly lower T1, T2, and PD values (p < 0.001, p = 0.008, and p = 0.003, respectively). T2 and ADC were most effective in differentiating between MTs and PAs (AUC = 0.928 and 0.939, respectively), and T1 and PD values for differentiating between MTs and WTs (AUC = 0.915 and 0.833, respectively). Combining T1 with T2 or ADC achieved accuracy of 86.4% in distinguishing between malignant and benign tumors. Similarly, combining PD with T2 or ADC reached accuracy of 86.4% for differentiating between malignant and benign tumors. Utilizing a combination of synthetic MRI parameters may assist in differentiating malignant from benign salivary gland lesions.

Enforcing Traffic Safety: A Deep Learning Approach for Detecting Motorcyclists’ Helmet Violations Using YOLOv8 and Deep Convolutional Generative Adversarial Network-Generated Images

In this study, we introduce an innovative methodology for the detection of helmet usage violations among motorcyclists, integrating the YOLOv8 object detection algorithm with deep convolutional generative adversarial networks (DCGANs). The objective of this research is to enhance the precision of existing helmet violation detection techniques, which are typically reliant on manual inspection and susceptible to inaccuracies. The proposed methodology involves model training on an extensive dataset comprising both authentic and synthetic images, and demonstrates high accuracy in identifying helmet violations, including scenarios with multiple riders. Data augmentation, in conjunction with synthetic images produced by DCGANs, is utilized to expand the training data volume, particularly focusing on imbalanced classes, thereby facilitating superior model generalization to real-world circumstances. The stand-alone YOLOv8 model exhibited an F1 score of 0.91 for all classes at a confidence level of 0.617, whereas the DCGANs + YOLOv8 model demonstrated an F1 score of 0.96 for all classes at a reduced confidence level of 0.334. These findings highlight the potential of DCGANs in enhancing the accuracy of helmet rule violation detection, thus fostering safer motorcycling practices.

Phenotyping methodologies of log end splitting in eucalyptus (Eucalyptus spp.)

AbstractThis study addresses the crucial consideration of log end splitting in breeding programmes for treated wood. There is a paucity of research focused on efficiently optimizing the phenotyping process for this particular trait. The study aimed to compare methodologies for log end splitting phenotyping and develop an image‐based crack evaluation approach. Initially, 32 eucalyptus clones underwent phenotyping using manual measurement, digital image analysis and visual evaluation. Results showed similar phenotypic values, but image analysis demonstrated better clone discrimination, reducing evaluation time to 78 h compared to manual measurement. The second part focused on testing convolutional neural network architectures (UNet, LinkNet and FPN) using real and synthetic images. U‐Net exhibited slight superiority based on higher Intersection over Union (IoU) values, exhibiting a high correlation (.89) with true values. This approach significantly reduced evaluation time to approximately 10.15 h, emphasizing its efficiency compared to traditional methods.

Validating Synthetic Data for Perception in Autonomous Airport Navigation Tasks

Autonomous navigation within airport environments presents significant challenges, mostly due to the scarcity of accessible and labeled data for training autonomous systems. This study introduces an innovative approach to assess the performance of vision-based models trained on synthetic datasets, with the goal of determining whether simulated data can train and validate navigation operations in complex airport environments. The methodology includes a comparative analysis employing image processing techniques and object detection algorithms. A comparative analysis of two different datasets was conducted: a synthetic dataset that mirrors real airport scenarios, generated using the Microsoft Flight Simulator 2020®video game, and a real-world dataset. The results indicate that models trained on a combination of both real and synthetic images perform much better in terms of adaptability and accuracy compared to those trained only on one type of dataset. This analysis makes a significant contribution to the field of autonomous airport navigation and offers a cost-effective and practical solution to overcome the challenges of dataset acquisition and algorithm validation. It is thus believed that this study lays the groundwork for future advancements in the field.

ECG-image-kit: a synthetic image generation toolbox to facilitate deep learning-based electrocardiogram digitization

Abstract Objective: Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution.&amp;#xD;&amp;#xD;Approach: We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background.&amp;#xD;&amp;#xD;Main results: As a case study, we used ECG-Image-Kit to create a dataset of 21,801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio (SNR) and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization.&amp;#xD;&amp;#xD;Significance: The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.

Optimizing synthetic aperture radar image classification and change detection: a proportional factor firefly algorithm and multilayer perceptron approach

Optimizing synthetic aperture radar image classification and change detection: a proportional factor firefly algorithm and multilayer perceptron approach

Application of MR Images in Radiotherapy Planning for brain tumor Based on Deep Learning

Purpose: Explore the function and dose calculation accuracy of MRI images in radiotherapy planning through deep learning methods. Methods: 131 brain tumor patients undergoing radiotherapy with previous MR and CT images were recruited for this study. A new series of MRI from the aligned MR was firstly registered to CT images strictly using MIM software and then resampled. A deep learning method (U-NET) was used to establish a MRI-to-CT conversion model, for which 105 patient images were used as the training set and 26 patient images were used as the tuning set. Data from additional 8 patients were collected as the test set, and the accuracy of the model was evaluated from a dosimetric standpoint. Results: Comparing the synthetic CT images with the original CT images, the difference in dosimetric parameters D98, D95, D2 and Dmean of PTV in 8 patients was less than 0.5%. The gamma passed rates of PTV and whole body volume were: 1%/1mm: 93.96%±6.75%, 2%/2mm: 99.87%±0.30%, 3%/3mm: 100.00%±0.00%; and 1%/1mm: 99.14%±0.80%, 2%/2mm: 99.92%±0.08%, 3%/3mm: 99.99%±0.01%. Conclusion: MR images can be used both in delineation and treatment efficacy evaluation and in dose calculation. Using the deep learning way to convert MR image to CT image is a viable method and can be further used in dose calculation.

SwinYOLOv7: Robust ship detection in complex synthetic aperture radar images

Using satellite-based SAR (Synthetic Aperture Radar) imagery to detect and track ships is a formidable challenge. However, accurate analysis is hampered by inherent difficulties such as obscured edges, multiple targets, varying dimensions and complex backgrounds. These factors contribute to a poor signal-to-noise ratio. Various artificial intelligence models have been developed to improve these problems, especially with YOLO-based models. To overcome the above challenges and achieve robust performance, this study presents a model called SwinYOLOv7, a novel fusion of the YOLOv7 framework with the Features Pyramid Network and the Swin Transformer using ground-breaking anchor-free detection algorithms. This innovative method aims to increase the accuracy of vessel detection while reducing the impact of background clutter. The proposed model improved by YOLOv7 examined three different datasets in detail: SRSDD-v1.0, HRSID, and SSDD to optimize the performance of the model. The training process was consistently verified using superior recall, precision, and F1-score values, which can be easily compared with previous studies. The results show that the model using the Swin Transformer attention mechanism and using an image size of 640×640 achieves the highest accuracy of 96.59%. Alternative attention mechanisms, including the Squeeze-and-Excitation Network (SEnet), the Convolutional Block Attention Module (CBAM), Channel Attention (CA) and Efficient Channel Attention (ECA), deliver poorer accuracy rates. The combination of YOLOv7 and Swin Transformer yielded encouraging results that enabled the proposed model to outperform the current benchmarking models. Therefore, the proposed model provides a compelling solution to ensure accurate vessel identification in complex search and rescue scenarios.

Deep learning-based bubble detection with swin transformer

ABSTRACT We developed a deep learning-based bubble detector with a Shifted window Transformer (Swin Transformer) to detect and segment individual bubbles among overlapping bubbles. To verify the performance of the detector, we calculated its average precision (AP) with different number of training images. The mask AP increased with the increase in the number of training images when there were less than 50 images. It was observed that the AP for the Swin Transformer and ResNet were almost the same when there were more than 50 images; however, when few training images were used, the AP of the Swin Transformer were higher than that of the ResNet. Furthermore, for the increase in void fraction, the AP of the Swin Transformer showed a decrease similar to that in the case of the ResNet; however, for few training images, the AP of the Swin Transformer was higher than that of the ResNet in all void fractions. Moreover, we confirmed the detector trained with experimental and synthetic bubble images was able to segment overlapping bubbles and deformed bubbles in a bubbly flow experiment. Thus, we verified that the new bubble detector with Swin Transformer provided higher AP than the detector with ResNet for fewer training images.

Cascaded combination of total variation regularization and contrast limited adaptive histogram equalization based image dehazing

ABSTRACT Haze and fog can significantly reduce the visibility of distant objects by scattering light and creating blurry, washed-out images lacking in detail. Image dehazing is a technique used in computer vision to enhance the clarity of such obscured images. This study examines the effectiveness of various dehazing methods using real hazy images and synthetic images with artificially created haze. Performance metrics such as PSNR, SSIM, MSE, CII, and computation time are used to evaluate the proposed method. The evaluation is carried out on datasets like RESIDE, GMAN, O-Haze, I-Haze, NH-Haze, and Dense haze to compare the proposed method with existing models. The proposed method attains 27.46%, 20.63% and 21.09% higher PSNR and 12.36%, 23.95% and 36.12% lower Natural Image Quality Evaluator for RESIDE dataset when analyzed to the existing models, such as strategic method towards contrast enhancement by 2D histogram equalization under TV decomposition (CE-TDHE-TVD), multiple level framework basis contrast enhancement for uniform with non-uniform back ground imageries utilizing appropriate histogram equalization (CE-VHE), and Contrast enhancement with brightness preservation of low light pictures with the help of combined CLAHE and BPDHE histogram equalization (CE-CLAHE-BPDHE) respectively.

Application of deep learning and inline holography to estimate the droplet size distribution

We examine five machine learning-based architectures to estimate the droplet size distributions obtained using digital inline holography. The architectures, namely, U-Net, R2 U-Net, Attention U-Net, V-Net, and Residual U-Net, are trained using synthetic holographic images. Our assessment focuses on evaluating the training, validation, and prediction performance of these architectures. Our results indicate that U-Net and R2 U-Net are the most proficient architectures, consistently demonstrating superior performance trends and achieving the highest Intersection Over Union (IOU) scores among the five architectures studied. We employ additional training using experimental holographic images for the two top-performing architectures to validate their efficacy further. Subsequently, they are employed to segment an experimental dataset illustrating the bag breakup phenomenon, facilitating the extraction of size distribution. The extracted size distribution from U-Net and R2 U-Net segmentation is then compared with the analytical model proposed by Jackiw and Ashgriz (2022) by employing the gamma and log-normal distributions. Our findings indicate that the gamma distribution provides a more accurate prediction of the multi-modal size distribution than the log-normal distribution owing to its long exponential tail. The present study offers valuable insights into the effectiveness of machine learning architectures in estimating particle/droplet sizes, highlighting their practical application in real-world experimental scenarios.

Optical coherence tomography choroidal enhancement using generative deep learning

Spectral-domain optical coherence tomography (SDOCT) is the gold standard of imaging the eye in clinics. Penetration depth with such devices is, however, limited and visualization of the choroid, which is essential for diagnosing chorioretinal disease, remains limited. Whereas swept-source OCT (SSOCT) devices allow for visualization of the choroid these instruments are expensive and availability in praxis is limited. We present an artificial intelligence (AI)-based solution to enhance the visualization of the choroid in OCT scans and allow for quantitative measurements of choroidal metrics using generative deep learning (DL). Synthetically enhanced SDOCT B-scans with improved choroidal visibility were generated, leveraging matching images to learn deep anatomical features during the training. Using a single-center tertiary eye care institution cohort comprising a total of 362 SDOCT-SSOCT paired subjects, we trained our model with 150,784 images from 410 healthy, 192 glaucoma, and 133 diabetic retinopathy eyes. An independent external test dataset of 37,376 images from 146 eyes was deployed to assess the authenticity and quality of the synthetically enhanced SDOCT images. Experts’ ability to differentiate real versus synthetic images was poor (47.5% accuracy). Measurements of choroidal thickness, area, volume, and vascularity index, from the reference SSOCT and synthetically enhanced SDOCT, showed high Pearson’s correlations of 0.97 [95% CI: 0.96–0.98], 0.97 [0.95–0.98], 0.95 [0.92–0.98], and 0.87 [0.83–0.91], with intra-class correlation values of 0.99 [0.98–0.99], 0.98 [0.98–0.99], and 0.95 [0.96–0.98], 0.93 [0.91–0.95], respectively. Thus, our DL generative model successfully generated realistic enhanced SDOCT data that is indistinguishable from SSOCT images providing improved visualization of the choroid. This technology enabled accurate measurements of choroidal metrics previously limited by the imaging depth constraints of SDOCT. The findings open new possibilities for utilizing affordable SDOCT devices in studying the choroid in both healthy and pathological conditions.

Brain MR image segmentation for tumor detection based on Riesz probability distributions

ABSTRACT This research introduces a new approach using the Riesz mixture model for medical image segmentation, specifically for diagnosing and treating brain tumors. We developed a novel technique for pixel classification based on the Riesz distribution, which is generated using an extended Bartlett decomposition. Our work is pioneering, as there are no existing studies addressing this issue in the literature. We aim to demonstrate the effectiveness of this distribution for brain image segmentation. We used the Expectation-Maximization algorithm to estimate the mixture parameters. To validate our segmentation algorithm, we conducted a comparative study with a recent method based on the Wishart distribution using Matlab software. Experiments with the Riesz mixture model showed that our method produces more intuitive results with a recognition rate of 94.52%. These results confirm the reliability of our method in detecting tumors using both synthetic and real brain images.

Self-supervised anatomical continuity enhancement network for 7T SWI synthesis from 3T SWI

Synthesizing 7T Susceptibility Weighted Imaging (SWI) from 3T SWI could offer significant clinical benefits by combining the high sensitivity of 7T SWI for neurological disorders with the widespread availability of 3T SWI in diagnostic routines. Although methods exist for synthesizing 7T Magnetic Resonance Imaging (MRI), they primarily focus on traditional MRI modalities like T1-weighted imaging, rather than SWI. SWI poses unique challenges, including limited data availability and the invisibility of certain tissues in individual 3T SWI slices. To address these challenges, we propose a Self-supervised Anatomical Continuity Enhancement (SACE) network to synthesize 7T SWI from 3T SWI using plentiful 3T SWI data and limited 3T–7T paired data. The SACE employs two specifically designed pretext tasks to utilize low-level representations from abundant 3T SWI data for assisting 7T SWI synthesis in a downstream task with limited paired data. One pretext task emphasizes input-specific morphology by balancing the elimination of redundant patterns with the preservation of essential morphology, preventing the blurring of synthetic 7T SWI images. The other task improves the synthesis of tissues that are invisible in a single 3T SWI slice by aligning adjacent slices with the current slice and predicting their difference fields. The downstream task innovatively combines clinical knowledge with brain substructure diagrams to selectively enhance clinically relevant features. When evaluated on a dataset comprising 97 cases (5495 slices), the proposed method achieved a Peak Signal-to-Noise Ratio (PSNR) of 23.05 dB and a Structural Similarity Index (SSIM) of 0.688. Due to the absence of specific methods for 7T SWI, our method was compared with existing enhancement techniques for general 7T MRI synthesis, outperforming these techniques in the context of 7T SWI synthesis. Clinical evaluations have shown that our synthetic 7T SWI is clinically effective, demonstrating its potential as a clinical tool.

Creating realistic anterior segment optical coherence tomography images using generative adversarial networks

AimsTo develop a generative adversarial network (GAN) capable of generating realistic high-resolution anterior segment optical coherence tomography (AS-OCT) images.MethodsThis study included 142 628 AS-OCT B-scans from the American University of...

Stereo matching from monocular images using feature consistency

AbstractSynthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks.

SWIFT: Simulated Wildfire Images for Fast Training Dataset

Wildland fires cause economic and ecological damage with devastating consequences, including loss of life. To reduce these risks, numerous fire detection and recognition systems using deep learning techniques have been developed. However, the limited availability of annotated datasets has decelerated the development of reliable deep learning techniques for detecting and monitoring fires. For such, a novel dataset, namely, SWIFT, is presented in this paper for detecting and recognizing wildland smoke and fires. SWIFT includes a large number of synthetic images and videos of smoke and wildfire with their corresponding annotations, as well as environmental data, including temperature, humidity, wind direction, and speed. It represents various wildland fire scenarios collected from multiple viewpoints, covering forest interior views, views near active fires, ground views, and aerial views. In addition, three deep learning models, namely, BoucaNet, DC-Fire, and CT-Fire, are adopted to recognize forest fires and address their related challenges. These models are trained using the SWIFT dataset and tested using real fire images. BoucaNet performed well in recognizing wildland fires and overcoming challenging limitations, including the complexity of the background, the variation in smoke and wildfire features, and the detection of small wildland fire areas. This shows the potential of sim-to-real deep learning in wildland fires.

BraNet: a mobil application for breast image classification based on deep learning algorithms.

Mobile health apps are widely used for breast cancer detection using artificial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named "BraNet" for 2D breast imaging segmentation and classification using deep learning algorithms. During the phase off-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classification models. During phase online, the BraNet app was developed using the react native framework, offering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classification. This application operates on a client-server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader's agreement was assessed using the kappa coefficient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classification compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts' accuracy, with DM classification being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classification than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifications, nodules, mass, asymmetry, and dense breasts) and can affect the API accuracy model.

Deep Learning Synthesis of White-Blood From Dark-Blood Late Gadolinium Enhancement Cardiac Magnetic Resonance.

Dark-blood late gadolinium enhancement (DB-LGE) cardiac magnetic resonance has been proposed as an alternative to standard white-blood LGE (WB-LGE) imaging protocols to enhance scar-to-blood contrast without compromising scar-to-myocardium contrast. In practice, both DB and WB contrasts may have clinical utility, but acquiring both has the drawback of additional acquisition time. The aim of this study was to develop and evaluate a deep learning method to generate synthetic WB-LGE images from DB-LGE, allowing the assessment of both contrasts without additional scan time. DB-LGE and WB-LGE data from 215 patients were used to train 2 types of unpaired image-to-image translation deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation, with 5 different loss function hyperparameter settings each. Initially, the best hyperparameter setting was determined for each model type based on the Fréchet inception distance and the visual assessment of expert readers. Then, the CycleGAN and contrastive unpaired translation models with the optimal hyperparameters were directly compared. Finally, with the best model chosen, the quantification of scar based on the synthetic WB-LGE images was compared with the truly acquired WB-LGE. The CycleGAN architecture for unpaired image-to-image translation was found to provide the most realistic synthetic WB-LGE images from DB-LGE images. The results showed that it was difficult for visual readers to distinguish if an image was true or synthetic (55% correctly classified). In addition, scar burden quantification with the synthetic data was highly correlated with the analysis of the truly acquired images. Bland-Altman analysis found a mean bias in percentage scar burden between the quantification of the real WB and synthetic white-blood images of 0.44% with limits of agreement from -10.85% to 11.74%. The mean image quality of the real WB images (3.53/5) was scored higher than the synthetic white-blood images (3.03), P = 0.009. This study proposed a CycleGAN model to generate synthetic WB-LGE from DB-LGE images to allow assessment of both image contrasts without additional scan time. This work represents a clinically focused assessment of synthetic medical images generated by artificial intelligence, a topic with significant potential for a multitude of applications. However, further evaluation is warranted before clinical adoption.