Image Spatial Quality Evaluator Research Articles

Vision-Based Online Molten Pool Image Acquisition and Assessment for Quality Monitoring in Gas–Metal Arc Welding

In gas–metal arc welding (GMAW), the welding quality is influenced by various factors, including the welding conditions and external environment. Achieving a high welding quality requires careful observation and control. Welding monitoring is crucial for validating a planned welding process and assessing its quality. This study introduces a vision system for the online acquisition of clear molten pool images. It uses a small camera equipped with a complementary metal-oxide-semiconductor sensor during GMAW, as well as a method for constructing this system. The proposed vision system does not require triggering using devices such as field-programmable gate arrays, facilitating lower costs and online quality monitoring under various welding conditions during mild-steel GMAW. Accurate measurement of radiation from the weld is essential for clear observation of the molten pool during welding, emphasizing the importance of selecting an optical system with appropriate lenses and filters. In addition, appropriate digital camera parameters must be set for monitoring. High-quality images were successfully captured using the proposed method, and the image quality was evaluated using the blind/referenceless image spatial quality evaluator algorithm.

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.

Gan-based data augmentation to improve breast ultrasound and mammography mass classification

Data imbalance is a common problem in breast cancer diagnosis, to address this challenge, the research explores the use of Generative Adversarial Networks (GANs) to generate synthetic medical data. Various GAN methods, including Wasserstein GAN with Gradient Penalty (WGAN-GP), Cycle GAN, Conditional GAN, and Spectral Normalization GAN (SNGAN), were tested for data augmentation in breast regions of interest (ROIs) using mammography and ultrasound databases. The study employed real, synthetic, and hybrid ROIs (128x128 pixels) to train a Resnet network for classifying as benign (B) or malignant (M) classes. The quality and diversity of the synthetic data were assessed using several metrics: Fréchet Inception Distance (FID), Kernel Inception Distance (KID), Structural Similarity Index (SSIM), Multi-Scale SSIM (MS-SSIM), Blind Reference Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), and Perception-based Image Quality Evaluator (PIQE).Results revealed that the SNGAN model (FID = 52.89) was most effective for augmenting mammography data, while CGAN (FID = 116.03) excelled with ultrasound data. Cycle GAN and WGAN-GP, though demonstrating lower KID values, did not perform better than SNGAN and CGAN. The lower average MS-SSIM values suggested that SNGAN and CGAN produced a high diversity of synthetic images. However, lower SSIM, BRISQUE, NIQE, and PIQE values indicated poor quality in both real and synthetic images. Classification results showed high accuracy without data augmentation in both US (93.1 %B/94.9 %M) and mammography (80.9 %B/76.9 %M). The research concludes that preprocessing and characterizing ROIs by abnormality type is crucial to generate diverse synthetic data and improve accuracy in the classification process using combined GANs and CNN models.

DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus.

Depth of focus (DOF) is defined as the axial range in which the specimen stage moves without losing focus while the imaging apparatus remains stable. It may not be possible to capture an image that includes the entire specimen in focus due to the narrow DOF in microscopic systems. Extended depth of focus (EDOF) is used to overcome this limitation in microscopic systems. Although the researchers have developed so many EDOF microscope approaches, this research field still has some crucial shortcomings such as high computational costs, complexity and execution time, requiring additional equipment, low precise characterization of curves, and edges in images, varying performance depending on the specimen and microscope, using only gray levels of input images to acquire the pixel's focus values. In order to minimize these shortcomings and comprehensively analyze the performance of EDOF approaches, a novel multi-focus image data set is generated, and a deep learning-based EDOF microscope approach is proposed in this study. When compared with the state-of-art EDOF approaches, our study provides various crucial contributions such as the first EDOF approach based on unsupervised deep learning, providing more accurate and specimen-free EDOF, generating a novel multi-focus image data, not requiring any pre- or post-processing technique and acquiring the pixel's focus degrees using deep features. In order to evaluate the effectiveness of the suggested approach, 20 different EDOF approaches are applied to a multi-focus image data set containing 9 image collections (4 synthetic and 5 microscope image collections) in total. Performance analysis metrics with and without requiring a reference image are preferred to identify which EDOF microscope approach can extract more essential details from the multi-focus images for the synthetic and microscope image collections, which are Root Mean Square Error (RMSE), Peak Signal Noise Ratio (PSNR), Universal Quality Index (UQI), Correlation Coefficient (CC), Perception-based Image Quality Evaluator (PIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Extension of Universal Quality Index for N Images (UQIN), and Naturalness Image Quality Evaluator (NIQE). Objective and subjective analysis of this study demonstrates that unsupervised deep learning model is more efficient to transmit crucial details from multi-focus images. Moreover, the suggested EDOF microscope approach with highest PSNR, UQI, CC, UQIN and lowest RMSE, PIQE, BRISQUE, NIQE produces higher performance than the state-of-art approaches.

Parametric image-based concrete defect assessment method

Structural health monitoring aims to ensure the integrity of infrastructure. Assessing structural integrity through image classification techniques based on human perception is often challenging. Incorporating a morphological image-based crack detection algorithm can mitigate these limitations. This study proposes a parametric approach for concrete crack analysis using digital image processing techniques. The objective is to detect damage to the concrete surface of infrastructures, potentially exacerbating structural deterioration. The research justifies the utilization of digital parametric image processing techniques, including a weighted median filter, grayscale, Otsu filter, and other methods. These techniques were applied to evaluate different concrete images for crack detection. The findings were validated through Image Quality Assessment (IQA), determining the condition of the studied images and statistical properties using metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Natural Image Quality Evaluator (NIQE), and Perceptual Image Quality Evaluator (PIQE). Additionally, uncontrollable factors such as variations in lighting effects under different conditions, testing setups, and different textures of the concrete were considered in this study. The comprehensive experimental results demonstrated that the Otsu filter outperforms other filtering techniques. Overall, the study achieved remarkable accuracy, approximately 95%, in detecting cracks on building infrastructure. The proposed method holds potential for integration with advanced techniques in practical applications for the maintenance and safety of infrastructure. This research not only contributes to technological advancements in concrete defect assessment but also carries significant implications for the future of automated and reliable structural health monitoring.

An improved blind/referenceless image spatial quality evaluator algorithm for image quality assessment

An improved blind/referenceless image spatial quality evaluator algorithm for image quality assessment

Hierarchical deconvolution dehazing method based on transmission map segmentation.

Images captured in fog are often affected by scattering. Due to the absorption and scattering of light by aerosols and water droplets, the image quality will be seriously degraded. The specific manifests are brightness decrease, contrast decrease, image blur, and noise increase. In the single-image dehazing method, the image degradation model is essential. In this paper, an effective image degradation model is proposed, in which the hierarchical deconvolution strategy based on transmission map segmentation can effectively improve the accuracy of image restoration. Specifically, the transmission map is obtained by using the dark channel prior (DCP) method, then the transmission histogram is fitted. The next step is to divide the image region according to the fitting results. Furthermore, to more accurately recover images of complex objects with a large depth of field, different levels of inverse convolution are adopted for different regions. Finally, the sub-images of different regions are fused to get the dehazing image. We tested the proposed method using synthetic fog images and natural fog images respectively. The proposed method is compared with eight advanced image dehazing methods on quantitative rating indexes such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM), image entropy, natural image quality evaluator (NIQE), and blind/referenceless image spatial quality evaluator (BRISQUE). Both subjective and objective evaluations show that the proposed method achieves competitive results.

Optimization Method to Predict Optimal Noise Reduction Parameters for the Non-Local Means Algorithm Based on the Scintillator Thickness in Radiography.

The resulting image obtained from an X-ray imaging system depends significantly on the characteristics of the detector. In particular, when an X-ray image is acquired by thinning the detector, a relatively large amount of noise inevitably occurs. In addition, when a thick detector is used to reduce noise in X-ray images, blurring increases and the ability to distinguish target areas deteriorates. In this study, we aimed to derive the optimal X-ray image quality by deriving the optimal noise reduction parameters based on the non-local means (NLM) algorithm. The detectors used were of two thicknesses (96 and 140 μm), and images were acquired based on the IEC 62220-1-1:2015 RQA-5 protocol. The optimal parameters were derived by calculating the edge preservation index and signal-to-noise ratio according to the sigma value of the NLM algorithm. As a result, a sigma value of the optimized NLM algorithm (0.01) was derived, and this algorithm was applied to a relatively thin X-ray detector system to obtain appropriate noise level and spatial resolution data. The no-reference-based blind/referenceless image spatial quality evaluator value, which analyzes the overall image quality, was best when using the proposed method. In conclusion, we propose an optimized NLM algorithm based on a new method that can overcome the noise amplification problem in thin X-ray detector systems and is expected to be applied in various photon imaging fields in the future.

Enhancing the image quality of blue light cystoscopy through green-hue correction and fogginess removal

Blue light cystoscopy (BLC) is a guideline-recommended endoscopic tool to detect bladder cancer with high sensitivity. Having clear, high-quality images during cystoscopy is crucial to the sensitive, efficient detection of bladder tumors; yet, important diagnostic information is often missed or poorly visualized in images containing illumination artifacts or impacted by impurities in the bladder. In this study, we introduce computational methods to remove two common artifacts in images from BLC videos: green hue and fogginess. We also evaluate the effect of artifact removal on the perceptual quality of the BLC images through a survey study and computation of Blind/Referenceless Image Spatial Quality Evaluator scores on the original and enhanced images. We show that corrections and enhancements made to cystoscopy images resulted in a better viewing experience for clinicians during BLC imaging and reliably restored lost tissue features that were important for diagnostics. Incorporating these enhancements during clinical and OR procedures may lead to more comprehensive tumor detection, fewer missed tumors during TURBT procedures, more complete tumor resection and shorter procedure time. When used in off-line review of cystoscopy videos, it may also better guide surgical planning and allow more accurate assessment and diagnosis.

Improvement of 2D cine image quality using 3D priors and cycle generative adversarial network for low field MRI-guided radiation therapy.

Cine magnetic resonance (MR) images have been used for real-time MR guided radiation therapy (MRgRT). However, the onboard MR systems with low-field strength face the problem of limited image quality. To improve the quality of cine MR images in MRgRT using prior image information provided by the patient planning and positioning MR images. This study employed MR images from 18 pancreatic cancer patients who received MR-guided stereotactic body radiation therapy. Planning 3D MR images were acquired during the patient simulation, and positioning 3D MR images and 2D sagittal cine MR images were acquired before and during the beam delivery, respectively. A deep learning-based framework consisting of two cycle generative adversarial networks (CycleGAN), Denoising CycleGAN and Enhancement CycleGAN, was developed to establish the mapping between the 3D and 2D MR images. The Denoising CycleGAN was trained to first denoise the cine images using the time domain cine image series, and the Enhancement CycleGAN was trained to enhance the spatial resolution and contrast by taking advantage of the prior image information from the planning and positioning images. The denoising performance was assessed by signal-to-noise ratio (SNR), structural similarity index measure, peak SNR, blind/reference-less image spatial quality evaluator (BRISQUE), natural image quality evaluator, and perception-based image quality evaluator scores. The quality enhancement performance was assessed by the BRISQUE and physician visual scores. In addition, the target contouring was evaluated on the original and processed images. Significant differences were found for all evaluation metrics after Denoising CycleGAN processing. The BRISQUE and visual scores were also significantly improved after sequential Denoising and Enhancement CycleGAN processing. In target contouring evaluation, Dice similarity coefficient, centroid distance, Hausdorff distance, and average surface distance values were significantly improved on the enhanced images. The whole processing time was within 20ms for a typical input image size of 512 × 512. Taking advantage of the prior high-quality positioning and planning MR images, the deep learning-based framework enhanced the cine MR image quality significantly, leading to improved accuracy in automatic target contouring. With the merits of both high computational efficiency and considerable image quality enhancement, the proposed method may hold important clinical implication for real-time MRgRT.

Practical study for comparing edge detection filters in digital image processing

Edge detection is a fundamental and important tool in image processing and computer vision. The research topic discusses edge extraction of a digital image using various digital image processing techniques. Digital image edge identification using variety of digital image processing methods. The most popular technique for identifying discontinuities in intensity levels is edge detection. The actual image contains noise that could affect the digital image's quality. Some edge detection filters were used such as Canny, Sobel, and Prewitt. Laplace of Gaussian (LOG) edge recognition, Robert boundary detection, zero edge recognition and analysis. In light of the results of the comparison of edge filters the best edge filter had been obtained. Also, a hybrid method that merges between Canny filter and morphology operations were produced for edge detection. The research aims to reach an appropriate image purification by using different types of filters and to reduce distortions at the edges of the image and to determine which type of filter is the best. As well as, a comparison operation is applied between the traditional method and the hybrid method. Following the results explained by the filters used and displaying the resulting images. The results evaluated from hybrid filter show that this method is optimal than the traditional filters based on the Blind/Reference less Image Spatial Quality Evaluator (BRISQUE) with a value equals 43.43. A smaller score indicates better perceptual quality. Also, the edged images quality consequences from the traditional filters were measured by this metric. The results produced from the traditional filters prove that the best filter for edge image detection is Canny filter based on Blind/Reference less Image Spatial Quality Evaluator (BRISQUE) that reaches 46.01. In addition, the correlation coefficient was estimated to find which of the resulting images are better and closer to the original image. While for correlation coefficient the better filter was Prewitt filter with 0.3133 value. This study program was applied under the MATLAB R2020b system.

Quantitative Analysis of Blurry Color Image Fusion Techniques using Color Transform

This work focuses on fused color images resulting from motion blur (left and right) with a blur block size of 11 pixels. The color conversion process was performed from RGB color space (Red, Green, Blue) to HSV (Hue, Saturation, Value), L*a*b*, and Ycbcr (Luminance, Chrominance) color space. The traditional (addition, multiplication) and proposed fusion techniques (absolute real standard deviation) were used for this purpose. The data was examined by quality criteria with reference (Mutual Information, Correlation Coefficient, Structural Content, Normalized Cross Correlation) and without reference (Blind Reference less Image Spatial Quality Evaluator, Naturalness Image Quality Evaluator, and Perception-based Image Quality Evaluator). In results and depending on the criteria, the best fusion method is the proposed real standard deviation.

Road damage detection with bounding box and generative adversarial networks based augmentation methods

AbstractIn this paper, based on the data augmentation techniques of bounding box augmentation and the road damage generative adversarial network based augmentation, a robust road damage detection method has been presented. To this end, first, Iran road damage dataset has been collected by means of a dashboard‐installed mobile phone. After processing these images by the blind referenceless image spatial quality evaluator technique, the substandard and inferior data have been automatically eliminated. In the second step, based on the YOLOv5 with several different baseline models, an algorithm has been developed for detecting the road surface damages. In the third step, by using the traditional as well as the bounding box augmentation and road damage generative adversarial network based augmentation techniques, the precision and the robustness of road damage detector under different environmental and field conditions have been improved. Finally, through the ensemble of the best models, the final detector accuracy has been enhanced. The findings of this article indicate that by using the proposed approach, the values of mAP and F1‐score are improved by 13.79% and 7.58%, respectively. The dataset and parts of the code are available at: https://github.com/IranRoadDamageDataset/IRRDD.

The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease.

To evaluate the effect of the deep learning model reconstruction (DLM) method in terms of image quality and diagnostic agreement in low-dose computed tomography (LDCT) for interstitial lung disease (ILD), 193 patients who underwent LDCT for suspected ILD were retrospectively reviewed. Datasets were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction Veo (ASiR-V), and DLM. For image quality analysis, the signal, noise, signal-to-noise ratio (SNR), blind/referenceless image spatial quality evaluator (BRISQUE), and visual scoring were evaluated. Also, CT patterns of usual interstitial pneumonia (UIP) were classified according to the 2022 idiopathic pulmonary fibrosis (IPF) diagnostic criteria. The differences between CT images subjected to FBP, ASiR-V 30%, and DLM were evaluated. The image noise and BRISQUE scores of DLM images was lower and SNR was higher than that of the ASiR-V and FBP images (ASiR-V vs. DLM, p < 0.001 and FBP vs. DLR-M, p < 0.001, respectively). The agreement of the diagnostic categorization of IPF between the three reconstruction methods was almost perfect (κ = 0.992, CI 0.990-0.994). Image quality was improved with DLM compared to ASiR-V and FBP.

Bilateral tone mapping scheme for color correction and contrast adjustment in nearly invisible medical images

AbstractMedical images are commonly used to diagnose and screen various diseases. However, medical images taken by operators with different skill levels have a considerable variation in visual quality. Poor illumination of images increases uncertainty in clinical treatment and lead to the risk of misdiagnosis. This paper proposes a novel bilateral tone‐mapped gamma correction to enhance the visual quality of medical images without affecting the natural color quality. First, the proposed tone‐mapped gamma correction is employed to enhance the intensity values of poorly illuminated medical images. Then, bilateral enhancement curve adjustment is performed to effectively improve the global luminance content of the input image with features and richer information. The image quality assessment measures like entropy, blind/reference less image spatial quality evaluator, natural image quality evaluator, perception‐based image quality evaluator, contrast enhancement based image quality parameter, and color contrast fog density evaluates the superior performance of the proposed technique. The experimental results significantly enhance the intensity difference between dark and bright areas and can aid clinical experts and intelligent health fields.

An efficient multi-level pre-processing algorithm for the enhancement of dermoscopy images in melanoma detection.

In this paper, a multi-level algorithm for pre-processing of dermoscopy images is proposed, which helps in improving the quality of the raw images, making it suitable for skin lesion detection. This multi-level pre-processing method has a positive impact on automated skin lesion segmentation using Regularized Extreme Learning Machine. Raw images are subjected to de-noising, illumination correction, contrast enhancement, sharpening, reflection removal, and virtual shaving before the skin lesion segmentation. The Non-Local Means (NLM) filter with lowest Blind Reference less Image Spatial Quality Evaluator (BRISQUE) score exhibits better de-noising of dermoscopy images. To suppress uneven illumination, gamma correction is subjected to the denoised image. The Robust Image Contrast Enhancement (RICE) algorithm is used for contrast enhancement, and produces enhanced images with better structural preservation and negligible loss of information. Unsharp masking for sharpening exhibits low BRISQUE scores for better sharpening of fine details in an image. Output images produced by the phase congruency-based method in virtual shaving show high similarity with ground truth images as the hair is removed completely from the input images. Obtained scores at each stage of pre-processing framework show that the performance is superior compared to all the existing methods, both qualitatively and quantitatively, in terms of uniform contrast, preservation of information content, removal of undesired information, and elimination of artifacts in melanoma images. The output of the proposed system is assessed qualitatively and quantitatively with and without pre-processing of dermoscopy images. From the overall evaluation results, it is found that the segmentation of skin lesion is more efficient using Regularized Extreme Learning Machine if the multi-level pre-processing steps are used in proper sequence.

De‐noising method of aquatic product image with foreign matters based on improved wavelet transform and bilateral filter

AbstractAiming at the strong spot noise caused by the reflection of meat slices in fish image with foreign matters that collected by ordinary camera or Single Lens Reflex (SLR) camera, we proposed an improved wavelet transform and bilateral filtering algorithm to reduce the noise of image. In this paper, our algorithm absorbed the advantages of wavelet threshold de‐noising algorithm and bilateral filtering algorithm, the wavelet threshold de‐noising algorithm being used for high frequency components and bilateral filtering being used for low frequency components, which not only achieved the effect of eliminating noise and weakening light spot, but also protected the details of the image. In the experiment, in order to verify the effectiveness of the proposed algorithm, we used the traditional bilateral filtering, Gaussian filtering and median filtering algorithms to process 500 salmon fish images which had residual fishbone, respectively. Since the original image itself was a noisy image, it was impossible to evaluate the noise reduction effect by using an algorithm that requires a noiseless image as a reference image, so we used five methods to evaluate the quality of the image processed by each algorithm, which were Blind/Referenceless Image Spatial QUality Evaluator (BRISQE), Cumulative Probability of Blur Detection (CPBD), variance, image entropy, and operation speed. Among them, BRISQE and CPBD could quantitatively reflect the overall quality of the image, the lower the BRISQE score or the higher the CPBD score, the better the quality of the image. Compared with other algorithms, the BRISQE score and CPBD score of the image processed by our algorithm were the best, with the average scores reaching 20.65 and .8421, respectively. Experimental results showed that the improved algorithm in this paper can effectively eliminate this kind of strong spot noise. The processed image has achieved better visual effect in both subjective and objective level.

Radiomics based automated quality assessment for T2W prostate MR images

PurposeThe guidelines for prostate cancer recommend the use of MRI in the prostate cancer pathway. Due to the variability in prostate MR image quality, the reliability of this technique in the detection of prostate cancer is highly variable in clinical practice. This leads to the need for an objective and automated assessment of image quality to ensure an adequate acquisition and hereby to improve the reliability of MRI. The aim of this study is to investigate the feasibility of Blind/referenceless image spatial quality evaluator (Brisque) and radiomics in automated image quality assessment of T2-weighted (T2W) images. MethodAnonymized axial T2W images from 140 patients were scored for quality using a five-point Likert scale (low, suboptimal, acceptable, good, very good quality) in consensus by two readers. Images were dichotomized into clinically acceptable (very good, good and acceptable quality images) and clinically unacceptable (low and suboptimal quality images) in order to train and verify the model. Radiomics and Brisque features were extracted from a central cuboid volume including the prostate. A reduced feature set was used to fit a Linear Discriminant Analysis (LDA) model to predict image quality. Two hundred times repeated 5-fold cross-validation was used to train the model and test performance by assessing the classification accuracy, the discrimination accuracy as receiver operating curve - area under curve (ROC-AUC), and by generating confusion matrices. ResultsThirty-four images were classified as clinically unacceptable and 106 were classified as clinically acceptable. The accuracy of the independent test set (mean ± standard deviation) was 85.4 ± 5.5%. The ROC-AUC was 0.856 (0.851 – 0.861) (mean; 95% confidence interval). ConclusionsRadiomics AI can automatically detect a significant portion of T2W images of suboptimal image quality. This can help improve image quality at the time of acquisition, thus reducing repeat scans and improving diagnostic accuracy.

SynthEye: Investigating the Impact of Synthetic Data on Artificial Intelligence-assisted Gene Diagnosis of Inherited Retinal Disease.

Rare disease diagnosis is challenging in medical image-based artificial intelligence due to a natural class imbalance in datasets, leading to biased prediction models. Inherited retinal diseases (IRDs) are a research domain that particularly faces this issue. This study investigates the applicability of synthetic data in improving artificial intelligence-enabled diagnosis of IRDs using generative adversarial networks (GANs). Diagnostic study of gene-labeled fundus autofluorescence (FAF) IRD images using deep learning. Moorfields Eye Hospital (MEH) dataset of 15692 FAF images obtained from 1800 patients with confirmed genetic diagnosis of 1 of 36 IRD genes. A StyleGAN2 model is trained on the IRD dataset to generate 512× 512 resolution images. Convolutional neural networks are trained for classification using different synthetically augmented datasets, including real IRD images plus 1800 and 3600 synthetic images, and a fully rebalanced dataset. We also perform an experiment with only synthetic data. All models are compared against a baseline convolutional neural network trained only on real data. We evaluated synthetic data quality using a Visual Turing Test conducted with 4 ophthalmologists from MEH. Synthetic and real images were compared using feature space visualization, similarity analysis to detect memorized images, and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score for no-reference-based quality evaluation. Convolutional neural network diagnostic performance was determined on a held-out test set using the area under the receiver operating characteristic curve (AUROC) and Cohen's Kappa (κ). An average true recognition rate of 63% and fake recognition rate of 47% was obtained from the Visual Turing Test. Thus, a considerable proportion of the synthetic images were classified as real by clinical experts. Similarity analysis showed that the synthetic images were not copies of the real images, indicating thatcopied real images, meaning the GAN was able to generalize. However, BRISQUE score analysis indicated that synthetic images were of significantly lower quality overall than real images (P < 0.05). Comparing the rebalanced model (RB) with the baseline (R), no significant change in the average AUROC and κ was found (R-AUROC=0.86[0.85-88], RB-AUROC=0.88[0.86-0.89], R-k=0.51[0.49-0.53], and RB-k=0.52[0.50-0.54]). The synthetic data trained model (S) achieved similar performance as the baseline (S-AUROC=0.86[0.85-87], S-k=0.48[0.46-0.50]). Synthetic generation of realistic IRD FAF images is feasible. Synthetic data augmentation does not deliver improvements in classification performance. However, synthetic data alone deliver a similar performance as real data, and hence may be useful as a proxy to real data. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.

Interval type-2 fuzzy set based block-SBU for image fusion technique

Image fusion is the process of examining one or more obscure images, combining only the critical information in those images to make them a good quality image. Due to the large gap between the high dynamic range of landscape scenes and the low quality of consumer quality cameras, a single-shot image cannot record the information of a single set. A part of image processing called image fusion is used to overcome the above problem. In this method, authors propose a new technology for image fusion with intuitionistic fuzzy sets. During the processing, the given images are converted into fuzzy images and then intuitionistic fuzzy images (IFIs). Thus, a significant change occurs between the given image and IFIs. The resulting IFIs are converted into interval type-2 fuzzy images (IT2FIs) to overcome this problem. The proposed technique is compared to other procedures such as discrete cosine harmonic wavelet transform (DCHWT), multi-resolution single value decay (MSVD), primary component analysis (PCA), standard wavelet transform (SWT), two scale image fusion (TSIF), and wavelet transform (WT). The proposed method gives the best results based on performance analysis such as Entropy, standard deviation (STD), average gradient (AG), mutual information (MIF), and blind referenceless image spatial quality evaluator (BRISQUE). Using the proposed technique, one can obtain the best results for entropy, STD, AG, MIF, and BRISQUE respectively as 7.6241, 49.6745, 69.2100, 5.7276, and 3.3091. Hence it reveals that the proposed method performs better than other methods regarding overall visual quality and performance measurements.