Multi-scale Structural Similarity Research Articles

Super-resolution application of generative adversarial network on brain time-of-flight MR angiography: image quality and diagnostic utility evaluation.

To develop a generative adversarial network (GAN) model to improve image resolution of brain time-of-flight MR angiography (TOF-MRA) and to evaluate the image quality and diagnostic utility of the reconstructed images. We included 180 patients who underwent 1-min low-resolution (LR) and 4-min high-resolution (routine) brain TOF-MRA scans. We used 50 patients' datasets for training, 12 for quantitative image quality evaluation, and the rest for diagnostic validation. We modified a pix2pix GAN to suit TOF-MRA datasets and fine-tuned GAN-related parameters, including loss functions. Maximum intensity projection images were generated and compared using multi-scale structural similarity (MS-SSIM) and information theoretic-based statistic similarity measure (ISSM) index. Two radiologists scored vessels' visibilities using a 5-point Likert scale. Finally, we evaluated sensitivities and specificities of GAN-MRA in depicting aneurysms, stenoses, and occlusions. The optimal model was achieved with a lambda of 1e5 and L1 + MS-SSIM loss. Image quality metrics for GAN-MRA were higher than those for LR-MRA (MS-SSIM, 0.87 vs. 0.73; ISSM, 0.60 vs. 0.35; p.adjusted < 0.001). Vessels' visibility of GAN-MRA was superior to LR-MRA (rater A, 4.18 vs. 2.53; rater B, 4.61 vs. 2.65; p.adjusted < 0.001). In depicting vascular abnormalities, GAN-MRA showed comparable sensitivities and specificities, with greater sensitivity for aneurysm detection by one rater (93% vs. 84%, p < 0.05). An optimized GAN could significantly improve the image quality and vessel visibility of low-resolution brain TOF-MRA with equivalent sensitivity and specificity in detecting aneurysms, stenoses, and occlusions. • GAN could significantly improve the image quality and vessel visualization of low-resolution brain MR angiography (MRA). • With optimally adjusted training parameters, the GAN model did not degrade diagnostic performance by generating substantial false positives or false negatives. • GAN could be a promising approach for obtaining higher resolution TOF-MRA from images scanned in a fraction of time.

Low-Dose CT Image Denoising Based on Improved DD-Net and Local Filtered Mechanism.

Low-dose CT (LDCT) images can reduce the radiation damage to the patients; however, the unavoidable information loss will influence the clinical diagnosis under low-dose conditions, such as noise, streak artifacts, and smooth details. LDCT image denoising is a significant topic in medical image processing to overcome the above deficits. This work proposes an improved DD-Net (DenseNet and deconvolution-based network) joint local filtered mechanism, the DD-Net is enhanced by introducing improved residual dense block to strengthen the feature representation ability, and the local filtered mechanism and gradient loss are also employed to effectively restore the subtle structures. First, the LDCT image is inputted into the network to obtain the denoised image. The original loss between the denoised image and normal-dose CT (NDCT) image is calculated, and the difference image between the NDCT image and the denoised image is obtained. Second, a mask image is generated by taking a threshold operation to the difference image, and the filtered LDCT and NDCT images are obtained by conducting an elementwise multiplication operation with LDCT and NDCT images using the mask image. Third, the filtered image is inputted into the network to obtain the filtered denoised image, and the correction loss is calculated. At last, the sum of original loss and correction loss of the improved DD-Net is used to optimize the network. Considering that it is insufficient to generate the edge information using the combination of mean square error (MSE) and multiscale structural similarity (MS-SSIM), we introduce the gradient loss that can calculate the loss of the high-frequency portion. The experimental results show that the proposed method can achieve better performance than conventional schemes and most neural networks. Our source code is made available at https://github.com/LHE-IT/Low-dose-CT-Image-Denoising/tree/main/Local Filtered Mechanism.

Low-Cost Probabilistic 3D Denoising with Applications for Ultra-Low-Radiation Computed Tomography.

We propose a pipeline for synthetic generation of personalized Computer Tomography (CT) images, with a radiation exposure evaluation and a lifetime attributable risk (LAR) assessment. We perform a patient-specific performance evaluation for a broad range of denoising algorithms (including the most popular deep learning denoising approaches, wavelets-based methods, methods based on Mumford–Shah denoising, etc.), focusing both on accessing the capability to reduce the patient-specific CT-induced LAR and on computational cost scalability. We introduce a parallel Probabilistic Mumford–Shah denoising model (PMS) and show that it markedly-outperforms the compared common denoising methods in denoising quality and cost scaling. In particular, we show that it allows an approximately 22-fold robust patient-specific LAR reduction for infants and a 10-fold LAR reduction for adults. Using a normal laptop, the proposed algorithm for PMS allows cheap and robust (with a multiscale structural similarity index >90%) denoising of very large 2D videos and 3D images (with over voxels) that are subject to ultra-strong noise (Gaussian and non-Gaussian) for signal-to-noise ratios far below 1.0. The code is provided for open access.

HyperNet: A deep network for hyperspectral, multispectral, and panchromatic image fusion

Traditional approaches mainly fuse a hyperspectral image (HSI) with a high-resolution multispectral image (MSI) to improve the spatial resolution of the HSI. However, such improvement in the spatial resolution of HSIs is still limited because the spatial resolution of MSIs remains low. To further improve the spatial resolution of HSIs, we propose HyperNet, a deep network for the fusion of HSI, MSI, and panchromatic image (PAN), which effectively injects the spatial details of an MSI and a PAN into an HSI while preserving the spectral information of the HSI. Thus, we design HyperNet on the basis of a uniform fusion strategy to solve the problem of complex fusion of three types of sources (i.e., HSI, MSI, and PAN). In particular, the spatial details of the MSI and the PAN are extracted by multiple specially designed multiscale-attention-enhance blocks in which multi-scale convolution is used to adaptively extract features from different reception fields, and two attention mechanisms are adopted to enhance the representation capability of features along the spectral and spatial dimensions, respectively. Through the capability of feature reuse and interaction in a specially designed dense-detail-insertion block, the previously extracted features are subsequently injected into the HSI according to the unidirectional feature propagation among the layers of dense connection. Finally, we construct an efficient loss function by integrating the multi-scale structural similarity index with the L1 norm, which drives HyperNet to generate high-quality results with a good balance between spatial and spectral qualities. Extensive experiments on simulated and real data sets qualitatively and quantitatively demonstrate the superiority of HyperNet over other state-of-the-art methods.

Iris Image Compression Using Deep Convolutional Neural Networks.

Compression is a way of encoding digital data so that it takes up less storage and requires less network bandwidth to be transmitted, which is currently an imperative need for iris recognition systems due to the large amounts of data involved, while deep neural networks trained as image auto-encoders have recently emerged a promising direction for advancing the state-of-the-art in image compression, yet the generalizability of these schemes to preserve the unique biometric traits has been questioned when utilized in the corresponding recognition systems. For the first time, we thoroughly investigate the compression effectiveness of DSSLIC, a deep-learning-based image compression model specifically well suited for iris data compression, along with an additional deep-learning based lossy image compression technique. In particular, we relate Full-Reference image quality as measured in terms of Multi-scale Structural Similarity Index (MS-SSIM) and Local Feature Based Visual Security (LFBVS), as well as No-Reference images quality as measured in terms of the Blind Reference-less Image Spatial Quality Evaluator (BRISQUE), to the recognition scores as obtained by a set of concrete recognition systems. We further compare the DSSLIC model performance against several state-of-the-art (non-learning-based) lossy image compression techniques including: the ISO standard JPEG2000, JPEG, H.265 derivate BPG, HEVC, VCC, and AV1 to figure out the most suited compression algorithm which can be used for this purpose. The experimental results show superior compression and promising recognition performance of the model over all other techniques on different iris databases.

DeBoNet: A deep bone suppression model ensemble to improve disease detection in chest radiographs.

Automatic detection of some pulmonary abnormalities using chest X-rays may be impacted adversely due to obscuring by bony structures like the ribs and the clavicles. Automated bone suppression methods would increase soft tissue visibility and enhance automated disease detection. We evaluate this hypothesis using a custom ensemble of convolutional neural network models, which we call DeBoNet, that suppresses bones in frontal CXRs. First, we train and evaluate variants of U-Nets, Feature Pyramid Networks, and other proposed custom models using a private collection of CXR images and their bone-suppressed counterparts. The DeBoNet, constructed using the top-3 performing models, outperformed the individual models in terms of peak signal-to-noise ratio (PSNR) (36.7977±1.6207), multi-scale structural similarity index measure (MS-SSIM) (0.9848±0.0073), and other metrics. Next, the best-performing bone-suppression model is applied to CXR images that are pooled from several sources, showing no abnormality and other findings consistent with COVID-19. The impact of bone suppression is demonstrated by evaluating the gain in performance in detecting pulmonary abnormality consistent with COVID-19 disease. We observe that the model trained on bone-suppressed CXRs (MCC: 0.9645, 95% confidence interval (0.9510, 0.9780)) significantly outperformed (p < 0.05) the model trained on non-bone-suppressed images (MCC: 0.7961, 95% confidence interval (0.7667, 0.8255)) in detecting findings consistent with COVID-19 indicating benefits derived from automatic bone suppression on disease classification. The code is available at https://github.com/sivaramakrishnan-rajaraman/Bone-Suppresion-Ensemble.

Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement.

Deep learning-based image compression methods have made significant achievements recently, of which the two key components are the entropy model for latent representations and the encoder-decoder network. Both the inaccurate estimation of the entropy estimation model and the existence of information redundancy in latent representations lead to a reduction in the compression efficiency. To address these issues, the study suggests an image compression method based on a hybrid domain attention mechanism and postprocessing improvement. This study embeds hybrid domain attention modules as nonlinear transformers in both the main encoder-decoder network and the hyperprior network, aiming at constructing more compact latent features and hyperpriors and then model the latent features as parametric Gaussian-scale mixture models to obtain more precise entropy estimation. In addition, we propose a solution to the errors introduced by quantization in image compression by adding an inverse quantization module. On the decoding side, we also provide a postprocessing enhancement module to further increase image compression performance. The experimental results show that the peak signal-to-noise rate (PSNR) and multiscale structural similarity (MS-SSIM) of the proposed method are higher than those of traditional compression methods and advanced neural network-based methods.

DENOISING SWEPT SOURCE OPTICAL COHERENCE TOMOGRAPHY VOLUMETRIC SCANS USING A DEEP LEARNING MODEL.

To evaluate the use of a deep learning noise reduction model on swept source optical coherence tomography volumetric scans. Three groups of images including single-line highly averaged foveal scans (averaged images), foveal B-scans from volumetric scans using no averaging (unaveraged images), and deep learning denoised versions of the latter (denoised images) were obtained. We evaluated the potential increase in the signal-to-noise ratio by evaluating the contrast-to-noise ratio of the resultant images and measured the multiscale structural similarity index to determine whether the unaveraged and denoised images held true in structure to the averaged images. We evaluated the practical effects of denoising on a popular metric of choroidal vascularity known as the choroidal vascularity index. Ten eyes of 10 subjects with a mean age of 31 years (range 24-64 years) were evaluated. The deep choroidal contrast-to-noise ratio mean values of the averaged and denoised image groups were similar (7.06 vs. 6.81, P = 0.75), and both groups had better maximum contrast-to-noise ratio mean values (27.65 and 46.34) than the unaveraged group (14.75; P = 0.001 and P < 0.001, respectively). The mean multiscale structural similarity index of the average-denoised images was significantly higher than the one from the averaged--unaveraged images (0.85 vs. 0.61, P < 0.001). Choroidal vascularity index values from averaged and denoised images were similar (71.81 vs. 71.16, P = 0.554). Using three different metrics, we demonstrated that the deep learning denoising model can produce high-quality images that emulate, and may exceed, the quality of highly averaged scans.

Detection and Diagnosis of Bearing Faults Under Fixed and Time-Varying Speed Conditions Using Persistence Spectrum and Multi-Scale Structural Similarity Index

With the widespread use of variable speed drives, a robust scheme that can detect and diagnose bearing faults under fixed and variable speed conditions becomes essential for reliable operation. Unfortunately, most of the reported methods in the literature are dedicated to working under fixed speed and will face challenges under variable speed conditions. Besides, most of them require detailed bearing information that may be unavailable in the real world. Therefore, in this paper, a new scheme is proposed for bearing faults detection and diagnosis under fixed and time-varying speed conditions. The proposed scheme is based on the analysis of vibration signals using the persistence spectrum that can provide images rich with health-related features largely independent from rotating speed. Then, the produced image is compared with priorly stored images of the persistence spectrum of a healthy case. This comparison is performed using the multi-scale structural similarity index, which is a robust basis for images comparison without the need for training or expert knowledge. The obtained index is compared against an adaptive threshold for fault detection. Upon detecting a fault, the persistence spectrum image is compared with that of stored different fault types for fault diagnosis. The proposed scheme is extensively validated using three experimental datasets under different speed conditions. The results show that it can detect bearing faults in an earlier stage without the need for bearing specifications or shaft speed. Moreover, it can successfully diagnose bearing faults severity with accuracy reaching 100% with the minimum required data.

NEW METHOD FOR REDUCING ARTIFACTUAL FLOW DEFICITS CAUSED BY COMPENSATION TECHNIQUES IN THE CHORIOCAPILLARIS WITH OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY.

To mitigate artifactual choriocapillaris flow deficits in optical coherence tomography angiography, which are a side effect of inverse structural optical coherence tomography compensation. In a modified algorithm, we set pixels in the original structural optical coherence tomography that were greater than one SD above the mean intensity (hyperreflective regions) to the mean pixel intensity of the image to remove hyporeflective regions in the inverse slab. We compared this algorithm to the original using flow deficit density and multiscale structural similarity index obtained from three distinct thresholding methods (local Phansalkar, global MinError (I), and global Li). We included 16 eyes of 16 healthy subjects (31.1 ± 6.9 years, 10 females). Using the modified optical coherence tomography correction, flow deficit density was lower compared with the original algorithm using Phansalkar (P < 0.001) but higher using Li thresholding (P = 0.049). Multiscale structural similarity index was increased after applying the modified algorithm with all three thresholding methods (P < 0.001), indicating a closer relationship to the original optical coherence tomography angiography scan. We demonstrate a new method that significantly reduced the introduction of artifactual flow deficits in the choriocapillaris during postprocessing. Given the improved multiscale structural similarity index, we believe our algorithm more accurately represents the choriocapillaris.

Label2label: training a neural network to selectively restore cellular structures in fluorescence microscopy.

ABSTRACTImmunofluorescence microscopy is routinely used to visualise the spatial distribution of proteins that dictates their cellular function. However, unspecific antibody binding often results in high cytosolic background signals, decreasing the image contrast of a target structure. Recently, convolutional neural networks (CNNs) were successfully employed for image restoration in immunofluorescence microscopy, but current methods cannot correct for those background signals. We report a new method that trains a CNN to reduce unspecific signals in immunofluorescence images; we name this method label2label (L2L). In L2L, a CNN is trained with image pairs of two non-identical labels that target the same cellular structure. We show that after L2L training a network predicts images with significantly increased contrast of a target structure, which is further improved after implementing a multiscale structural similarity loss function. Here, our results suggest that sample differences in the training data decrease hallucination effects that are observed with other methods. We further assess the performance of a cycle generative adversarial network, and show that a CNN can be trained to separate structures in superposed immunofluorescence images of two targets.

An encoder–decoder based thermo-visible image translation for disguised and undisguised faces

Thermal cameras can capture images even in low light conditions. However, humans cannot recognize human faces in thermal images. Translation of thermal images to visible domain is one solution to the problem of face recognition in thermal images. Most of the research works have proposed Generative Adversarial Networks (GANs) based solutions for thermal to visible image translation. However, GAN is a heavy network that consumes huge amount of resource for thermal to visible image translation. In this paper, we propose an encoder–decoder architecture for thermal to visible image translation of human faces. Since our proposed architecture is not based on GANs, it is lightweight. The proposed method works well for both disguised and non-disguised thermal facial images. Standard comparison parameters such as Peak Signal-to-noise Ratio (PSNR), Structural Similarity Index (SSIM), and Multiscale Structural Similarity Index (MS-SSIM) are used to evaluate the quality of the generated visible images with respect to the ground truth. It has been found that our proposed architecture outperforms the current state-of-the-art image translator architectures namely pix2pix, Cycle-GAN, modified thermal to visible GAN and Dual GAN by a considerable margin for both disguised as well as non-disguised dataset.

Phase dual-resolution networks for a computer-generated hologram.

The computer-generated hologram (CGH) is a method for calculating arbitrary optical field interference patterns. Iterative algorithms for CGHs require a built-in trade-off between computation speed and accuracy of the hologram, which restricts the performance of applications. Although the non-iterative algorithm for CGHs is quicker, the hologram accuracy does not meet expectations. We propose a phase dual-resolution network (PDRNet) based on deep learning for generating phase-only holograms with fixed computational complexity. There are no ground-truth holograms employed in the training; instead, the differentiability of the angular spectrum method is used to realize unsupervised training of the convolutional neural network. In the PDRNet algorithm, we optimized the dual-resolution network as the prototype of the hologram generator to enhance the mapping capability. The combination of multi-scale structural similarity (MS-SSIM) and mean square error (MSE) is used as the loss function to generate a high-fidelity hologram. The simulation indicates that the proposed PDRNet can generate high-fidelity 1080P resolution holograms in 57 ms. Experiments in the holographic display show fewer speckles in the reconstructed image.

Learning to Remove Clutter in Real-World GPR Images Using Hybrid Data

The clutter in the ground-penetrating radar (GPR) radargram disguises or distorts subsurface target responses, which severely affects the accuracy of target detection and identification. Existing clutter removal methods either leave residual clutter or deform target responses when facing complex and irregular clutter in the real-world radargram. To tackle the challenge of clutter removal in real scenarios, a clutter-removal neural network (CR-Net) trained on a large-scale hybrid dataset is presented in this study. The CR-Net integrates residual dense blocks into the U-Net architecture to enhance its capability in clutter suppression and target reflection restoration. The combination of the mean absolute error (MAE) loss and the multi-scale structural similarity (MS-SSIM) loss is used to effectively drive the optimization of the network. To train the proposed CR-Net to remove complex and diverse clutter in real-world radargrams, the first large-scale hybrid dataset named CLT-GPR dataset containing clutter collected by different GPR systems in multiple scenarios is built. The CLT-GPR dataset significantly improves the generalizability of the network to remove clutter in real-world GPR radargrams. Extensive experimental results demonstrate that the CR-Net achieves superior performance over existing methods in removing clutter and restoring target responses in diverse real-world scenarios. Moreover, the CR-Net with its end-to-end design does not require manual parameter tuning, making it highly suitable for automatically producing clutter-free radargrams in GPR applications. The CLT-GPR dataset and the code implemented in the paper can be found at https://haihan-sun.github.io/GPR.html.

Application of region of interest extraction method based on deep learning in UAV high performance image compression

UAV has been widely used in detecting targets, but the image transmission of UAV still faces the problems of distortion and frame loss. Most image compression methods based on deep learning are lossy compression, and lossy compression reduces image quality in exchange for higher compression ratio. In order to improve the quality of the region of interest (ROI) in the reconstructed image with a certain bit rate, an importance map extraction module is embedded in the encoder, and the importance map is generated by extracting the output features of the last layer of the encoder. Finally, the mask is generated to guide the efficient allocation of bit rate in the process of drop coding. At the same time, a decoder enhancement module is embedded in the decoder output to predict the high frequency components in the reconstructed image and improve the quality of the reconstructed image by enhancing the details in the reconstructed image. The experimental results show that the proposed method is superior to the comparison method when multi-scale structural similarity (MS-SSIM) is used as the evaluation index, and the proposed method achieves better visual perception quality.

Medical image fusion quality evaluation method combined multi-angle and multi-scale information

At present, the existing evaluation indicators of image fusion algorithms do not in conformity with the standards of human vision system and are not suitable for medical image application scenarios. Therefore, this paper proposes a medical image fusion quality evaluation method combining multi-angle and multi-scale information. We use Gabor Filter to decompose the image and obtain multi-angle texture information, and design a new index, called Multiscale Structural Similarity with Image Resolution (SSIM-IR), to comprehensively evaluate the fused image from edge, structure and sharpness. The experimental results show that this method is more suitable for medical image application scenarios, consistent with subjective evaluation, and can be used for measuring the advantages and disadvantages of medical image fusion algorithm.

Deep Learning for Simultaneous Seismic Image Super-Resolution and Denoising

Seismic interpretation is often limited by low resolution and strong noise data. To deal with this issue, we propose to leverage deep convolutional neural network (CNN) to achieve seismic image super-resolution and denoising simultaneously. To train the CNN, we simulate a lot of synthetic seismic images with different resolutions and noise levels to serve as training data sets. To improve the perception quality, we use a loss function that combines the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula> loss and multiscale structural similarity loss. Extensive experimental results on both synthetic and field seismic images demonstrate that the proposed workflow can significantly improve the perception of quality of original data. Compared to conventional methods, the network obtains better performance in enhancing detailed structural and stratigraphic features, such as thin layers and small-scale faults. From the seismic images super-sampled by our CNN method, a fault detection method can compute more accurate fault maps than from the original seismic images.

Deep Arbitrary HDRI: Inverse Tone Mapping With Controllable Exposure Changes

Deep convolutional neural networks (CNNs) have recently made significant advances in the inverse tone mapping technique, which generates a high dynamic range (HDR) image from a single low dynamic range (LDR) image that has lost information in over- and under-exposed regions. The end-to-end inverse tone mapping approach specifies the dynamic range in advance, thereby limiting dynamic range expansion. In contrast, the method of generating multiple exposure LDR images from a single LDR image and subsequently merging them into an HDR image enables flexible dynamic range expansion. However, existing methods for generating multiple exposure LDR images require an additional network for each exposure value to be changed or a process of recursively inferring images that have different exposure values. Therefore, the number of parameters increases significantly due to the use of additional networks, and an error accumulation problem arises due to recursive inference. To solve this problem, we propose a novel network architecture that can control arbitrary exposure values without adding networks or applying recursive inference. The training method of the auxiliary classifier-generative adversarial network structure is employed to generate the image conditioned on the specified exposure. The proposed network uses a newly designed spatially-adaptive normalization to address the limitation of existing methods that cannot sufficiently restore image detail due to the spatially equivariant nature of the convolution. Spatially-adaptive normalization facilitates restoration of the high frequency component by applying different normalization parameters to each element in the feature map according to the characteristics of the input image. Experimental results show that the proposed method outperforms state-of-the-art methods, yielding a 5.48dB higher average peak signal-to-noise ratio, a 0.05 higher average structure similarity index, a 0.28 higher average multi-scale structure similarity index, and a 7.36 higher average HDR-VDP-2 for various datasets.

Unsupervised Low-Light Image Enhancement by Extracting Structural Similarity and Color Consistency

A novel structure-aware unsupervised network is proposed to deal with low-light image enhancement issues based on the inspiration of Retinex theory and self-supervised perceptual loss. It comprises four main components, namely the original structural similarity module, the novel color consistency module, the attentional enhancement module, and the naturalness discriminator module. Specially for the structural similarity module, an embedded structural feature extractor (SFE) model capable of generating structure correspondence is well designed and pre-trained by employing the contrastive learning technique, and a multi-scale structural similarity distance is introduced to optimize the SFE network. Besides, a self-supervised color consistency module is established by using a degraded estimation algorithm for recovering the missing colors. The whole enhancement framework operates in unsupervised manners and finally obtains the best naturalness image quality evaluator metric. Experimental results demonstrate that the proposed unsupervised network is able to recover natural structure and color images more effectively, which would also help to enlarge the practical application without collecting paired datasets in advance.

Hybrid Single Image Super-Resolution Algorithm for Medical Images

High-quality medical microscopic images used for diseases detection are expensive and difficult to store. Therefore, low-resolution images are favorable due to their low storage space and ease of sharing, where the images can be enlarged when needed using Super-Resolution (SR) techniques. However, it is important to maintain the shape and size of the medical images while enlarging them. One of the problems facing SR is that the performance of medical image diagnosis is very poor due to the deterioration of the reconstructed image resolution. Consequently, this paper suggests a multi-SR and classification framework based on Generative Adversarial Network (GAN) to generate high-resolution images with higher quality and finer details to reduce blurring. The proposed framework comprises five GAN models: Enhanced SR Generative Adversarial Networks (ESRGAN), Enhanced deep SR GAN (EDSRGAN), Sub-Pixel-GAN, SRGAN, and Efficient Wider Activation-B GAN (WDSR-b-GAN). To train the proposed models, we have employed images from the famous BreakHis dataset and enlarged them by 4× and 16× upscale factors with the ground truth of the size of 256 × 256 × 3. Moreover, several evaluation metrics like Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Structural Similarity Index (SSIM), Multiscale Structural Similarity Index (MS-SSIM), and histogram are applied to make comprehensive and objective comparisons to determine the best methods in terms of efficiency, training time, and storage space. The obtained results reveal the superiority of the proposed models over traditional and benchmark models in terms of color and texture restoration and detection by achieving an accuracy of 99.7433%.