NG-GAN: A Robust Noise-Generation Generative Adversarial Network for Generating Old-Image Noise.

Numerous old images and videos were captured and stored under unfavorable conditions. Hence, old images and videos have uncertain and different noise patterns compared with those of modern ones. Denoising old images is an effective technique for reconstructing a clean image containing crucial information. However, obtaining noisy-clean image pairs for denoising old images is difficult and challenging for supervised learning. Preparing such a pair is expensive and burdensome, as existing denoising approaches require a considerable number of noisy-clean image pairs. To address this issue, we propose a robust noise-generation generative adversarial network (NG-GAN) that utilizes unpaired datasets to replicate the noise distribution of degraded old images inspired by the CycleGAN model. In our proposed method, the perception-based image quality evaluator metric is used to control noise generation effectively. An unpaired dataset is generated by selecting clean images with features that match the old images to train the proposed model. Experimental results demonstrate that the dataset generated by our proposed NG-GAN can better train state-of-the-art denoising models by effectively denoising old videos. The denoising models exhibit significantly improved peak signal-to-noise ratios and structural similarity index measures of 0.37 dB and 0.06 on average, respectively, on the dataset generated by our proposed NG-GAN.

Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images.

We propose an encoder-decoder architecture using wide and deep convolutional layers combined with different aggregation modules for the segmentation of medical images. Initially, we obtain a rich representation of features that span from low to high levels and from small to large scales by stacking multiple k × k kernels, where each k × k kernel operation is split into k × 1 and 1 × k convolutions. In addition, we introduce two feature-aggregation modules-multiscale feature aggregation (MFA) and hierarchical feature aggregation (HFA)-to better fuse information across end-to-end network layers. The MFA module progressively aggregates features and enriches feature representation, whereas the HFA module merges the features iteratively and hierarchically to learn richer combinations of the feature hierarchy. Furthermore, because residual connections are advantageous for assembling very deep networks, we employ an MFA-based long residual connections to avoid vanishing gradients along the aggregation paths. In addition, a guided block with multilevel convolution provides effective attention to the features that were copied from the encoder to the decoder to recover spatial information. Thus, the proposed method using feature-aggregation modules combined with a guided skip connection improves the segmentation accuracy, achieving a high similarity index for ground-truth segmentation maps. Experimental results indicate that the proposed model achieves a superior segmentation performance to that obtained by conventional methods for skin-lesion segmentation, with an average accuracy score of 0.97 on the ISIC-2018, PH2, and UFBA-UESC datasets.

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans.

In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeeze-expand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers' extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation.

Multi-Scale Squeeze U-SegNet with Multi Global Attention for Brain MRI Segmentation.

In this paper, we propose a multi-scale feature extraction with novel attention-based convolutional learning using the U-SegNet architecture to achieve segmentation of brain tissue from a magnetic resonance image (MRI). Although convolutional neural networks (CNNs) show enormous growth in medical image segmentation, there are some drawbacks with the conventional CNN models. In particular, the conventional use of encoder-decoder approaches leads to the extraction of similar low-level features multiple times, causing redundant use of information. Moreover, due to inefficient modeling of long-range dependencies, each semantic class is likely to be associated with non-accurate discriminative feature representations, resulting in low accuracy of segmentation. The proposed global attention module refines the feature extraction and improves the representational power of the convolutional neural network. Moreover, the attention-based multi-scale fusion strategy can integrate local features with their corresponding global dependencies. The integration of fire modules in both the encoder and decoder paths can significantly reduce the computational complexity owing to fewer model parameters. The proposed method was evaluated on publicly accessible datasets for brain tissue segmentation. The experimental results show that our proposed model achieves segmentation accuracies of 94.81% for cerebrospinal fluid (CSF), 95.54% for gray matter (GM), and 96.33% for white matter (WM) with a noticeably reduced number of learnable parameters. Our study shows better segmentation performance, improving the prediction accuracy by 2.5% in terms of dice similarity index while achieving a 4.5 times reduction in the number of learnable parameters compared to previously developed U-SegNet based segmentation approaches. This demonstrates that the proposed approach can achieve reliable and precise automatic segmentation of brain MRI images.

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer's Disease: A Survey.

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer's disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

Multimodal medical image fusion in NSST domain with structural and spectral features enhancement.

For the past 25 years, medical imaging has been extensively used for clinical diagnosis. The main difficulties in medicine are accurate disease recognition and improved therapy. Using a single imaging modality to diagnose disease is challenging for clinical personnel. In this paper, a novel structural and spectral feature enhancement method in NSST Domain for multimodal medical image fusion (MMIF) is proposed. Initially, the proposed method uses the Intensity, Hue, Saturation (IHS) method to generate two pairs of images. The input images are then decomposed using the Non-Subsampled Shearlet Transform (NSST) method to obtain low frequency and high frequency sub-bands. Next, a proposed Structural Information (SI) fusion strategy is employed to Low Frequency Sub-bands (LFS's). It will enhance the structural (texture, background) information. Then, Principal Component Analysis (PCA) is employed as a fusion rule to High Frequency Sub-bands (HFS's) to obtain the pixel level information. Finally, the fused final image is obtained by employing inverse NSST and IHS. The proposed algorithm was validated using different modalities containing 120 image pairs. The qualitative and quantitative results demonstrated that the algorithm proposed in this research work outperformed numerous state-of-the-art MMIF approaches.

A novel CT image de-noising and fusion based deep learning network to screen for disease (COVID-19).

A COVID-19, caused by SARS-CoV-2, has been declared a global pandemic by WHO. It first appeared in China at the end of 2019 and quickly spread throughout the world. During the third layer, it became more critical. COVID-19 spread is extremely difficult to control, and a huge number of suspected cases must be screened for a cure as soon as possible. COVID-19 laboratory testing takes time and can result in significant false negatives. To combat COVID-19, reliable, accurate and fast methods are urgently needed. The commonly used Reverse Transcription Polymerase Chain Reaction has a low sensitivity of approximately 60% to 70%, and sometimes even produces negative results. Computer Tomography (CT) has been observed to be a subtle approach to detecting COVID-19, and it may be the best screening method. The scanned image's quality, which is impacted by motion-induced Poisson or Impulse noise, is vital. In order to improve the quality of the acquired image for post segmentation, a novel Impulse and Poisson noise reduction method employing boundary division max/min intensities elimination along with an adaptive window size mechanism is proposed. In the second phase, a number of CNN techniques are explored for detecting COVID-19 from CT images and an Assessment Fusion Based model is proposed to predict the result. The AFM combines the results for cutting-edge CNN architectures and generates a final prediction based on choices. The empirical results demonstrate that our proposed method performs extensively and is extremely useful in actual diagnostic situations.

Correction: Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture.

[This corrects the article DOI: 10.1371/journal.pone.0236493.].

A novel M-SegNet with global attention CNN architecture for automatic segmentation of brain MRI.

In this paper, we propose a novel M-SegNet architecture with global attention for the segmentation of brain magnetic resonance imaging (MRI). The proposed architecture consists of a multiscale deep network at the encoder side, deep supervision at the decoder side, a global attention mechanism, different sizes of convolutional kernels, and combined-connections with skip connections and pooling indices. The multiscale side input layers were used to support deep layers for extracting the discriminative information and the upsampling layer at the decoder side provided deep supervision, which reduced the gradient problem. The global attention mechanism is utilized to capture rich contextual information in the decoder stage by integrating local features with their respective global dependencies. In addition, multiscale convolutional kernels of different sizes were used to extract abundant semantic features from brain MRI scans in the encoder and decoder modules. Moreover, combined-connections were used to pass features from the encoder to the decoder path to recover the spatial information lost during downsampling and makes the model converge faster. Furthermore, we adopted uniform non-overlapping input patches to focus on fine details for the segmentation of brain MRI. We verified the proposed architecture on publicly accessible datasets for the task of segmentation of brain MRI. The experimental results show that the proposed model outperforms conventional methods by achieving an average Dice similarity coefficient score of 0.96.

Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture.

Accurate segmentation of brain magnetic resonance imaging (MRI) is an essential step in quantifying the changes in brain structure. Deep learning in recent years has been extensively used for brain image segmentation with highly promising performance. In particular, the U-net architecture has been widely used for segmentation in various biomedical related fields. In this paper, we propose a patch-wise U-net architecture for the automatic segmentation of brain structures in structural MRI. In the proposed brain segmentation method, the non-overlapping patch-wise U-net is used to overcome the drawbacks of conventional U-net with more retention of local information. In our proposed method, the slices from an MRI scan are divided into non-overlapping patches that are fed into the U-net model along with their corresponding patches of ground truth so as to train the network. The experimental results show that the proposed patch-wise U-net model achieves a Dice similarity coefficient (DSC) score of 0.93 in average and outperforms the conventional U-net and the SegNet-based methods by 3% and 10%, respectively, for on Open Access Series of Imaging Studies (OASIS) and Internet Brain Segmentation Repository (IBSR) dataset.

Fast Computation of Integer DCT-V, DCT-VIII, and DST-VII for Video Coding.

Joint exploration model (JEM) reference codecs of ISO/IEC and ITU-T utilize multiple types of integer transforms based on DCT and DST of various transform sizes for intra- and inter-predictive coding, which has brought a significant improvement in coding efficiency. JEM adopts three types of integer DCTs (DCT-II, DCT-V, and DCT-VIII), and two types of integer DSTs (DST-I and DST-VII). The fast computations of Integer DCT-II and DST-I are well known, but few studies have been performed for the other types such as DCT-V, DCT-VIII, and DST-VII for all transform sizes. In this paper, we present fast computation methods of N-point DCT-V and DCT-VIII. For this, we first decompose the DCT-VIII into a preprocessing matrix, the DST-VII and a post-processing matrix to quickly compute it by using the linear relation between DCT-VIII and DST-VII. Then, we approximate integer kernels of N = 4, 8, 16, and 32 for DCT-V, DCT-VIII, and DST-VII with norm scaling and bit-shift to be compatible with quantization in each stage of multiplications between decomposed matrices for video coding. In various experiments, the proposed fast computation methods have shown to effectively reduce the total complexity of the matrix operations with little loss in BDBR performance. In particular, our methods reduce the number of addition and multiplication operations by 38% and 80.3%, respectively, in average, compared to the original JEM.

A CU-Level Rate and Distortion Estimation Scheme for RDO of Hardware-Friendly HEVC Encoders Using Low-Complexity Integer DCTs.

In this paper, a low complexity coding unit (CU)-level rate and distortion estimation scheme is proposed for High Efficiency Video Coding (HEVC) hardware-friendly implementation where a Walsh-Hadamard transform (WHT)-based low-complexity integer discrete cosine transform (DCT) is employed for distortion estimation. Since HEVC adopts quadtree structures of coding blocks with hierarchical coding depths, it becomes more difficult to estimate accurate rate and distortion values without actually performing transform, quantization, inverse transform, de-quantization, and entropy coding. Furthermore, DCT for rate-distortion optimization (RDO) is computationally high, because it requires a number of multiplication and addition operations for various transform block sizes of 4-, 8-, 16-, and 32-orders and requires recursive computations to decide the optimal depths of CU or transform unit. Therefore, full RDO-based encoding is highly complex, especially for low-power implementation of HEVC encoders. In this paper, a rate and distortion estimation scheme is proposed in CU levels based on a low-complexity integer DCT that can be computed in terms of WHT whose coefficients are produced in prediction stages. For rate and distortion estimation in CU levels, two orthogonal matrices of 4×4 and 8×8 , which are applied to WHT that are newly designed in a butterfly structure only with addition and shift operations. By applying the integer DCT based on the WHT and newly designed transforms in each CU block, the texture rate can precisely be estimated after quantization using the number of non-zero quantized coefficients and the distortion can also be precisely estimated in transform domain without de-quantization and inverse transform required. In addition, a non-texture rate estimation is proposed by using a pseudoentropy code to obtain accurate total rate estimates. The proposed rate and the distortion estimation scheme can effectively be used for HW-friendly implementation of HEVC encoders with 9.8% loss over HEVC full RDO, which much less than 20.3% and 30.2% loss of a conventional approach and Hadamard-only scheme, respectively.