Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

Research related to the diagnosis of prostate cancer based on machine learning medical images: A review

BACKGROUND

Prostate cancer is currently the second most prevalent cancer among men. Accurate diagnosis of prostate cancer can provide effective treatment for patients and greatly reduce mortality. The current medical imaging tools for screening prostate cancer are mainly MRI, CT and ultrasound. In the past 20 years, these medical imaging methods have made great progress with machine learning, especially the rise of deep learning has led to a wider application of artificial intelligence in the use of image-assisted diagnosis of prostate cancer.

METHOD

This review collected medical image processing methods, prostate and prostate cancer on MR images, CT images, and ultrasound images through search engines such as web of science, PubMed, and Google Scholar, including image pre-processing methods, segmentation of prostate gland on medical images, registration between prostate gland on different modal images, detection of prostate cancer lesions on the prostate.

CONCLUSION

Through these collated papers, it is found that the current research on the diagnosis and staging of prostate cancer using machine learning and deep learning is in its infancy, and most of the existing studies are on the diagnosis of prostate cancer and classification of lesions, and the accuracy is low, with the best results having an accuracy of less than 0.95. There are fewer studies on staging. The research is mainly focused on MR images and much less on CT images, ultrasound images.

DISCUSSION

Machine learning and deep learning combined with medical imaging have a broad application prospect for the diagnosis and staging of prostate cancer, but the research in this area still has more room for development.

Enhancing cancer differentiation with synthetic MRI examinations via generative models: a systematic review

Contemporary deep learning-based decision systems are well-known for requiring high-volume datasets in order to produce generalized, reliable, and high-performing models. However, the collection of such datasets is challenging, requiring time-consuming processes involving also expert clinicians with limited time. In addition, data collection often raises ethical and legal issues and depends on costly and invasive procedures. Deep generative models such as generative adversarial networks and variational autoencoders can capture the underlying distribution of the examined data, allowing them to create new and unique instances of samples. This study aims to shed light on generative data augmentation techniques and corresponding best practices. Through in-depth investigation, we underline the limitations and potential methodology pitfalls from critical standpoint and aim to promote open science research by identifying publicly available open-source repositories and datasets.

A new unsupervised pseudo-siamese network with two filling strategies for image denoising and quality enhancement

Digital image noise may be introduced during acquisition, transmission, or processing and affects readability and image processing effectiveness. The accuracy of established image processing techniques, such as segmentation, recognition, and edge detection, is adversely impacted by noise. There exists an extensive body of work which focuses on circumventing such issues through digital image enhancement and noise reduction, but this work is limited by a number of constraints including the application of non-adaptive parameters, potential loss of edge detail information, and (with supervised approaches) a requirement for clean, labeled, training data. This paper, developed on the principle of Noise2Void, presents a new unsupervised learning approach incorporating a pseudo-siamese network. Our method enables image denoising without the need for clean images or paired noise images, instead requiring only noise images. Two independent branches of the network utilize different filling strategies, namely zero filling and adjacent pixel filling. Then, the network employs a loss function to improve the similarity of the results in the two branches. We also modify the Efficient Channel Attention module to extract more diverse features and improve performance on the basis of global average pooling. Experimental results show that compared with traditional methods, the pseudo-siamese network has a greater improvement on the ADNI dataset in terms of quantitative and qualitative evaluation. Our method therefore has practical utility in cases where clean images are difficult to obtain.

Multilevel Strip Pooling-Based Convolutional Neural Network for the Classification of Carotid Plaque Echogenicity

Carotid plaque echogenicity in ultrasound images has been found to be closely correlated with the risk of stroke in atherosclerotic patients. The automatic and accurate classification of carotid plaque echogenicity is of great significance for clinically estimating the stability of carotid plaques and predicting cardiovascular events. Existing convolutional neural networks (CNNs) can provide an automatic carotid plaque echogenicity classification; however, they require a fixed-size input image, while the carotid plaques are of varying sizes. Although cropping and scaling the input carotid plaque images is promising, it will cause content loss or distortion and hence reduce the classification accuracy. In this study, we redesign the spatial pyramid pooling (SPP) and propose multilevel strip pooling (MSP) for the automatic and accurate classification of carotid plaque echogenicity in the longitudinal section. The proposed MSP module can accept arbitrarily sized carotid plaques as input and capture a long-range informative context to improve the accuracy of classification. In our experiments, we implement an MSP-based CNN by using the visual geometry group (VGG) network as the backbone. A total of 1463 carotid plaques (335 echo-rich plaques, 405 intermediate plaques, and 723 echolucent plaques) were collected from Zhongnan Hospital of Wuhan University. The 5-fold cross-validation results show that the proposed MSP-based VGGNet achieves a sensitivity of 92.1%, specificity of 95.6%, accuracy of 92.1%, and F1-score of 92.1%. These results demonstrate that our approach provides a way to enhance the applicability of CNN by enabling the acceptance of arbitrary input sizes and improving the classification accuracy of carotid plaque echogenicity, which has a great potential for an efficient and objective risk assessment of carotid plaques in the clinic.

Feasibility of Three-Dimensional Balanced Steady-State Free Precession Cine Magnetic Resonance Imaging Combined with an Image Denoising Technique to Evaluate Cardiac Function in Children with Repaired Tetralogy of Fallot

Objective

To investigate the feasibility of cine three-dimensional (3D) balanced steady-state free precession (b-SSFP) imaging combined with a non-local means (NLM) algorithm for image denoising in evaluating cardiac function in children with repaired tetralogy of Fallot (rTOF).

Materials and Methods

Thirty-five patients with rTOF (mean age, 12 years; range, 7–18 years) were enrolled to undergo cardiac cine image acquisition, including two-dimensional (2D) b-SSFP, 3D b-SSFP, and 3D b-SSFP combined with NLM. End-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), and ejection fraction (EF) of the two ventricles were measured and indexed by body surface index. Acquisition time and image quality were recorded and compared among the three imaging sequences.

Results

3D b-SSFP with denoising vs. 2D b-SSFP had high correlation coefficients for EDV, ESV, SV, and EF of the left (0.959–0.991; p < 0.001) as well as right (0.755–0.965; p < 0.001) ventricular metrics. The image acquisition time ± standard deviation (SD) was 25.1 ± 2.4 seconds for 3D b-SSFP compared with 277.6 ± 0.7 seconds for 2D b-SSFP, indicating a significantly shorter time with the 3D than the 2D sequence (p < 0.001). Image quality score was better with 3D b-SSFP combined with denoising than with 3D b-SSFP (mean ± SD, 3.8 ± 0.6 vs. 3.5 ± 0.6; p = 0.005). Signal-to-noise ratios for blood and myocardium as well as contrast between blood and myocardium were higher for 3D b-SSFP combined with denoising than for 3D b-SSFP (p < 0.05 for all but septal myocardium).

Conclusion

The 3D b-SSFP sequence can significantly reduce acquisition time compared to the 2D b-SSFP sequence for cine imaging in the evaluation of ventricular function in children with rTOF, and its quality can be further improved by combining it with an NLM denoising method.

Quantitative and Comparative Analysis of Effectivity and Robustness for Enhanced and Optimized Non-Local Mean Filter Combining Pixel and Patch Information on MR Images of Musculoskeletal System

In the area of musculoskeletal MR images analysis, the image denoising plays an important role in enhancing the spatial image area for further processing. Recent studies have shown that non-local means (NLM) methods appear to be more effective and robust when compared with conventional local statistical filters, including median or average filters, when Rician noise is presented. A significant limitation of NLM is the fact that thy have the tendency to suppress tiny objects, which may represent clinically important information. For this reason, we provide an extensive quantitative and objective analysis of a novel NLM algorithm, taking advantage of pixel and patch similarity information with the optimization procedure for optimal filter parameters selection to demonstrate a higher robustness and effectivity, when comparing with NLM and conventional local means methods, including average and median filters. We provide extensive testing on variable noise generators with dynamical noise intensity to objectively demonstrate the robustness of the method in a noisy environment, which simulates relevant, variable and real conditions. This work also objectively evaluates the potential and benefits of the application of NLM filters in contrast to conventional local-mean filters. The final part of the analysis is focused on the segmentation performance when an NLM filter is applied. This analysis demonstrates a better performance of tissue identification with the application of smoothing procedure under worsening image conditions.

A Survey on State-of-the-art Denoising Techniques for Brain Magnetic Resonance Images

The accuracy of the magnetic resonance (MR) image diagnosis depends on the quality of the image, which degrades mainly due to noise and artifacts. The noise is introduced because of erroneous imaging environment or distortion in the transmission system. Therefore, denoising methods play an important role in enhancing the image quality. However, a tradeoff between denoising and preserving the structural details is required. Most of the existing surveys are conducted on a specific MR image modality or on limited denoising schemes. In this context, a comprehensive review on different MR image denoising techniques is inevitable. This survey suggests a new direction in categorizing the MR image denoising techniques. The categorization of the different image models used in medical image processing serves as the basis of our classification. This study includes recent improvements on deep learning-based denoising methods alongwith important traditional MR image denoising methods. The major challenges and their scope of improvement are also discussed. Further, many more evaluation indices are considered for a fair comparison. An elaborate discussion on selecting appropriate method and evaluation metric as per the kind of data is presented. This study may encourage researchers for further work in this domain.

Image Denoising Using Non-Local Means (NLM) Approach in Magnetic Resonance (MR) Imaging: A Systematic Review

The non-local means (NLM) noise reduction algorithm is well known as an excellent technique for removing noise from a magnetic resonance (MR) image to improve the diagnostic accuracy. In this study, we undertook a systematic review to determine the effectiveness of the NLM noise reduction algorithm in MR imaging. A systematic literature search was conducted of three databases of publications dating from January 2000 to March 2020; of the 82 publications reviewed, 25 were included in this study. The subjects were categorized into four major frameworks and analyzed for each research result. Research in NLM noise reduction for MR images has been increasing worldwide; however, it was found to have slightly decreased since 2016. It was found that the NLM technique was most frequently used on brain images taken using the general MR imaging technique; these were most frequently performed during simultaneous real and simulated experimental studies. In particular, comparison parameters were frequently used to evaluate the effectiveness of the algorithm on MR images. The ultimate goal is to provide an accurate method for the diagnosis of disease, and our conclusion is that the NLM noise reduction algorithm is a promising method of achieving this goal.

Synthesis of Prostate MR Images for Classification Using Capsule Network-Based GAN Model

Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data augmentation methods cannot ensure the quality and the diversity of generated training samples. In this paper, we have proposed a novel GAN model for synthesis of MR images by utilizing its powerful ability in modeling the complex data distributions. The proposed model is designed based on the architecture of deep convolutional GAN. To learn the more equivariant representation of images that is robust to the changes in the pose and spatial relationship of objects in the images, the capsule network is applied to replace CNN used in the discriminator of regular GAN. Meanwhile, the least squares loss has been adopted for both the generator and discriminator in the proposed GAN to address the vanishing gradient problem of sigmoid cross entropy loss function in regular GAN. Extensive experiments are conducted on the simulated and real MR images. The results demonstrate that the proposed capsule network-based GAN model can generate more realistic and higher quality MR images than the compared GANs. The quantitative comparisons show that among all evaluated models, the proposed GAN generally achieves the smallest Kullback-Leibler divergence values for image generation task and provides the best classification performance when it is introduced into the deep learning method for image classification task.

FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising

Magnetic Resonance Imaging (MRI) is an indispensable tool in the diagnosis of brain diseases due to painlessness and safety. Nevertheless, Rician noise is inevitably injected during the image acquisition process, which leads to poor observation and interferes with the treatment. Owing to the complexity of Rician noise, using the elimination method of Gaussian to remove it does not perform well. Therefore, the feature fusion and attention network (FFA-DMRI) is proposed to separate noise from observed MRI. Inspired by the attention-guided CNN network (ADNet) and Convolutional block attention module (CBAM), a spatial attention mechanism has been specially designed to obtain the area of interest in MRI. Furthermore, the feature fusion block concatenates local with global information, which makes full use of the multilevel structure and boosts the expressive ability of network. The comprehensive experiments on Alzheimer's disease neuroimaging initiative dataset (ADNI) have demonstrated high effectiveness of FFA-DMRI with maintaining the crucial brain details. Moreover, in terms of visual inspections, the denoising results are also consistent with human perception.