Medical Imaging Networks Research Articles

Deep Neural Networks in Medical Imaging: Advances, Challenges, and Future Directions for Precision Healthcare

Deep Neural Networks in Medical Imaging: Advances, Challenges, and Future Directions for Precision Healthcare

Application of generative adversarial networks in image, face reconstruction and medical imaging: challenges and the current progress

ABSTRACT In deep learning, GANs (Generative Adversarial Networks) are one of the prominent study areas due to their ability to generate synthetic data thereby solving the problem of the unavailability and the limited data sets. GAN is a framework of deep neural networks that can learn from a set of training data and generate new data with similar characteristics as the training data. In this review, the history of GAN, various types of GANs, objective functions, loss functions, and performance analysis done for GANs in various fields are also analysed. The main objective of the paper is to analyse the application of GANs in face restoration, and medical imaging including their evaluation metrics and data sets used. A deep review has been carried out on various types of GANs, their architecture, objective functions, and applications. This review focuses more on the medical applications using various types of GANs including image augmentation, disease detection, medical image enhancement, face restoration, detection, etc. The challenges, current progress, and future applications using various GANs are also discussed. This review clearly shows that the application of GANs has increased considerably and thus it proves a promising future in the field of deep learning.

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

Generative Adversarial Networks (GANs) in Medical Imaging: Advancements, Applications, and Challenges

ADVANCED ULTRAWIDEBAND PATCH ANTENNA FOR WEARABLE AND WBAN APPLICATIONS

Present communication devices are adopting an application-centric approach with the integration of electronic gadgets into wearable accessories in recent years. This paper presents a wearable antenna with a flexible textile substrate. The design comprises a low-profile, textile-based UWB (3.1-10.6 GHz) antenna of 25 × 20 × 1 mm<sup>3</sup> size with a defected ground structure. Design antenna performance characteristics have been simulated in Computer Simulation Technology studio. It offers a gain of 4.204 dBi at 5.11 GHz frequency and 2.993 dBi at 7.39 GHz frequency using a cotton substrate with a 1.6 dielectric constant. A simulated testing of the design antenna on a human body phantom has resulted in a gain of 0.697 dBi with a return loss of -30.863dB and 1.058 VSWR at 5.3125 GHz frequency. A specific absorption rate value of 1.64 W/kg of the designed antenna for 10 g tissue shows that it is safe for the human body. The patch antenna of the paper is promising for wearable, medical imaging, tumor detection, and other wireless body area network (WBAN) biomedical applications.

Transfer Learning Strategies for Fine-Tuning Pretrained Convolutional Neural Networks in Medical Imaging

In the area of medical imaging, transfer learning has become a potent technique that uses pretrained Convolutional Neural Networks (CNNs) to improve the performance of particular tasks. An overview of several transfer learning techniques used for optimising pretrained CNNs in the context of medical image analysis is given in this abstract. The size limitations of medical imaging datasets make it difficult to train deep learning models from scratch. Pre-trained CNNs are a good place to start, such as those that have been trained on huge natural picture datasets like ImageNet. When these pre-trained models are applied to medical imaging applications, fine-tuning is frequently used. One common method is feature extraction, where the bottom layers of the pretrained CNN are frozen and operate as feature extractors. Then, for the specific medical task at hand, these features are loaded into a bespoke classifier. The ability of the pretrained network to recognise subtle picture patterns is advantageous in this method. Another strategy is to optimise the CNN architecture as a whole, which enables the model to adjust to the features of medical images. Small learning rates are frequently used in transfer learning techniques to avoid overfitting during fine-tuning. Additionally, to further enhance model generalisation, domain-specific data augmentation is essential. The use of ensemble approaches, which combine several pretrained CNNs, is also investigated. These models are capable of offering various feature representations and improving classification precision. In order to bridge the domain gap between natural photos and medical images, domain adaption techniques are also used. One approach to align feature distributions is by adversarial training, while another is through domain-specific batch normalisation. The feature extraction, network fine-tuning, ensemble approaches, and domain adaptation are all part of transfer learning methodologies for optimising pretrained CNNs in medical imaging. Researchers have made great progress using these techniques in a number of medical image processing tasks, proving the value of transfer learning in this important area.

Approximation of curve-based sleeve functions in high dimensions

Sleeve functions are generalizations of the well-established ridge functions that play a major role in the theory of partial differential equation, medical imaging, statistics, and neural networks. Where ridge functions are non-linear, univariate functions of the distance to hyperplanes, sleeve functions are based on the squared distance to lower-dimensional manifolds. The present work is a first step to study general sleeve functions by starting with sleeve functions based on finite-length curves. To capture these curve-based sleeve functions, we propose and study a two-step method, where first the outer univariate function—the profile—is recovered, and second, the underlying curve is represented by a polygonal chain. Introducing a concept of well-separation, we ensure that the proposed method always terminates and approximates the true sleeve function with a certain quality. Investigating the local geometry, we study an inexact version of our method and show its success under certain conditions.

Deep Neural Networks in Medical Imaging: Privacy Preservation, Image Generation and Applications

Medical Imaging plays a key role in disease management, starting from baseline risk assessment, diagnosis, staging, therapy planning, therapy delivery, and follow-up [...]

A novel Parametric Flatten-p Mish activation function based deep CNN model for brain tumor classification

The brain tumor is one of the deadliest diseases of all cancers. Influenced by the recent developments of convolutional neural networks (CNNs) in medical imaging, we have formed a CNN based model called BMRI-Net for brain tumor classification. As the activation function is one of the important modules of CNN, we have proposed a novel parametric activation function named Parametric Flatten-p Mish (PFpM) to improve the performance. PFpM can tackle the significant disadvantages of the pre-existing activation functions like neuron death and bias shift effect. The parametric approach of PFpM also offers the model some extra flexibility to learn the complex patterns more accurately from the data. To validate our proposed methodology, we have used two brain tumor datasets namely Figshare and Br35H. We have compared the performance of our model with state-of-the-art deep CNN models like DenseNet201, InceptionV3, MobileNetV2, ResNet50 and VGG19. Further, the comparative performance of PFpM has been presented with various activation functions like ReLU, Leaky ReLU, GELU, Swish and Mish. We have performed record-wise and subject-wise (patient-level) experiments for Figshare dataset whereas only record-wise experiments have been performed in case of Br35H dataset due to unavailability of subject-wise information. Further, the model has been validated using hold-out and 5-fold cross-validation techniques. On Figshare dataset, our model has achieved 99.57% overall accuracy with hold-out validation and 98.45% overall accuracy with 5-fold cross validation in case of record-wise data split. On the other hand, the model has achieved 97.91% overall accuracy with hold-out validation and 97.26% overall accuracy with 5-fold cross validation in case of subject-wise data split. Similarly, for Br35H dataset, our model has attained 99% overall accuracy with hold-out validation and 98.33% overall accuracy with 5-fold cross validation using record-wise data split. Hence, our findings can introduce a secondary procedure in the clinical diagnosis of brain tumors.

Detection and classification of skin diseases with ensembles of deep learning networks in medical imaging

Skin disorders are a serious worldwide public health issue that affects a large number of individuals. In recent years, with the fast advancement of technology and the use of different data mining approaches, treatment of skin predictive classification has really become highly predictive as well as accurate. As a result, the type of machine learning approaches capable of efficiently differentiating skin condition categorization is essential. So far, no one machine learning approach has outperformed the others in terms of skin disease prediction. In this research, we introduce a new method that combines two separate data mining approaches into a single unit, as well as an ensemble approach that combines both data mining techniques into a single group. We explore different data mining strategies to categorize the skin condition using an informative Dermatology publicly accessible dataset ISIC2019 images, and then apply an ensemble deep learning method. Furthermore, the presented ensemble technique, which is based on machine and deep learning, was tested on Dermatology datasets and was able to categorize skin disorders into seven categories.

The effect of dataset confounding on predictions of deep neural networks for medical imaging

The use of Convolutional Neural Networks (CNN) in medical imaging has often outperformed previous solutions and even specialists, becoming a promising technology for Computer-aidedDiagnosis (CAD) systems. However, recent works suggested that CNN may have poor generalisation on new data, for instance, generated in different hospitals. Uncontrolled confounders have been proposed as a common reason. In this paper, we experimentally demonstrate the impact of confounding data in unknown scenarios. We assessed the effect of four confounding configurations: total, strong, light and balanced. We found the confounding effect is especially prominent in total confounder scenarios, while the effect on light and strong confounding scenarios may depend on the dataset robustness. Our findings indicate that the confounding effect is independent of the architecture employed. These findings might explain why models can report good metrics during the development stage but fail to translate to real-world settings. We highlight the need for thorough consideration of these commonly unattended aspects, to develop safer CNN-based CAD systems.

Quantile-Based Iterative Methods for Corrupted Systems of Linear Equations

Often in applications ranging from medical imaging and sensor networks to error correction and data science (and beyond), one needs to solve large-scale linear systems in which a fraction of the measurements have been corrupted. We consider solving such large-scale systems of linear equations $\mathbf{A}\mathbf{x}=\mathbf{b}$ that are inconsistent due to corruptions in the measurement vector $\mathbf{b}$. We develop several variants of iterative methods that converge to the solution of the uncorrupted system of equations, even in the presence of large corruptions. These methods make use of a quantile of the absolute values of the residual vector in determining the iterate update. We present both theoretical and empirical results that demonstrate the promise of these iterative approaches.

Spectral decoupling for training transferable neural networks in medical imaging

SummaryMany neural networks for medical imaging generalize poorly to data unseen during training. Such behavior can be caused by overfitting easy-to-learn features while disregarding other potentially informative features. A recent implicit bias mitigation technique called spectral decoupling provably encourages neural networks to learn more features by regularizing the networks' unnormalized prediction scores with an L2 penalty. We show that spectral decoupling increases the networks′ robustness for data distribution shifts and prevents overfitting on easy-to-learn features in medical images. To validate our findings, we train networks with and without spectral decoupling to detect prostate cancer on tissue slides and COVID-19 in chest radiographs. Networks trained with spectral decoupling achieve up to 9.5 percent point higher performance on external datasets. Spectral decoupling alleviates generalization issues associated with neural networks and can be used to complement or replace computationally expensive explicit bias mitigation methods, such as stain normalization in histological images.

Emerging Aspects of Artificial Intelligence for Smart Life

Nowadays Artificial intelligence makes our life easy and comfortable that is hard to imagine that to survive our life without AI technology. We all know that Artificial Intelligence (AI) is a precious gift to human being. Recently it is used in robotics, education, agriculture, computer vision, cyber security, face recognition, speech recognition, self driving cars, medical image processing, biometrics, bioinformatics, satellite control, disease detection, drugs development, network developments, manufacturing, business, healthcare and medicine. In the digital era AI provides the best results in all most all the domains. This article helps to understand the emerging aspects of AI in various fields.

Narrative review of generative adversarial networks in medical and molecular imaging.

Recent years have witnessed a rapidly expanding use of artificial intelligence and machine learning in medical imaging. Generative adversarial networks (GANs) are techniques to synthesize images based on artificial neural networks and deep learning. In addition to the flexibility and versatility inherent in deep learning on which the GANs are based, the potential problem-solving ability of the GANs has attracted attention and is being vigorously studied in the medical and molecular imaging fields. Here this narrative review provides a comprehensive overview for GANs and discuss their usefulness in medical and molecular imaging on the following topics: (I) data augmentation to increase training data for AI-based computer-aided diagnosis as a solution for the data-hungry nature of such training sets; (II) modality conversion to complement the shortcomings of a single modality that reflects certain physical measurement principles, such as from magnetic resonance (MR) to computed tomography (CT) images or vice versa; (III) de-noising to realize less injection and/or radiation dose for nuclear medicine and CT; (IV) image reconstruction for shortening MR acquisition time while maintaining high image quality; (V) super-resolution to produce a high-resolution image from low-resolution one; (VI) domain adaptation which utilizes knowledge such as supervised labels and annotations from a source domain to the target domain with no or insufficient knowledge; and (VII) image generation with disease severity and radiogenomics. GANs are promising tools for medical and molecular imaging. The progress of model architectures and their applications should continue to be noteworthy.

PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging.

Application of deep neural networks to medical imaging tasks has in some sense become commonplace. Still, a "thorn in the side" of the deep learning movement is the argument that deep networks are prone to overfitting and are thus unable to generalize well when datasets are small (as is common in medical imaging tasks). One way to bolster confidence is to provide mathematical guarantees, or bounds, on network performance after training which explicitly quantify the possibility of overfitting. In this work, we explore recent advances using the PAC-Bayesian framework to provide bounds on generalization error for large (stochastic) networks. While previous efforts focus on classification in larger natural image datasets (e.g., MNIST and CIFAR-10), we apply these techniques to both classification and segmentation in a smaller medical imagining dataset: the ISIC 2018 challenge set. We observe the resultant bounds are competitive compared to a simpler baseline, while also being more explainable and alleviating the need for holdout sets.

Application and Construction of Deep Learning Networks in Medical Imaging.

Deep learning (DL) approaches are part of the machine learning (ML) subfield concerned with the development of computational models to train artificial intelligence systems. DL models are characterized by automatically extracting high-level features from the input data to learn the relationship between matching datasets. Thus, its implementation offers an advantage over common ML methods that often require the practitioner to have some domain knowledge of the input data to select the best latent representation. As a result of this advantage, DL has been successfully applied within the medical imaging field to address problems, such as disease classification and tumor segmentation for which it is difficult or impossible to determine which image features are relevant. Therefore, taking into consideration the positive impact of DL on the medical imaging field, this article reviews the key concepts associated with its evolution and implementation. The sections of this review summarize the milestones related to the development of the DL field, followed by a description of the elements of deep neural network and an overview of its application within the medical imaging field. Subsequently, the key steps necessary to implement a supervised DL application are defined, and associated limitations are discussed.

Cybersecurity Protection for PACS and Medical Imaging: Deployment Considerations and Practical Problems

Cybersecurity is increasingly affecting the healthcare sector. In a recent article, the authors analyzed specific attacks against picture archiving and communications systems (PACS) and medical imaging networks and proposed security measures. This article discusses issues that require consideration when deploying these proposed measures and provides recommendations on how to implement them. Hospitals should deploy virus scanners on systems where permitted, with high priority on devices that are part of the central IT infrastructure of the hospital. They should introduce a systematic management of software updates on operating system, application software and virus scanner level and clarify the provision of security updates for the intended duration of use when purchasing a new device. They should agree with the PACS vendor on a long-term strategy for implementing access rights, and enable encrypted network communication where possible. This requires an agreement on the encryption algorithms to be used, and a public-key infrastructure. For most of these tasks, standards and profiles exist today. There are, however, some gaps: Implementation of cybersecurity measures would be facilitated by integration profiles on certificate and signature management, and access rights in a PACS environment.

A light CNN for detecting COVID-19 from CT scans of the chest.

Computer Tomography (CT) imaging of the chest is a valid diagnosis tool to detect COVID-19 promptly and to control the spread of the disease. In this work we propose a light Convolutional Neural Network (CNN) design, based on the model of the SqueezeNet, for the efficient discrimination of COVID-19 CT images with respect to other community-acquired pneumonia and/or healthy CT images. The architecture allows to an accuracy of 85.03% with an improvement of about 3.2% in the first dataset arrangement and of about 2.1% in the second dataset arrangement. The obtained gain, though of low entity, can be really important in medical diagnosis and, in particular, for Covid-19 scenario. Also the average classification time on a high-end workstation, 1.25s, is very competitive with respect to that of more complex CNN designs, 13.41s, witch require pre-processing. The proposed CNN can be executed on medium-end laptop without GPU acceleration in 7.81s: this is impossible for methods requiring GPU acceleration. The performance of the method can be further improved with efficient pre-processing strategies for witch GPU acceleration is not necessary.

Self-supervised multimodal reconstruction of retinal images over paired datasets

Data scarcity represents an important constraint for the training of deep neural networks in medical imaging. Medical image labeling, especially if pixel-level annotations are required, is an expensive task that needs expert intervention and usually results in a reduced number of annotated samples. In contrast, extensive amounts of unlabeled data are produced in the daily clinical practice, including paired multimodal images from patients that were subjected to multiple imaging tests. This work proposes a novel self-supervised multimodal reconstruction task that takes advantage of this unlabeled multimodal data for learning about the domain without human supervision. Paired multimodal data is a rich source of clinical information that can be naturally exploited by trying to estimate one image modality from others. This multimodal reconstruction requires the recognition of domain-specific patterns that can be used to complement the training of image analysis tasks in the same domain for which annotated data is scarce.In this work, a set of experiments is performed using a multimodal setting of retinography and fluorescein angiography pairs that offer complementary information about the eye fundus. The evaluations performed on different public datasets, which include pathological and healthy data samples, demonstrate that a network trained for self-supervised multimodal reconstruction of angiography from retinography achieves unsupervised recognition of important retinal structures. These results indicate that the proposed self-supervised task provides relevant cues for image analysis tasks in the same domain.

Cybersecurity Challenges for PACS and Medical Imaging

Cybersecurity issues have been on the rise for years, increasingly affecting the healthcare sector. In 2019, several attacks have been published that specifically aim at medical network protocols and file formats, in particular digital imaging and communications in medicine. This article describes five attack scenarios on picture archiving and communications systems (PACS) and medical imaging networks: the import of patient data from storage media containing malware, a compromise of the hospital network, malware embedded in digital imaging and communications in medicine images or reports, a malicious manipulation of medical images and a network infiltration of malicious health level seven messages. Prevention and mitigation measures for each of these attacks exist, some of which can be implemented by the system user (e.g., hospital), while others require implementation in the PACS and medical imaging devices by the vendors. In practice, however, many of these are not in common use. What is missing today are PACS network security guidelines for practitioners that support users in keeping their network secure. Furthermore, integrating the healthcare enterprise integration profiles and test tools might be needed to address the deployment of public key infrastructure and digital signatures in the PACS environment.