Current Medical Imaging

In the current era, due to various reasons, the disease occurrence rate in humans is gradually rising rapidly. In order to support accurate disease detection and also reduce the diagnostic burdens of the doctors during the mass screening process, a considerable number of traditional and modern disease detection systems are proposed and implemented by the researchers. The term medical data refers to the collection of the essential bio-signals and bio-images from the patients using the recommended protocol and after collecting the essential information from the patient, the database is then examined using the traditional and modern approaches. The traditional technique involves data pre-processing, post-processing and semi-automated and automated segmentation and classification approaches. Based on the implementation procedures, modern methods can be categorized as the machine-learning and deep-learning methods. Most of the machine-learning techniques combine the traditional disease detection procedures with the modern classifiers, which help categorize the medical data into normal and abnormal class. The traditional and machine-learning methods require very little computation const compared to the deep-learning methods. The deep-learning methods are one of the key research domains in which a Convolutional Neural Network is employed to diagnose the disease in medical data with accuracy. The computation cost required for this scheme is more compared to other methods. The recent works in the literature confirmed that, compared to the traditional methods, the machine-learning and deep-learning works are largely implemented to evaluate bio-signals and bio-images. When raw medical data is given to these systems, it will help assist the doctors to identify the disease and its severity level; which is the prime parameter during the decision making and treatment implementation process. The Current Medical Imaging (Current Medical Imaging Reviews) Journal provides an outstanding standard for propagation and understanding of different medical data supported disease investigative methodologies followed in clinics. This special issue of Current Medical Imaging entitled “Medical Data Assessment with Traditional, Machine-learning and Deep-learning Techniques” brings together the author’s effort to convey up-to-date technical and scientific conversation on the applications of customary and modern disease diagnostic methods available in the field of medical imaging. This issue includes the following outstanding contributions from eminent researchers and presents the applications of medical data assisted disease assessment in key fields, such as (i) Breast cancer, (ii) Retinal disorder, (iii) Gastric tract infections and (iv) Data tagging. This special issue clearly increases the applications of medical data appraisal methods for the design and analysis of a variety of semi-automated and automated diagnostic tools. I am indebted to the Editor-in-Chief, Prof. Dr. Euishin Edmund Kim for his valuable support. I thank Maryam Fatima, Assistant Manager Publications, Bentham Science Publishers for the invaluable assistance and support. The Editor would like to thank all the Reviewers of this special issue for their excellent reviews and comments.

The recent development in science, technology and the medical domain helped the human communality to live life with a better ambiance. The improved livelihood helps humans to access a wide variety of facilities, including the state of the art medical facilities. Even though considerable measures are taken to prevent and cure the diseases in humans, the incident rates of new kinds of infectious and communicable/non-communicable diseases are rapidly rising in humans irrespective of their age, race and gender. In order to support the early diagnosis and treatment implementation for the disease, a number of diagnostic procedures are proposed and implemented in various disease diagnostic centers and clinics. The disease diagnosis based on the medical image is quite straight forward as compared to other diagnostic procedures. Hence, a number of disease examination techniques based on the medical-images of varied modalities are practically used in hospitals. Based on the observation from these images, the doctor will plan for an appropriate treatment procedure to cure the disease. Examination of medical images requires precise and accurate image processing techniques, and hence computer-based diagnostic techniques are recently employed to assess a variety of medical images. The recently soft-computing procedure also plays a major role in medical image analysis by reducing the diagnostic burden during the mass screening process. The Current Medical Imaging (formerly: Current Medical Imaging Reviews) Journal offers an exceptional standard for the propagation and understanding of various medical imaging assisted disease diagnostic techniques followed in hospitals. This special issue of Current Medical Imaging entitled “Medical image Examination using Traditional and Soft-computing Approaches” brings together the author’s endeavor to bring up-to-date scientific and technological discussion on the applications of traditional and modern computational techniques in the field of medical imaging. This issue includes the following outstanding contributions from eminent researchers and presents the applications of image supported disease examination in key domains, such as (i) Dentistry, (ii) Dermatology, (iii) Breast abnormality and (iv) Brain abnormality assessment [1-11]. This special issue evidently magnifies the applications of medical image assessment procedures for the design and analysis of various computer-assisted diagnostic tools. I am indebted to the Editor-in-Chief, Prof. Dr. Euishin Edmund Kim, for his valuable support. I thank Ms. Romasa Azhar Mahaser, Assistant Manager Publications, Bentham Science Publishers for the invaluable assistance and support. The Editor would like to thank all the Reviewers of this special issue for their excellent reviews and comments.

1. INTRODUCTION Medical imaging is the procedure used to produce images of inner parts of body for facilitating diagnosis and treatment according to the view of interior tissues or organs. In the past decades, medical imaging technologies, such as X-ray radiography, X-ray Computed Tomography (CT), Magnetic Resonance Imaging (MRI), ultrasonography, elastography, optical imaging, Radionuclide imaging includes (Scintigraphy, Positron Emission Tomography (PET) and Single Photon Emission Computed Tomography (SPECT)), thermography, and Terahertz imaging, have been used to help diagnose a wide variety of diseases and injuries. Meanwhile, the rapid development of computer technology in medical image processing and analysis can produce high quality images and obtain useful quantitative information from the original medical images. In the field of medical image processing and analysis, it includes a variety of research areas such as image segmentation, image registration, image fusion and 3D visualization. 2. THEMES OF THIS SPECIAL ISSUE This special issue contains research papers addressing the state-of-the-art in computational algorithms on medical image processing. The manuscripts tackle research on different topics including detection of white matter hyperintensities from brain MRI, classification of uterus movements from MRI, identification of bone tunnel opening sites from 2D X-ray images, and the set of accepted papers are briefly described in the remaining parts of this section. White Matter Hyperintensities (WMHs) are cerebral white matter lesions that are characterized by abnormal tissues of variable sizes and appear hyperintense in T2-weighted Magnetic Resonance (MR) measurements without cavitation. Typically, these abnormal tissue regions, which are associated with several geriatric neurodegenerative diseases, can be observed in the MR images of brains of healthy old people. However, manual measurement of WMHs requires time and meets the intra- and inter-observer errors caused by human subjectivity. Computer-aided technologies have been used to measure WMH volumes. Chen et al. [1] proposed a computer-aided technique for automatically detecting and segmenting anomalies in MR images. The proposed method consists of two steps: (1) a Band Expansion Process (BEP) to expand the dimensions of brain MR images nonlinearly and (2) anomaly detection algorithms to detect WMHs. In the experiments, synthesized MR images provided by BrainWeb were used as benchmarks for the comparison of performance among the algorithms. From experimental results, the proposed method is superior to other algorithms from brain MRIs. The uterus has movements called uterine peristalsis, which is the wavelike movements of the subendometrial myometrium to assist in the transport of sperms. The direction and frequency of peristalsis are known to change among menstrual cycle phases. Two different movements, the upward and the downward, happen in the menstrual and luteal phases, respectively. Recently, random and mixed movements that occur in all phases in infertile patients are observed from MRI. Mori et al. [2] proposed a classification algorithm to identify complicated uterine movements from MRIs and investigate the relationship between uterine peristalsis and female infertility. Six fundamental movements have been found from 26 MRI scans. From the experimental results, two fundamental movements are identified as the candidate factor of female infertility successfully. These results showed that the proposed method is useful to identify uterine movement for analyzing infertile patients. One of the most common knee injures is an Anterior Cruciate Ligament (ACL) sprain or tear causing knee instability which affects sports activity involving cutting and twisting motions. To treat this kind of injure is to replace the damaged ACL with artificial one which is fixed to the bone tunnels opened by the surgeon by using ACL reconstruction surgery.The tunnel drilling technique is the critical factor in placement of the bone tunnels, and it affects the surgical results. The quadrant method is used for the post-operative evaluation of the ACL reconstruction surgery, which estimates the bone tunnel opening sites on the lateral 2D X-ray radiograph. Morita et al. [3] proposed a computer-aided surgical planning system for the ACL reconstruction. The experimental image data are synthesized the pseudo lateral 2D X-ray radiograph from the patients' knee MRI. The experimental results show that the proposed method can identify appropriate bone tunnel opening sites on the pseudo lateral 2D X-ray radiograph synthesized from the pre-operative knee MRI. Quantifying cortical morphological dynamics of adult brain deformation is able to assist neurologists to identify brain deformation disorders. If the normal cortical shape evolution for adults can be found, doctors are able to predict abnormal or early deformation of the brain with time according to the evolution trajectories. Shape variability from statistical models has become functional with success to perform various research in the field of medical image analysis in both two-dimensional (2D) and three-dimensional (3D) images. Alam et al. [4] introduced a novel approach for constructing a 3D spatiotemporal statistical shape model (st-SSM) using brain MRI of adults. The 3D st-SSM is created for temporal 3D shape change analysis of the adult brain with respect to cortical surfaces using an expectation-maximization (EM) based weighted PCA (wPCA) learning frame-work. The performance of st-SSM is superior to conventional SSM. An application of the proposed approach is also introduced which involves Alzheimer’s disease (AD) identification utilizing support vector machine.

Soft computing refers to a collection of imprecision-tolerant techniques which can fairly deal with uncertainty, partial truth, and approximation. The basic constituents of soft computing are fuzzy logic, neural computing, evolutionary computation, and machine learning. Soft computing may be viewed as a foundation component for the emerging field of conceptual intelligence to generate human-type intelligence in computers. Most of the current research works are focused on one or the other methods encouraged by these concepts and therefore, attracting students. Soft computing is having a especially important role in science and engineering in many ways and becoming a backbone of almost all the upcoming technologies. This special issue contains research contributions from leading scholars from all over the world with comprehensive coverage of each specific topic, highlighting recent and future trends and describing the latest advances. Highlighting theoretical perspectives and empirical research, we hope that this special issue will prove to be a comprehensive reference source for researchers, practitioners, students, and professionals interested in the current advancements and efficient use of Soft Computing methods. This issue is a catalogue of ten quality papers presented by various authors across the globe. All the issues related to soft computing and its applications are covered in the following papers: A Comprehensive Review on Nature Inspired Neural Network-based Adaptive Filter for Eliminating Noise in Medical Images: In this comprehensive review article, more than 65 research articles are investigated to illustrate the applications of Artificial Neural Networks (ANN) in the field of biomedical image denoising. The objective is to highlight the hybridized filtering model using nature-inspired algorithms and artificial neural networks for suppression of noise. Various other techniques, such as fixed filter, linear adaptive filters and gradient descent learning-based neural network filters, are also included. This article envisages how to train ANN using derivative-free nature-inspired algorithms, and its performance in various medical images modalities and noise conditions [1]. Computational Intelligence Techniques for Assessing Anthropometric Indices Changes in Female Athletes: This research proposes a novel approach for determining the slimming effect of a herbal composition as a natural medicine for weight loss. To build an effective prediction model, a modern hybrid approach, merging Adaptive Network-based Fuzzy Inference System and Particle Swarm Optimization (ANFIS-PSO) was designed for prediction of changes in anthropometric indices including waist circumference, waist to hip ratio, thigh circumference and mid-upper arm circumference, on female athletes after the consumption of caraway extract during ninety days clinical trial. The outcomes showed that caraway extract intake was effective in lowering all anthropometric indices in female athletes after ninety days trial. The results by ANFIS-PSO was more accurate compared to SPSS [2]. An Improved B-hill Climbing Optimization Technique for Solving the Text Documents Clustering Problem: This paper presents a novel local clustering technique, namely, β-hill-climbing, to solve the problem of the text document clustering through modeling the β-hill-climbing technique for dividing the similar documents into the same cluster. The β parameter is the primary innovation in β-hill climbing technique. Experiments were conducted on eight benchmark standard text datasets with different characteristics taken from the Laboratory of Computational Intelligence (LABIC). The results proved that the proposed β-hill-climbing achieved better results in comparison with the original hill-climbing technique in solving the text clustering problem [3]. Modified Cuckoo Search Algorithm Using a New Selection Scheme for Unconstrained Optimization Problems: In this paper, the modified cuckoo search algorithm (MCSA) is proposed to enhance the performance of CSA for unconstrained optimization problems. MCSA is focused on the default selection scheme of CSA (i.e. random selection), which is replaced with tournament selection. The experimental results showed that the performance of MCSA outperformed standard CSA and the existing literature methods [4]. An Intuitionistic Fuzzy Based Novel Approach to CPU Scheduler: This paper introduces a novel approach to design an intuitionistic fuzzy inference system for CPU scheduler. The proposed inference system is implemented with a priority scheduler. The proposed scheduler has the ability to dynamically handle the impreciseness of both priority and estimated execution time. Simulation results prove the effectiveness and efficiency of intuitionistic fuzzy-based priority scheduler [5]. Cat Swarm Optimization based Functional Link Multilayer Perceptron for Suppression of Gaussian and Impulse Noise from Computed Tomography Images: This paper discusses the Gaussian and impulse noise that corrupts the Computed Tomography (CT) images either individually or collectively, and the conventional fixed filters that do not have the potential to suppress these noises. These spurious noises affect the inherent features of the CT image. Hence, to handle such a situation, an adaptive Cat Swarm Optimization based Functional Link Multilayer Perceptron (CSO-FLMLP) has been proposed in this paper to get rid of unwanted noise from the CT images. In this work, the cost function considered for CSO highlights the error between noisy and contextual pixels of reference images. For examining the efficiency of the CSO-FLMLP filter, it is compared with the other six competitive adaptive filters [6]. Implementation and Analysis of Classification Algorithms for Diabetes: This paper presents a novel classification technique for the detection of diabetes in a timely and effective manner. In this study, a comparative analysis of outcomes obtained by with and without the use of GA for the same set of classification technique. It has been conclusively inferred that GA is helpful in removing insignificant attributes, reducing the cost and computation time while enhancing ROC and accuracy. The utilized strategy may likewise be executed for other medical issues [7]. Multi-Objective Evolutionary Approach for the Performance Improvement of Learners Using Ensembling Feature selection and Discretization Technique on Medical Data: This paper proposes a novel multi-objective based dimensionality reduction framework, which incorporates both discretization and feature reduction as an ensemble model for performing feature selection and discretization. The selection of optimal features and categorization of discretized and nondiscretized features from the feature subset are governed by the multi-objective genetic algorithm (NSGA-II). An extensive experiment was conducted on the dataset, to prove that the proposed model improves the classification rate and outperforms the base learner [8]. Design of Patient-Specific Spinal Implant (Pedicle Screw Fixation) using FE Analysis and Soft Computing Techniques: This work uses the Genetic Algorithm (GA) for optimum design of patient-specific spinal implants (pedicle screw) with varying implant diameter and bone condition. The optimum pedicle screw fixation in terms of implant diameter works on the basis of minimum strain difference from the intact bones (natural) to implantation at the peri-prosthetic bone for the considered six different peri-implant positions. This design problem is expressed as an optimization problem using the desirability function, where the data generated by finite element analysis is converted into an Artificial Neural Network (ANN) model [9]. Half Difference Expansion Based Reversible Data Hiding Scheme for Medical Image Forensics: Medical image authentication is an important area which attempts to establish ownership authentication and data authentication of medical images. In this paper, the authors proposed a new reversible watermarking scheme based on a novel half difference expansion technique for medical image forensics. Experimental study of the proposed scheme on the standard medical images from the Osrix medical image data set showed that the proposed watermarking scheme outperforms the existing schemes in terms of the visual quality of the watermarked image and embedding rate [10]. We express our heartfelt gratitude to all the authors, reviewers and Bentham Science personnel, especially Aqsa Hassan, for endless motivation and patience. Special thanks to Ms. Ambreen Irshad and Romasa Azhar Mahaser for their constant support. We hope that this issue will be beneficial to all the concerned readers.

Multi-Modality Cardiac Imaging in Interventional Cardiology

Internet of Things (IoT) plays a vital role in medical imaging technologies to enable fast access to information about patient health and continuous monitoring through the wireless environment. By using the cloud platform, the patient’s healthcare data can be stored and accessed. It makes e-health smarter in all aspects. Wireless Body Area Network (WBAN) is the most important factor and it will be surrounded by the patient. This WBAN technology helps resolve the issues including secure and safe communication, high efficiency and low complexity in installation. The advancement of this technology includes cloud storage, big data analytics, embedded sensors, sustainable computing, data mining, biomedical imaging, computational vision, healthcare informatics, cyber-physical/biological methods and smart wearable devices. Internet of Health Things (IoHT) is applied to collect the both data and vital information [1] from hospitals. Based on the information provided, intelligent algorithms are implemented. IoHT [2] helps to diagnosis the disease in earlier stage and provides the better solution by using decision making process. Big data analytics [3] helps to maintain the structured and unstructured data to avoid complexity in data transmission. Deep learning algorithm [4] plays a vital role in the detection of disease and helps in the diagnosis process. Magnetic Resonance Network in MS (MAGNIMS) [5] helps to update the image feature and pattern recognition process based on deep learning approach. This special issue focused on the various aspects of medical imaging technologies such as the detection and classification of disease, disease prediction, fault diagnosis, wireless communication and IoT based video transmission. This issue addresses the research issues faced in normal day to day life activities such as communication security, transmission delay, channel allocation, resource utilization, signal propagation, topology maintenance, link control, error control, energy saving, lifetime maintenance and efficient communication.

Sarcoidosis is a complex disorder characterized by non-caseating granulomatous inflammation, preferentially affecting the lungs but virtually every organ and tissue. Epidemiology is quite complex due to variability related to gender, racial and geographical distribution, and sometimes can be underestimated if atypical or non-specific presentation occurs. Sarcoidosis can lead to significant morbidity if not recognized and treated promptly, therefore every effort should be made to achieve an early diagnosis. Imaging techniques, such as high-resolution computed tomography and magnetic resonance imaging can give useful diagnostic clues, and should be integrated with biopsy of affected tissues. FDG-PET has several advantages as can be useful to assess disease activity, monitor response to the therapy and demonstrates occult sites to guide biopsy, both of pulmonary and extrapulmonary manifestations. This special issue aims at describing current state of the art of FDG-PET imaging of sarcoidosis, both pulmonary and extrapulmonary disease. The investigators are invited to contribute with original research and review articles focused, but not limited, to the following topics. Both solicited and unsolicited articles will be considered.

No Text Found