Current Medical Imaging - Volume 19, Issue 1, 2023

COVID-19 is a pandemic initially identified in Wuhan, China, which is caused by a novel coronavirus, also recognized as the Severe Acute Respiratory Syndrome (SARS-nCoV-2). Unlike other coronaviruses, this novel pathogen may cause unusual contagious pain, which results in viral pneumonia, serious heart problems, and even death. Researchers worldwide are continuously striving to develop a cure for this highly infectious disease, yet there are no well-defined absolute treatments available at present. Several vaccination drives using emergency use authorisation vaccines have been held across many countries; however, their long-term efficacy and side-effects studies are yet to be studied. Various analytical and statistical models have been developed, however, their outcome rate is prolonged. Thus, modern science stresses the application of state-of-the-art methods to combat COVID-19. This paper aims to provide a deep insight into the comprehensive literature about AI and AI-driven tools in the battle against the COVID-19 pandemic. The high efficacy of these AI systems can be observed in terms of highly accurate results, i.e., > 95%, as reported in various studies. The extensive literature reviewed in this paper is divided into five sections, each describing the application of AI against COVID-19 viz. COVID-19 prevention, diagnostic, infection spread trend prediction, therapeutic and drug repurposing. The application of Artificial Intelligence (AI) and AI-driven tools are proving to be useful in managing and fighting against the COVID-19 pandemic, especially by analysing the X-Ray and CT-Scan imaging data of infected subjects, infection trend predictions, etc.

Background: Treatment planning is one of the crucial stages of healthcare assessment and delivery. Moreover, it also has a significant impact on patient outcomes and system efficiency. With the evolution of transformative healthcare technologies, most areas of healthcare have started collecting data at different levels, as a result of which there is a splurge in the size and complexity of health data being generated every minute. Introduction: This paper explores the different characteristics of health data with respect to big data. Besides this, it also classifies research efforts in treatment planning on the basis of the informatics domain being used, which includes medical informatics, imaging informatics and translational bioinformatics. Methods: This is a survey paper that reviews existing literature on the use of big data technologies for treatment planning in the healthcare ecosystem. Therefore, a qualitative research methodology was adopted for this work. Results: Review of existing literature has been analyzed to identify potential gaps in research, identifying and providing insights into high prospect areas for potential future research. Conclusion: The use of big data for treatment planning is rapidly evolving, and findings of this research can head start and streamline specific research pathways in the field.

Big data has been a topic of interest for many researchers and industries for the past few decades. Due to the exponential growth of technology, a tremendous amount of data is generated every minute. This article provides a strategic review of big data in the healthcare sector. In particular, this article highlights various applications and issues faced by the healthcare industry using big data by evaluating various journal articles between 2016 and 2021. Multiple issues related to data mining, storing, analyzing, and sharing of big data in healthcare, briefly summarizing deep-learning-based tools available for big data analytics, have been covered in this article. This article aims to benefit the research community by summarizing various research tools and processes available today to manage big data in healthcare.

Background: Computer vision in general and semantic segmentation has experienced many achievements in recent years. Consequently, the emergence of medical imaging has provided new opportunities for conducting artificial intelligence research. Since cancer is the second-leading cause of death in the world, early-stage diagnosis is an essential process that directly slows down the development speed of cancer. Methods: Deep neural network-based methods are anticipated to reduce diagnosis time for pathologists. Results: In this research paper, an approach to liver tumor identification based on two types of medical images has been presented: computed tomography scans and whole-slide. It is constructed based on the improvement of U-Net and GLNet architectures. It also includes sub-modules that are combined with segmentation models to boost up the overall performance during inference phases. Conclusion: Based on the experimental results, the proposed unified framework has been emerging to be used in the production environment.

Background: In order to remain active and productive, older adults with poor health require a combination of advanced methods of visual monitoring, optimization, pattern recognition, and learning, which provide safe and comfortable environments and serve as a tool to facilitate the work of family members and workers, both at home and in geriatric homes. Therefore, there is a need to develop technologies to provide these adults autonomy in indoor environments. Objective: This study aimed to generate a prediction model of daily living activities through classification techniques and selection of characteristics in order to contribute to the development in this area of knowledge, especially in the field of health. Moreover, the study aimed to accurately monitor the activities of the elderly or people with disabilities. Technological developments allow predictive analysis of daily life activities, contributing to the identification of patterns in advance in order to improve the quality of life of the elderly. Methods: The vanKasteren, CASAS Kyoto, and CASAS Aruba datasets were used to validate a predictive model capable of supporting the identification of activities in indoor environments. These datasets have some variation in terms of occupation and the number of daily living activities to be identified. Results: Twelve classifiers were implemented, among which the following stand out: Classification via Regression, OneR, Attribute Selected, J48, Random SubSpace, RandomForest, RandomCommittee, Bagging, Random Tree, JRip, LMT, and REP Tree. The classifiers that show better results when identifying daily life activities are analyzed in the light of precision and recall quality metrics. For this specific experimentation, the Classification via Regression and OneR classifiers obtain the best results. Conclusion: The efficiency of the predictive model based on classification is concluded, showing the results of the two classifiers, i.e., Classification via Regression and OneR, with quality metrics higher than 90% even when the datasets vary in occupation and number of activities.

Background: Automatic classification of brain tumors is an important issue in computeraided diagnosis (CAD) for medical applications since it can efficiently improve the clinician’s diagnostic performance and the current study focused on the CAD system of the brain tumors. Methods: Existing studies mainly focused on a single classifier either based on traditional machinelearning algorithms or deep learning algorithms with unsatisfied results. In this study, we proposed an ensemble of pre-trained convolutional neural networks to classify brain tumors into three types from their T1-weighted contrast-enhanced MRI (CE-MRI) images, which are meningioma, glioma, and pituitary tumor. Three pre-trained convolutional neural networks (Inception-v3, Resnet101, Densenet201) with the best classification performance (i.e. accuracy of 96.21%, 97.00%, 96.54%, respectively) on the CE-MRI benchmark dataset were selected as backbones of the ensemble model. The features extracted by backbone networks in the ensemble model were further classified by a support vector machine. Results: The ensemble system achieved an average classification accuracy of 98.14% under a five-fold cross-validation process, outperforming any single deep learning model in the ensemble system and other methods in the previous studies. Performance metrics for each brain tumor type, including area under the curve, sensitivity, specificity, precision, and F-score, were calculated to show the ensemble system’s performance. Our work addressed a practical issue by evaluating the model with fewer training samples. The classification accuracy was reduced to 97.23%, 96.87%, and 93.96% when 75%, 50%, and 25% training data was used to train the ensemble model, respectively. Conclusion: Our ensemble model has a great capacity and achieved the best performance in any single convolutional neural networks for brain tumors classification and is potentially applicable in real clinical practice.

Background: How to reduce the radiation dose received from full-body CT scans during the follow-up of lymphoma patients is a concern. Objective: The aim of the study was to investigate the image quality and radiation dose of reduced-dose full-body computerized tomography (CT) in lymphoma patients during the follow-up. Methods: 121 patients were included and divided into conventional CT group (group 1, 120-kVp, n = 61) or reduced-dose CT group (group 2, 100-kVp combined dual-energy CT (DECT), n = 60). 140-kVp polychromatic images and 70-keV monochromatic images were reconstructed from DECT. The abdominal virtual non-enhanced (VNE) images were reconstructed from monochromatic images. Two radiologists rated the overall image quality with a five-point scale and graded the depiction of lesions using a four-point scale. The objective image quality was evaluated using image noise, signal-to-noise ratio, and contrast-to-noise ratio. The radiation dose and image quality were compared between the groups. Results: The comparable subjective image quality was observed between 70-keV and 120-kVp images in the neck, while 120-kVp images showed better objective image quality. 70-keV images showed better objective image quality in the chest. While the subjective image quality of abdominal VNE images was inferior to that of true non-enhanced images, the improved objective image quality was observed in VNE images. In the abdominal arterial phase, similar subjective image quality was observed between the groups. Abdominal 70-keV images in the arterial phase showed improved objective image quality. Similar image quality was obtained in the abdominal venous phase between the groups. The effective radiation dose in group 2 showed a significant reduction. Conclusion: The application of reduced-dose full-body CT can significantly reduce the radiation dose for lymphoma patients during the follow-up while maintaining or improving the image quality.

Introduction: A 67-year-old female with no significant past medical history presented to the critical care department with symptoms of encephalopathy. Case Presentation: The patient’s Main Concerns and the Important Clinical Findings: The patient had a history of COVID -19 vaccination (recombinant ChAdOX1 nCoV-19) 14 days prior to the symptoms. She underwent an MRI of the brain and cervical spine and a lumbar puncture. The Primary Diagnoses, Interventions, and Outcomes: The patient was examined and sent for an MRI of the brain and cervical spine, followed by extensive blood and CSF investigations to rule out any infective, paraneoplastic, connective tissue disorder, or inflammatory disorder. The patient was given steroids, and a good response was reported. The primary diagnosis was made as vaccine-induced ADEM. Conclusion: The clinical exam, location, sparse contrast enhancement, and CSF findings were all consistent with an acute demyelinating event, and the history of vaccination, together with the clinical situation, was found to be favourable for the development of acute disseminated encephalomyelitis.