Secure data sharing with blockchain for remote health monitoring applications: a review.

Remote Health Monitoring (RHM) is going to reinvent the future healthcare industry and bring about abundant value to hospitals, doctors, and patients by overcoming the many challenges currently being faced in monitoring patient's well-being, promoting preventive care, and managing the quality of drugs and equipment. Despite the many benefits of RHM, it is yet to be widely deployed due to the healthcare data security and privacy challenges. Healthcare data are highly sensitive and require fail-safe measures against unauthorized data access, leakages, and manipulations, and as such, there are stringent regulations governing how healthcare data can be secured, communicated, and stored, such as General Data Protection Regulation (GDPR) and the Health Insurance Portability and Accountability Act (HIPAA). The challenges and regulatory demands in RHM applications can be addressed using blockchain technology due to its distinguishing features of decentralization, immutability, and transparency to address the challenges of data security and privacy. This article will provide a systematic review on the use of blockchain in RHM, focusing primarily on data security and privacy.

Federated Learning for Medical Image Analysis with Deep Neural Networks.

Medical image analysis using deep neural networks (DNN) has demonstrated state-of-the-art performance in image classification and segmentation tasks, aiding disease diagnosis. The accuracy of the DNN is largely governed by the quality and quantity of the data used to train the model. However, for the medical images, the critical security and privacy concerns regarding sharing of local medical data across medical establishments precludes exploiting the full DNN potential for clinical diagnosis. The federated learning (FL) approach enables the use of local model's parameters to train a global model, while ensuring data privacy and security. In this paper, we review the federated learning applications in medical image analysis with DNNs, highlight the security concerns, cover some efforts to improve FL model performance, and describe the challenges and future research directions.

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks.

Artificial Intelligence (AI) techniques of deep learning have revolutionized the disease diagnosis with their outstanding image classification performance. In spite of the outstanding results, the widespread adoption of these techniques in clinical practice is still taking place at a moderate pace. One of the major hindrance is that a trained Deep Neural Networks (DNN) model provides a prediction, but questions about why and how that prediction was made remain unanswered. This linkage is of utmost importance for the regulated healthcare domain to increase the trust in the automated diagnosis system by the practitioners, patients and other stakeholders. The application of deep learning for medical imaging has to be interpreted with caution due to the health and safety concerns similar to blame attribution in the case of an accident involving autonomous cars. The consequences of both a false positive and false negative cases are far reaching for patients' welfare and cannot be ignored. This is exacerbated by the fact that the state-of-the-art deep learning algorithms comprise of complex interconnected structures, millions of parameters, and a 'black box' nature, offering little understanding of their inner working unlike the traditional machine learning algorithms. Explainable AI (XAI) techniques help to understand model predictions which help develop trust in the system, accelerate the disease diagnosis, and meet adherence to regulatory requirements. This survey provides a comprehensive review of the promising field of XAI for biomedical imaging diagnostics. We also provide a categorization of the XAI techniques, discuss the open challenges, and provide future directions for XAI which would be of interest to clinicians, regulators and model developers.

Multi-head deep learning framework for pulmonary disease detection and severity scoring with modified progressive learning.

Chest X-rays (CXR) are the most commonly used imaging methodology in radiology to diagnose pulmonary diseases with close to 2 billion CXRs taken every year. The recent upsurge of COVID-19 and its variants accompanied by pneumonia and tuberculosis can be fatal in some cases and lives could be saved through early detection and appropriate intervention for the advanced cases. Thus CXRs can be used for an automated severity grading of pulmonary diseases that can aid radiologists in making better and informed diagnoses. In this article, we propose a single framework for disease classification and severity scoring produced by segmenting the lungs into six regions. We present a modified progressive learning technique in which the amount of augmentations at each step is capped. Our base network in the framework is first trained using modified progressive learning and can then be tweaked for new data sets. Furthermore, the segmentation task makes use of an attention map generated within and by the network itself. This attention mechanism allows to achieve segmentation results that are on par with networks having an order of magnitude or more parameters. We also propose severity score grading for 4 thoracic diseases that can provide a single-digit score corresponding to the spread of opacity in different lung segments with the help of radiologists. The proposed framework is evaluated using the BRAX data set for segmentation and classification into six classes with severity grading for a subset of the classes. On the BRAX validation data set, we achieve F1 scores of 0.924 and 0.939 without and with fine-tuning, respectively. A mean matching score of 80.8% is obtained for severity score grading while an average area under receiver operating characteristic curve of 0.88 is achieved for classification.

Automated grading of chest x-ray images for viral pneumonia with convolutional neural networks ensemble and region of interest localization.

Following its initial identification on December 31, 2019, COVID-19 quickly spread around the world as a pandemic claiming more than six million lives. An early diagnosis with appropriate intervention can help prevent deaths and serious illness as the distinguishing symptoms that set COVID-19 apart from pneumonia and influenza frequently don't show up until after the patient has already suffered significant damage. A chest X-ray (CXR), one of many imaging modalities that are useful for detection and one of the most used, offers a non-invasive method of detection. The CXR image analysis can also reveal additional disorders, such as pneumonia, which show up as anomalies in the lungs. Thus these CXRs can be used for automated grading aiding the doctors in making a better diagnosis. In order to classify a CXR image into the Negative for Pneumonia, Typical, Indeterminate, and Atypical, we used the publicly available CXR image competition dataset SIIM-FISABIO-RSNA COVID-19 from Kaggle. The suggested architecture employed an ensemble of EfficientNetv2-L for classification, which was trained via transfer learning from the initialised weights of ImageNet21K on various subsets of data (Code for the proposed methodology is available at: https://github.com/asadkhan1221/siim-covid19.git). To identify and localise opacities, an ensemble of YOLO was combined using Weighted Boxes Fusion (WBF). Significant generalisability gains were made possible by the suggested technique's addition of classification auxiliary heads to the CNN backbone. The suggested method improved further by utilising test time augmentation for both classifiers and localizers. The results for Mean Average Precision score show that the proposed deep learning model achieves 0.617 and 0.609 on public and private sets respectively and these are comparable to other techniques for the Kaggle dataset.

Outcome after transcatheter occlusion of patent ductus arteriosus in infants less than 6 kg: A national study from United Kingdom and Ireland.

OBJECTIVES: This study aimed to report our national experience with transcatheter patent ductus arteriosus (PDA) occlusion in infants weighing <6 kg. BACKGROUND: The technique of transcatheter PDA closure has evolved in the past two decades and is increasingly used in smaller patients but data on safety and efficacy are limited. METHODS: Patients weighing < 6 kg in whom transcatheter PDA occlusion was attempted in 13 tertiary paediatric cardiology units in the United Kingdom and Ireland were retrospectively analyzed to review the outcome and complications. RESULTS: A total of 408 patients underwent attempted transcatheter PDA closure between January 2004 and December 2014. The mean weight at catheterization was 4.9 ± 1.0 kg and mean age was 5.7 ± 3.0 months. Successful device implantation was achieved in 374 (92%) patients without major complication and of these, complete occlusion was achieved in 356 (95%) patients at last available follow-up. Device embolization occurred in 20 cases (5%). The incidence of device related obstruction to the left pulmonary artery or aorta and access related peripheral vascular injury were low. There were no deaths related to the procedure. CONCLUSIONS: Transcatheter closure of PDA can be accomplished in selected infants weighing <6 kg despite the manufacturer's recommended weight limit of 6 kg for most ductal occluders. The embolization rate is higher than previously reported in larger patients. Retrievability of the occluder and duct morphology needs careful consideration before deciding whether surgical ligation or transcatheter therapy is the better treatment option.

WiseEye: Next Generation Expandable and Programmable Camera Trap Platform for Wildlife Research.

The widespread availability of relatively cheap, reliable and easy to use digital camera traps has led to their extensive use for wildlife research, monitoring and public outreach. Users of these units are, however, often frustrated by the limited options for controlling camera functions, the generation of large numbers of images, and the lack of flexibility to suit different research environments and questions. We describe the development of a user-customisable open source camera trap platform named 'WiseEye', designed to provide flexible camera trap technology for wildlife researchers. The novel platform is based on a Raspberry Pi single-board computer and compatible peripherals that allow the user to control its functions and performance. We introduce the concept of confirmatory sensing, in which the Passive Infrared triggering is confirmed through other modalities (i.e. radar, pixel change) to reduce the occurrence of false positives images. This concept, together with user-definable metadata, aided identification of spurious images and greatly reduced post-collection processing time. When tested against a commercial camera trap, WiseEye was found to reduce the incidence of false positive images and false negatives across a range of test conditions. WiseEye represents a step-change in camera trap functionality, greatly increasing the value of this technology for wildlife research and conservation management.

Limitations of recreational camera traps for wildlife management and conservation research: a practitioner's perspective.

The availability of affordable 'recreational' camera traps has dramatically increased over the last decade. We present survey results which show that many conservation practitioners use cheaper 'recreational' units for research rather than more expensive 'professional' equipment. We present our perspective of using two popular models of 'recreational' camera trap for ecological field-based studies. The models used (for >2 years) presented us with a range of practical problems at all stages of their use including deployment, operation, and data management, which collectively crippled data collection and limited opportunities for quantification of key issues arising. Our experiences demonstrate that prospective users need to have a sufficient understanding of the limitations camera trap technology poses, dimensions we communicate here. While the merits of different camera traps will be study specific, the performance of more expensive 'professional' models may prove more cost-effective in the long-term when using camera traps for research.

SPECTRUM OF CENTRAL NERVOUS SYSTEM TUMOURS--A SINGLE CENTER HISTOPATHOLOGICAL REVIEW OF 761 CASES OVER 5 YEARS.

BACKGROUND: The incidence of central nervous system (CNS) tumours has rapidly increased over the past few years. There is no accurate nationwide CNS tumour epidemiology in Pakistan that makes policy making for tumour screening and early treatment difficult. The purpose of this study was to provide the spectrum of CNS tumours in a premier diagnostic and referral centre of Pakistan. METHODS: This cross-sectional study was carried out at Histopathology Department, Armed Forces Institute of Pathology over a period of 5 years. A total of 761 cases patients who were diagnosed with CNS tumours on histopathology, both benign and malignant, belonging to both genders, between the ages of 1-85 years, from 11.2009 to 31.12.2013 were included in the study. RESULTS: Seven CNS tumour categories were as follows; tumours of neuroepithelial tissue (56.0%), tumours of the meninges (28.3%), tumour of the sellar region (2.6%), germ cell tumour (0.1), tumour of cranial and paraspinal nerves (5.4%), lymphomas and haematopoietic neoplasm (2.4%), metastatic tumours (4.9%), where histological types by age and gender showed great variability. Astrocytic tumours were the commonest neuroepithelial tumours (69.4%). Glioblastoma multiform forming the largest subtype of neuroepithelial tumours (40.4%) with a mean age at diagnosis being 47.1 years. Overall, males exceeded females in number of most of the CNS tumour types, however meningeal tumours were more frequently noted in females. CONCLUSIONS: Neuroepithelial tumours are commonest tumour and comprise more than half of all operated CNS tumours in our setup, followed by meningeal tumours. Glioblastoma multiforme is largest subtype of neuroepithelial tumour, and comprising 40.4% of all.