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.

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.

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.

Dementia affects millions of people worldwide, and poses significant challenges due to its irreversible nature and a lack of effective treatment options. Dementia has a considerable influence on people and society and puts a heavy burden on the healthcare systems. This underscores an urgent need for proactive measures to address this public health concern through early detection and intervention. This paper investigates the use of machine learning for an early detection of dementia and its progression utilizing a public dataset. Various traditional machine learning algorithms, were used on the demographic data, with the Gaussian Naïve Bayes achieving the highest accuracy of 91.30%. Four deep learning models, ResNet50, DenseNet121, VGG16, and Inceptionv3 were used on image data, with the DenseNet121 model achieving the highest accuracy of 90%. We also used SHapley Additive exPlanations (SHAP) framework for dementia progression which revealed that Normalised Whole Brain Volume (nWBV) exhibited higher variability in their impact across models. This study demonstrates the potential of machine learning approaches for early dementia detection and prognosis, which can have significant effect in patient care strategies.

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.