Classification of diabetic retinopathy using unlabeled data and knowledge distillation.

Over the last decade, advances in Machine Learning and Artificial Intelligence have highlighted their potential as a diagnostic tool in the healthcare domain. Despite the widespread availability of medical images, their usefulness is severely hampered by a lack of access to labeled data. For example, while Convolutional Neural Networks (CNNs) have emerged as an essential analytical tool in image processing, their impact is curtailed by training limitations due to insufficient labeled data availability. Transfer Learning enables models developed for one task to be reused for a second task. Knowledge distillation enables transferring knowledge from a pre-trained model to another. However, it suffers from limitations, and the two models' constraints need to be architecturally similar. Knowledge distillation addresses some of the shortcomings of transfer learning by generalizing a complex model to a lighter model. However, some parts of the knowledge may not be distilled by knowledge distillation sufficiently. In this paper, a novel knowledge distillation approach using transfer learning is proposed. The proposed approach transfers the complete knowledge of a model to a new smaller one. Unlabeled data are used in an unsupervised manner to transfer the new smaller model's maximum amount of knowledge. The proposed method can be beneficial in medical image analysis, where labeled data are typically scarce. The proposed approach is evaluated in classifying images for diagnosing Diabetic Retinopathy on two publicly available datasets, including Messidor and EyePACS. Simulation results demonstrate that the approach effectively transfers knowledge from a complex model to a lighter one. Furthermore, experimental results illustrate that different small models' performance is improved significantly using unlabeled data and knowledge distillation.

Detection of COVID-19 in X-ray images by classification of bag of visual words using neural networks.

Coronavirus disease 2019 (COVID-19) was classified as a pandemic by the World Health Organization in March 2020. Given that this novel virus most notably affects the human respiratory system, early detection may help prevent severe lung damage, save lives, and help prevent further disease spread. Given the constraints on the healthcare facilities and staff, the role of artificial intelligence for automatic diagnosis is critical. The automatic diagnosis of COVID-19 based on medical images is, however, not straightforward. Due to the novelty of the disease, available X-ray datasets are very limited. Furthermore, there is a significant similarity between COVID-19 X-rays and other lung infections. In this paper, these challenges are addressed by proposing an approach consisting of a bag of visual words and a neural network classifier. The proposed method can classify X-ray chest images into non-COVID-19 and COVID-19 with high performance. Three public datasets are used to evaluate the proposed approach. Our best accuracy on the first, second, and third datasets is 96.1, 99.84, and 98 percent. Since detection of COVID-19 is important, sensitivity is used as a criterion. The proposed method's best sensitivities are 90.32, 99.65, and 91 percent on these datasets, respectively. The experimental results show that extracting features with the bag of visual words results in better classification accuracy than the state-of-the-art techniques.

A Model for QoS - Aware Wireless Communication in Hospitals.

In the recent decade, research regarding wireless applications in electronic health (e-Health) services has been increasing. The main benefits of using wireless technologies in e-Health applications are simple communications, fast delivery of medical information, reducing treatment cost and also reducing the medical workers' error rate. However, using wireless communications in sensitive healthcare environment raises electromagnetic interference (EMI). One of the most effective methods to avoid the EMI problem is power management. To this end, some of methods have been proposed in the literature to reduce EMI effects in health care environments. However, using these methods may result in nonaccurate interference avoidance and also may increase network complexity. To overcome these problems, we introduce two approaches based on per-user location and hospital sectoring for power management in sensitive healthcare environments. Although reducing transmission power could avoid EMI, it causes a number of successful message deliveries to the access point to decrease and, hence, the quality of service requirements cannot be meet. In this paper, we propose the use of relays for decreasing the probability of outage in the aforementioned scenario. Relay placement is the main factor to enjoy the usefulness of relay station benefits in the network and, therefore, we use the genetic algorithm to compute the optimum positions of a fixed number of relays. We have considered delay and maximum blind point coverage as two main criteria in relay station problem. The performance of the proposed method in outage reduction is investigated through simulations.