UreteroPelvic Junction Obstruction (UPJO) is a common hydronephrosis disease in children that can result in an even progressive loss of renal function. Ultrasonography is an economical, radiationless, noninvasive, and high noise preliminary diagnostic step for UPJO. Artificial intelligence has been widely applied to medical fields and can greatly assist doctors' diagnostic abilities. The demand for a highly secure network environment in transferring electronic medical data online, therefore, has led to the development of blockchain technology. In this study, we built and tested a framework that integrates a deep learning diagnosis model with blockchain technology. Our diagnosis model is a combination of an attention-based pyramid semantic segmentation network and a discrete wavelet transformation-processed residual classification network. We also compared the performance between benchmark models and our models. Our diagnosis model outperformed benchmarks on the segmentation task and classification task with$\mathsf{MloU}=87.93,\ \mathsf{MPA}=93.52$, and$\text{accuracy}=91.77\%$. For the blockchain system, we applied the InterPlanetary File System protocol to build a secure and private sharing environment. This framework can automatically grade the severity of UPJO using ultrasound images, guarantee secure medical data sharing, assist in doctors' diagnostic ability, relieve patients' burden, and provide technical support for future federated learning and linkage of the Internet of Medical Things (IoMT).
Muhammad Umar Nasir, Muhammad Zubair, Taher M. Ghazal, Muhammad Farhan Khan Ā· 9 authors
Kidney cancer is a very dangerous and lethal cancerous disease caused by kidney tumors or by genetic renal disease, and very few patients survive because there is no method for early prediction of kidney cancer. Early prediction of kidney cancer helps doctors start proper therapy and treatment for the patients, preventing kidney tumors and renal transplantation. With the adaptation of artificial intelligence, automated tools empowered with different deep learning and machine learning algorithms can predict cancers. In this study, the proposed model used the Internet of Medical Things (IoMT)-based transfer learning technique with different deep learning algorithms to predict kidney cancer in its early stages, and for the patient's data security, the proposed model incorporates blockchain technology-based private clouds and transfer-learning trained models. To predict kidney cancer, the proposed model used biopsies of cancerous kidneys consisting of three classes. The proposed model achieved the highest training accuracy and prediction accuracy of 99.8% and 99.20%, respectively, empowered with data augmentation and without augmentation, and the proposed model achieved 93.75% prediction accuracy during validation. Transfer learning provides a promising framework with the combination of IoMT technologies and blockchain technology layers to enhance the diagnosing capabilities of kidney cancer.
Abstract In recent years, the rapid development in information technologies appears in the form of digitalization, all of the processes in the health domain. Among the stateāofāart, virtual reality, artificial intelligence, and blockchain technologies are among the most mentioned. In addition, the exponential increase in data kept in the electronic environment causes traditional central applications to face new challenges. The most important of these are accountability, transparency, security, cost, and time efficiency. In this study, a model based on blockchain technologies has been proposed to increase the transparency, accountability, and security of multiāstakeholder shared medical data by using smart contracts (SCs). In the first part, there are briefly introduced the current situation of the health domain, blockchain technology, hyperledger fabric (HLF) and SCs. Afterward, in line with the latest technological developments, the studies carried out using the blockchain framework related to organ/tissue transplantation were examined. Lastly, the proposed framework was designed based on blockchain technologies for organ/tissue transplantation by using the HLF environment. The blockchain technology not only provides more visibility, more security, and better outcomes but also enables to store data securely and cheaply without allocating extra resources to a trusted authority. Thus, it can be ensured that the system is more transparent and more accountable.
Since the first successful kidney transplant in 1954, organ donation and transplantation has been an important medical treatment that improves the lives of thousands of patients who experienced organ failure(s). However, the allocation of scarce kidneys is a complex process, partially due to a significant imbalance between kidney supply and demand. To solve this issue, a number of allocation algorithms have been used and a few blockchain-based solutions have been proposed. To improve organ donation and cover more patients in need, organizations responsible for organ donation around the world are looking to combine their efforts. Nevertheless, there are still many unanswered questions. For instance, organ allocation policies and guidelines considerably differ depending on the country, and hence international regulations are needed. One of the important aspects of such regulations is the fact that the data from stakeholders and the matching patients - donors algorithm is stored in the central point of these organizations. In this short survey, we investigate existing organ allocation algorithms. The focus of this paper is on blockchain-based decentralized systems. Out of many organ donation systems, the aim of this review is on kidney allocation algorithms, this choice is justified by the fact that the kidney is one of the most in-demand organ transplants. We also discuss some limitations in exiting organ donation systems and allocation algorithms and elaborate on how blockchain technologies could be the cornerstone technology to solve some of the existing issues in the area of organ donation.