Blockchain Papers

Andrew Kim, Jarrett Bobrin, David Weinstein, Isabelle Kim

Non-fungible Tokens (NFTs) in Diagnostic ImagingAndrew Kim1, Jarrett Bobrin1, David Weinstein1, Isabelle G. Kim.Temple University Hospital1, Department of Radiology, Philadelphia, PA.Non-fungible tokens (NFTs) have garnered significant media attention in recent years, largely due to the astronomical prices fetched by some digital artworks. They have emerged as a popular medium for buying and selling digital art. Most people associate NFTs with high-profile examples such as the Bored Ape Yacht Club or Beeple’s digital artwork, the latter of which famously sold for over $69 million. Even the world’s first SMS text message was converted into an NFT and sold for over 100,000 euros. In 2021, the NFT market was valued at approximately $41 billion USD, and the term “NFT” ranked among the most popular search terms on Google during both 2021 and early 2022.However, NFTs are more than just digital collectibles; they hold significant untapped potential, particularly in the medical field, including diagnostic imaging. While blockchain technology has been widely explored in healthcare, the specific role of NFTs in diagnostic imaging remains largely unexplored. Although there has been extensive discussion on the use of blockchain in medicine, the application of NFTs in this space is still in its infancy.So, what exactly is an NFT? A non-fungible token is a unique digital asset representing ownership of a specific item or piece of data—whether that be digital artwork, music, or in more recent applications, items in video games or medical records. NFTs are built using the same blockchain technology as cryptocurrencies like Ethereum. However, unlike cryptocurrencies or fiat currencies, NFTs are non-fungible, meaning they are not interchangeable, and each holds a distinct value. Both NFTs and cryptocurrencies rely on blockchain transactions to validate authenticity and ownership. NFTs serve as a digital certificate of ownership, and each time an NFT changes hands, the transaction is recorded on the blockchain decentralized, public ledger.NFTs also incorporate smart contract technology, which is particularly relevant to the field of medicine. For instance, in the art world, the original artist may receive royalty every time their artwork is resold. This same mechanism can be applied to healthcare data, offering both security and potential financial benefits to patients.In the U.S., it is estimated that each patient generates approximately 80 megabytes of health data annually. Utilizing NFTs to manage medical data would allow patients to enhance the confidentiality of their personal health information. Through smart contracts, patients could control and define who has access to their data—whether it’s their primary care physician, an emergency room doctor, a radiologist, or a specialist at a cancer center. Once recorded on a public, decentralized blockchain, this data becomes immutable and highly secure, preventing tampering or unauthorized access.This model empowers patients and shifts control away from commercial or nonprofit institutions that often manage and monetize patient data without individual input. As Dr. Kristin Kostick-Quenet has pointed out, once health information is digitized, it typically falls out of the patient’s control and is commodified by companies for profit. NFTs offer a solution: patients could maintain ownership over their data and even receive financial compensation when it is accessed or utilized.The digital contracts associated with NFTs also allow patients to trace the use of their data—who accessed it, when, how, and why. According to an article from Cointelegraph, the healthcare platform Aimedis plans to tokenize anonymized patient data into NFTs, which can then be sold to pharmaceutical companies. In return, patients may receive revenue from the sales of these NFT tokens. However, a key challenge remains, healthcare IT systems are currently fragmented and not yet optimized for this level of integration. In an ideal future, patients would use a single login interface to manage all their health data.Importantly, NFTs can enhance the quality and accessibility of medical data, making it more suitable for artificial intelligence applications and data mining. Aimedis aims to revolutionize global exchange and monetize de-identified health data using blockchain and NFT technologies.NFTs also have direct applications in radiology. Patients could predefine which radiologists or physicians can access their imaging studies and reports. They could also track who views their data and under what circumstances. If their imaging is later sold or used by a commercial entity—such as a medical center or pharmaceutical company—for research or drug development, the patient could receive royalty payments each time it is used. For example, if a cancer patient undergoes a PET/CT scan and the resulting data is converted into an NFT, a pharmaceutical company using that data in drug research might owe compensation to the patient.Moreover, NFTs could enhance the information available to radiologists. For example, they could include important historical details, such as previous reactions to gadolinium contrast, a history of renal insufficiency, or retained metal that could affect MRI compatibility. Such centralized and accessible data would aid in ensuring patient safety and improving diagnostic accuracy.With the rise of telemedicine, NFTs could also play a key role in verifying transactions between the physical and digital healthcare environments. For example, a doctor’s prescription or imaging order could be tokenized, eliminating any ambiguity regarding its origin or intent. In radiology, this could clarify whether a referring physician wanted a CT scan with or without contrast or preferred a two-view chest X-ray over a portable study—ultimately improving communication between referring clinicians and radiology departments.Teleradiology images could also be tokenized, giving patients visibility over who has accessed their reports and to whom results were sent. In addition, NFTs could be used to verify the credentials of radiologists, such as medical degrees and certifications. Since this information would be recorded on an immutable blockchain, it would be secure and tamper-proof. This could reduce administrative burdens, such as those placed on radiology file rooms by repeated requests for copies of reports or credentials.Tokenized radiology data may also serve as a valuable audit trail, allowing radiologists to confirm that their reports were viewed and used appropriately by referring clinicians.While numerous challenges remain, including legal considerations, government regulations, and the environmental impact of blockchain technology, NFTs are poised to play a growing role in healthcare. Diagnostic imaging, often at the forefront of technological innovation in medicine, is well positioned to benefit from the adoption of blockchain-based NFT applications.References:Conti, R. (2022, August 16). What is an NFT? non-fungible tokens explained. Forbes. Retrieved August 29, 2022, from https://www.forbes.com/advisor/investing/cryptocurrency/nft-non-fungible-token/Culbertson, N. (2021, August 6). Council post: The Skyrocketing Volume of Healthcare Data Makes Privacy Imperative. Forbes. Retrieved August 29, 2022, from https://www.forbes.com/sites/forbestechcouncil/2021/08/06/the-skyrocketing-volume-of-healthcare-data-makes-privacy-imperative/?sh=327ba8536555Diaz, N. (n.d.). What nfts need to achieve before healthcare implementation. Becker’s Hospital Review. Retrieved August 29, 2022, from https://www.beckershospitalreview.com/healthcare-information-technology/what-nfts-need-to-achieve-before-healthcare-implementation.htmlHarrison, S. (2022, April 13). Some medical ethicists endorse nfts-here’s why. Scientific American. Retrieved August 29, 2022, from https://www.scientificamerican.com/article/some-medical-ethicists-endorse-nfts-heres-why/HHMGlobal, C. T. (2022, April 11). Content team HHMGlobal. HHM Global B2B Online Platform Magazine. Retrieved August 29, 2022, from https://www.hhmglobal.com/knowledge-bank/news/can-nfts-be-repurposed-for-the-healthcare-industryJones, C. (2021, September 13). Why nfts, crypto and blockchain can help e-health thrive. Cointelegraph. Retrieved August 29, 2022, from https://cointelegraph.com/news/why-nfts-crypto-and-blockchain-can-help-e-health-thriveKhatri, N. (2021, December 8). Beyond Trendy Investments: Three applications of nfts in healthcare and Pharma Marketing. PM360. Retrieved August 29, 2022, from https://www.pm360online.com/beyond-trendy-investments-three-applications-of-nfts-in-healthcare-and-pharma-marketing/Kostick-Quenet, K., Mandl, K. D., Minssen, T., Cohen, I. G., Gasser, U., Kohane, I., & McGuire, A. L. (2022). How nfts could transform Health Information Exchange. Science, 375(6580), 500–502. https://doi.org/10.1126/science.abm2004Limited, V. M. P. (n.d.). AIMEDIS announces the NFT Healthcare Platform. Newsfile. Retrieved August 29, 2022, from https://www.newsfilecorp.com/release/103552/Aimedis-Announces-the-NFT-Healthcare-PlatformMcGuire, A. (2022, February 4). Can NFT technology benefit healthcare? in. Retrieved August 29, 2022, from https://healthcare-in-europe.com/en/news/can-nft-technology-benefit-healthcare.htmlShyam Sabat MD, M. B. A. (2021, April 27). Blockchain - promises for academic radiology. LinkedIn. Retrieved August 29, 2022, from https://www.linkedin.com/pulse/blockchain-promises-academic-radiology-shyam-sabat-md-sabat-mdTagliafico AS, Campi C, Bianca B, et al. Blockchain in radiology research and clinical practice: current trends and future directions. La Radiologia Medica. 2022 Apr;127(4):391-397.YouTube. (2021, September 20). How nfts will revolutionize medicine. YouTube. Retrieved August 29, 2022, from https://www.youtube.com/watch?v=TnhmUltTGo

Mohsen Beikali Soltani, Hugo Bouchard

Abstract Purpose The purpose of this study is to adapt a Bayesian dual‐virtual non‐contrast (VNC) method by integrating prior anatomical knowledge from AI‐based multi‐organ segmentation and to generalize it for spectral photon‐counting CT (PCCT) with an arbitrary number of energy channels. Methods A previously proposed Bayesian VNC method is reformulated for any number of energies and adapted for integration with AI segmentation. TotalSegmentator, an open‐access whole‐body AI segmentation model, is used to provide spatial priors. The method is applied to simulated contrast‐enhanced dual‐energy CT (DECT) and PCCT datasets from eight virtual patients, with and without AI segmentation. Key radiotherapy‐relevant parameters such as electron density () and proton stopping power ratio (SPR) are estimated and compared to ground truth values. Additional results are obtained for non‐contrast scans by setting contrast agent uptake to zero. Results AI‐based segmentation improved the accuracy of parameter estimation for both DECT and PCCT, with a more pronounced effect for PCCT. The combination of high spectral resolution and anatomical priors led to reduced RMS errors in SPR and . Mean absolute water‐equivalent path length (WEPL) errors confirmed the superiority of segmentation‐assisted PCCT over other methods. Conclusion This proof of concept demonstrates a flexible, AI‐assisted Bayesian framework for extracting quantitative information from contrast‐enhanced spectral CT. By integrating AI segmentation and generalizing to PCCT, the method shows improved tissue characterization, suggesting the value of AI in extracting quantitative information beyond DECT. Further validation on clinical datasets is needed. Background Quantitative VNC methods offer the potential to extract radiotherapy‐related parameters from contrast‐enhanced spectral CT without the need for additional non‐contrast imaging. However, the inherently ill‐posed nature of tissue characterization from limited spectral data remains a major limitation, which requires advanced techniques.

Roger T. Tomihama, M. C. Wilkinson, Sharon C. Kiang

Blockchain technology (BCT) enables the building of a distributed decentralized network that securely stores and exchanges unchangeable data, controlled by individual users. In health care, BCT may help streamline interoperability and information transmission while guaranteeing medical record authenticity and safeguarding patient privacy. Possible applications in radiology include patient-controlled image sharing, facilitation of multiinstitutional research, and artificial intelligence integration. Radiologists should stay informed of BCT given its ongoing improvements and unique potential to support the specialty's needs.

Florian van Breevoort, Ali Sair, Matyas Jozsef Doszpod, MARCELO LEAL LOA

No abstract is available for this record.

Giuseppe Rovere, Francesco Bosco, Angelo Miceli, Salvatore Ratano · 10 authors

Blockchain technology has gained popularity since the invention of Bitcoin in 2008. It offers a decentralized and secure system for managing and protecting data. In the healthcare sector, where data protection and patient privacy are crucial, blockchain has the potential to revolutionize various aspects, including patient data management, orthopedic registries, medical imaging, research data, and the integration of Internet of Things (IoT) devices. This manuscript explores the applications of blockchain in orthopedics and highlights its benefits. Furthermore, the combination of blockchain with artificial intelligence (AI), machine learning, and deep learning can enable more accurate diagnoses and treatment recommendations. AI algorithms can learn from large datasets stored on the blockchain, leading to advancements in automated clinical decision-making. Overall, blockchain technology has the potential to enhance data security, interoperability, and collaboration in orthopedics. While there are challenges to overcome, such as adoption barriers and data sharing willingness, the benefits offered by blockchain make it a promising innovation for the field.

Ronghua Xu, Yu Chen, Genshe Chen, Erik Blasch

The rapid development of three-dimensional (3D) acquisition technology based on 3D sensors provides a large volume of data, which is often represented in the form of point clouds. Point cloud representation can preserve the original geometric information along with associated attributes in a 3D space. Therefore, it has been widely adopted in many scene-understanding-related applications such as virtual reality (VR) and autonomous driving. However, the massive amount of point cloud data aggregated from distributed 3D sensors also poses challenges for secure data collection, management, storage, and sharing. Thanks to the characteristics of decentralization and security nature, Blockchain has a great potential to improve point cloud services and enhance security and privacy preservation. Inspired by the rationales behind Software Defined Network (SDN) technology, this paper envisions SAUSA, a blockchain-based authentication network that is capable of recording, tracking, and auditing the access, usage, and storage of 3D point cloud data sets in their life-cycle in a decentralized manner. SAUSA adopts an SDN-enabled point cloud service architecture which allows for efficient data processing and delivery to satisfy diverse Quality-of-Service (QoS) requirements. A blockchain-based authentication framework is proposed to ensure security and privacy preservation in point cloud data acquisition, storage, and analytics. Leveraging smart contracts for digitizing access control policies and point cloud data on the blockchain, data owners have full control of their 3D sensors and point clouds. In addition, anyone can verify the authenticity and integrity of point clouds in use without relying on a third party. Moreover, SAUSA integrates a decentralized storage platform to store encrypted point clouds while recording references of raw data on the distributed ledger. Such a hybrid on-chain and off-chain storage strategy not only improves robustness and availability but also ensures privacy preservation for sensitive information in point cloud applications. A proof-of-concept prototype is implemented and tested on a physical network. The experimental evaluation validates the feasibility and effectiveness of the proposed SAUSA solution.

Alberto Tagliafico, Cristina Campi, Bianca Bignotti, Chandra Bortolotto · 9 authors

Blockchain usage in healthcare, in radiology, in particular, is at its very early infancy. Only a few research applications have been tested, however, blockchain technology is widely known outside healthcare and widely adopted, especially in Finance, since 2009 at least. Learning by history, radiology is a potential ideal scenario to apply this technology. Blockchain could have the potential to increase radiological data value in both clinical and research settings for the patient digital record, radiological reports, privacy control, quantitative image analysis, cybersecurity, radiomics and artificial intelligence.Up-to-date experiences using blockchain in radiology are still limited, but radiologists should be aware of the emergence of this technology and follow its next developments. We present here the potentials of some applications of blockchain in radiology.

Pedro Miguel Martínez-Gironés, Javier Vera-Olmos, Mario Gil-Correa, Ana Ramos · 8 authors

Typically, pseudo-Computerized Tomography (CT) synthesis schemes proposed in the literature rely on complete atlases acquired with the same field of view (FOV) as the input volume. However, clinical CTs are usually acquired in a reduced FOV to decrease patient ionization. In this work, we present the Franken-CT approach, showing how the use of a non-parametric atlas composed of diverse anatomical overlapping Magnetic Resonance (MR)-CT scans and deep learning methods based on the U-net architecture enable synthesizing extended head and neck pseudo-CTs. Visual inspection of the results shows the high quality of the pseudo-CT and the robustness of the method, which is able to capture the details of the bone contours despite synthesizing the resulting image from knowledge obtained from images acquired with a completely different FOV. The experimental Zero-Normalized Cross-Correlation (ZNCC) reports 0.9367 ± 0.0138 (mean ± SD) and 95% confidence interval (0.9221, 0.9512); the experimental Mean Absolute Error (MAE) reports 73.9149 ± 9.2101 HU and 95% confidence interval (66.3383, 81.4915); the Structural Similarity Index Measure (SSIM) reports 0.9943 ± 0.0009 and 95% confidence interval (0.9935, 0.9951); and the experimental Dice coefficient for bone tissue reports 0.7051 ± 0.1126 and 95% confidence interval (0.6125, 0.7977). The voxel-by-voxel correlation plot shows an excellent correlation between pseudo-CT and ground-truth CT Hounsfield Units (m = 0.87; adjusted R2 = 0.91; p < 0.001). The Bland–Altman plot shows that the average of the differences is low (−38.6471 ± 199.6100; 95% CI (−429.8827, 352.5884)). This work serves as a proof of concept to demonstrate the great potential of deep learning methods for pseudo-CT synthesis and their great potential using real clinical datasets.

Fadila Zerka, Visara Urovi, Akshayaa Vaidyanathan, Samir Barakat · 11 authors

The utility of Artificial Intelligence (AI) in healthcare strongly depends upon the quality of the data used to build models, and the confidence in the predictions they generate. Access to sufficient amounts of high-quality data to build accurate and reliable models remains problematic owing to substantive legal and ethical constraints in making clinically relevant research data available offsite. New technologies such as distributed learning offer a pathway forward, but unfortunately tend to suffer from a lack of transparency, which undermines trust in what data are used for the analysis. To address such issues, we hypothesized that, a novel distributed learning that combines sequential distributed learning with a blockchain-based platform, namely Chained Distributed Machine learning C-DistriM, would be feasible and would give a similar result as a standard centralized approach. C-DistriM enables health centers to dynamically participate in training distributed learning models. We demonstrate C-DistriM using the NSCLC-Radiomics open data to predict two-year lung-cancer survival. A comparison of the performance of this distributed solution, evaluated in six different scenarios, and the centralized approach, showed no statistically significant difference (AUCs between central and distributed models), all DeLong tests yielded p -val >0.05. This methodology removes the need to blindly trust the computation in one specific server on a distributed learning network. This fusion of blockchain and distributed learning serves as a proof-of-concept to increase transparency, trust, and ultimately accelerate the adoption of AI in multicentric studies. We conclude that our blockchain-based model for sequential training on distributed datasets is a feasible approach, provides equivalent performance to the centralized approach.

Sébastien Philippe, R.J. Goldston, Alexander Glaser, Francesco d’Errico

Zero-knowledge proofs are mathematical cryptographic methods to demonstrate the validity of a claim while providing no further information beyond the claim itself. The possibility of using such proofs to process classified and other sensitive physical data has attracted attention, especially in the field of nuclear arms control. Here we demonstrate a non-electronic fast neutron differential radiography technique using superheated emulsion detectors that can confirm that two objects are identical without revealing their geometry or composition. Such a technique could form the basis of a verification system that could confirm the authenticity of nuclear weapons without sharing any secret design information. More broadly, by demonstrating a physical zero-knowledge proof that can compare physical properties of objects, this experiment opens the door to developing other such secure proof-systems for other applications.