[Paper Review] Access Control Management for Computer-Aided Diagnosis Systems using Blockchain

Mayra Samaniego, Sara Hosseinzadeh Kassani+2 more|arXiv (Cornell University)|Jun 20, 2020

Brain Tumor Detection and Classification10 references4 citations

TL;DR

This paper proposes a blockchain-based access control management system for multi-institutional Computer-Aided Diagnosis (CAD) systems using a consortium Ethereum network. The solution enables decentralized, auditable, and fine-grained access control for medical image data, ensuring data integrity and compliance in distributed research environments with a prototype DApp implementation demonstrating feasibility and security.

ABSTRACT

Computer-Aided Diagnosis (CAD) systems have emerged to support clinicians in interpreting medical images. CAD systems are traditionally combined with artificial intelligence (AI), computer vision, and data augmentation to evaluate suspicious structures in medical images. This evaluation generates vast amounts of data. Traditional CAD systems belong to a single institution and handle data access management centrally. However, the advent of CAD systems for research among multiple institutions demands distributed access management. This research proposes a blockchain-based solution to enable distributed data access management in CAD systems. This solution has been developed as a distributed application (DApp) using Ethereum in a consortium network.

Motivation & Objective

• To address the limitations of centralized access control in multi-institutional CAD systems, where data sharing across institutions lacks transparency and auditability.
• To enable secure, decentralized, and auditable access control for medical image data used in AI-driven diagnostic research.
• To design and implement a distributed application (DApp) on a consortium Ethereum blockchain for fine-grained access control in CAD workflows.
• To ensure data integrity, confidentiality, and compliance with privacy regulations in collaborative medical imaging research.
• To demonstrate the feasibility of blockchain technology in managing access control for sensitive medical data in distributed CAD environments.

Proposed method

• The system uses a permissioned Ethereum consortium blockchain to manage access control policies across multiple institutions.
• Access control is implemented via smart contracts that enforce role-based access and data usage policies on medical image datasets.
• Each access request is recorded on the blockchain, creating an immutable audit log for compliance and accountability.
• The DApp integrates with existing CAD systems to mediate access requests based on user roles and data sensitivity levels.
• The architecture supports data provenance tracking and ensures that only authorized users can access specific medical images or model outputs.
• The solution leverages cryptographic hashing to verify data integrity and prevent unauthorized modifications.

Experimental results

Research questions

• RQ1 How can access control for medical image data be decentralized while maintaining security and compliance in multi-institutional CAD systems?
• RQ2 What role can a blockchain-based system play in enabling auditable and transparent access management for AI-driven diagnostic workflows?
• RQ3 Can a consortium Ethereum network effectively support real-time access control decisions in a clinical research environment?
• RQ4 How does the proposed system ensure data integrity and prevent unauthorized access in a distributed CAD setting?
• RQ5 What are the practical implications of using smart contracts for managing fine-grained access policies in medical image analysis?

Key findings

• The proposed blockchain-based access control system successfully enables decentralized, auditable, and fine-grained access management across multiple institutions.
• The implementation as a DApp on a consortium Ethereum network demonstrates feasibility for real-world deployment in medical research settings.
• All access requests and decisions are immutably logged on the blockchain, ensuring end-to-end auditability and compliance.
• The system supports role-based access control with cryptographic verification, reducing the risk of data leakage or unauthorized access.
• The prototype shows that blockchain can effectively manage access control for sensitive medical image data without compromising performance or scalability in a research context.
• The solution enhances trust among collaborating institutions by providing a transparent and verifiable access control mechanism.