Encryption Security Analysis for Medical MRI Images with Blockchain Verification

Experimental results on a DICOM-compliant system for secure medical image transfer demonstrate high reconstruction quality (PSNR: 46–51 dB, SSIM: 0.92–0.97) and strong cryptographic properties (NPCR: 99.6%, UACI: 33.46%). The 5.5 KB dataset, authored by Bicky Yadav and last updated in May 2026, contains results from testing a unified pipeline integrating compression, hyperchaotic encryption, and blockchain-based provenance on clinical MRI and susceptibility-weighted imaging data.

Use Cases

• Benchmarking image compression and encryption techniques based on reported PSNR, SSIM, NPCR, and UACI metrics.
• Evaluating post-quantum key establishment methods for medical data based on the described NIST-standard ML-KEM and HKDF usage.
• Studying blockchain applications for verifiable data provenance in healthcare based on the permissioned blockchain metadata recording.
• Analyzing the trade-offs between compression ratio and diagnostic quality in medical imaging based on the described -regularized near-lossless compression.

Strengths

• Specific performance metrics are provided, including PSNR (46–51 dB), SSIM (0.92–0.97), NPCR (99.6%), and UACI (33.46%).
• The dataset is associated with a detailed technical description of a novel, integrated security system for medical images.
• It is shared under a permissive CC-BY-4.0 license, allowing for broad reuse.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope, likely containing summary results rather than raw image data.
• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The evaluation focuses specifically on MRI-based modalities, which may limit generalizability to other medical imaging types.

Provenance

Source

Bicky Yadav via figshare

Collection Method

Likely contains experimental results from testing the described DICOM-compliant security system.

Freshness

Last updated 2026-05-08 17:40:55; freshness should be verified.