Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Provenance-Driven Reliable Semantic Medical Image Vector Reconstruction via Lightweight Blockchain-Verified Latent Fingerprints

Mohsin Rasheed, Abdullah Al-Mamun

TL;DR

Prosima tackles reliable medical image reconstruction under corruption while providing tamper-evident provenance. It fuses semantic-guided reconstruction with latent fingerprints anchored on a lightweight scale-free blockchain and employs deterministic shard fragmentation for scalable verification. Empirical results on BraTS 2020 show superior structural fidelity, semantic alignment, and 100% provenance verification with low latency, outperforming pixel-only and non-semantic baselines. The approach promises improved diagnostic confidence and regulatory compliance by delivering auditable, semantically faithful reconstructions in distributed clinical workflows.

Abstract

Medical imaging is essential for clinical diagnosis, yet real-world data frequently suffers from corruption, noise, and potential tampering, challenging the reliability of AI-assisted interpretation. Conventional reconstruction techniques prioritize pixel-level recovery and may produce visually plausible outputs while compromising anatomical fidelity, an issue that can directly impact clinical outcomes. We propose a semantic-aware medical image reconstruction framework that integrates high-level latent embeddings with a hybrid U-Net architecture to preserve clinically relevant structures during restoration. To ensure trust and accountability, we incorporate a lightweight blockchain-based provenance layer using scale-free graph design, enabling verifiable recording of each reconstruction event without imposing significant overhead. Extensive evaluation across multiple datasets and corruption types demonstrates improved structural consistency, restoration accuracy, and provenance integrity compared with existing approaches. By uniting semantic-guided reconstruction with secure traceability, our solution advances dependable AI for medical imaging, enhancing both diagnostic confidence and regulatory compliance in healthcare environments.

Provenance-Driven Reliable Semantic Medical Image Vector Reconstruction via Lightweight Blockchain-Verified Latent Fingerprints

TL;DR

Prosima tackles reliable medical image reconstruction under corruption while providing tamper-evident provenance. It fuses semantic-guided reconstruction with latent fingerprints anchored on a lightweight scale-free blockchain and employs deterministic shard fragmentation for scalable verification. Empirical results on BraTS 2020 show superior structural fidelity, semantic alignment, and 100% provenance verification with low latency, outperforming pixel-only and non-semantic baselines. The approach promises improved diagnostic confidence and regulatory compliance by delivering auditable, semantically faithful reconstructions in distributed clinical workflows.

Abstract

Medical imaging is essential for clinical diagnosis, yet real-world data frequently suffers from corruption, noise, and potential tampering, challenging the reliability of AI-assisted interpretation. Conventional reconstruction techniques prioritize pixel-level recovery and may produce visually plausible outputs while compromising anatomical fidelity, an issue that can directly impact clinical outcomes. We propose a semantic-aware medical image reconstruction framework that integrates high-level latent embeddings with a hybrid U-Net architecture to preserve clinically relevant structures during restoration. To ensure trust and accountability, we incorporate a lightweight blockchain-based provenance layer using scale-free graph design, enabling verifiable recording of each reconstruction event without imposing significant overhead. Extensive evaluation across multiple datasets and corruption types demonstrates improved structural consistency, restoration accuracy, and provenance integrity compared with existing approaches. By uniting semantic-guided reconstruction with secure traceability, our solution advances dependable AI for medical imaging, enhancing both diagnostic confidence and regulatory compliance in healthcare environments.

Paper Structure

This paper contains 33 sections, 5 equations, 3 figures, 5 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. Motivation
  3. Proposed Approach and Challenges
  4. Our Contributions
  5. Related Work
  6. Deep Learning for Medical Image Reconstruction
  7. Diffusion/Score-Based Priors for Inverse Problems
  8. Diffusion/Score-Based Priors for Inverse Problems
  9. Semantic Guidance in Medical Imaging
  10. Provenance, Trustworthy AI, and Blockchain in Imaging
  11. Limitations of Current Solutions
  12. Methodology
  13. Prosima System Overview
  14. Problem Definition
  15. Training Objective
  16. ...and 18 more sections

Figures (3)

  • Figure 1: Proposed Prosima framework for semantic-aware image reconstruction powered by lightweight blockchain ledger equipped with scale-free graph mechanism and geographic fragmentation technique.
  • Figure 2: Visual fidelity achieved by the proposed Prosima framework on three different representative corrupted brain tumor images.
  • Figure 3: Blockchain throughput and latency scalability of Prosima.