CONTEXT BASED QUANTUM-INSPIRED IMAGE ENCODING: RECONSTRUCTION, FIDELITY, STABILITY AND CLASSIFICATION TRADE-OFFS

Read full text Summarise with VIRAT
Authors: Sayak Konar, SUBRATA SINHA, Gunjan Mukherjee
Cited by: 0
References: 4

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Quantum-inspired image encodings offer compact visual representations, but their utility for lung histopathology is unclear.This study evaluates Amplitude, FRQI, NEQR, QBIP, and Hybrid-NEQR+RAE on lung carcinoma WSI patches, assessing reconstruction, perceptual stability, and classification.Amplitude achieves PSNR > 45 dB, Hybrid-NEQR+RAE ≈ 43 dB with stable sharpness, exposure, colour, and noise metrics.While NEQR and QBIP deliver the best diagnostic separation with macro-F1 ≈ 49% and 47%,Hybrid-NEQR+RAE collapses to ≈ 22% F1 due to class bias.Confusion matrices confirm that high-fidelity hybrid reconstruction suppresses discriminative variance.The study highlights that medical diagnosis demands task-aware quantum encoding.

Fields of Study & Subjects

Quantum Computing Algorithms and Architecture AI in cancer detection Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
Science and Culture
Volume
92
Publication date
17 March 2026
Language
EN