Real‐Time High‐Definition Hyperspectral Endoscopy via Spatial‐Temporal Low‐Frequency‐Stochastic Spectral Encoding
Open Access
- 15 January 2026
- journal article
- Published by Wiley in Advanced Science
- Vol. 13 (16) , e17746
Abstract
Hyperspectral endoscopy enables minimally invasive visualization of both structural and compositional information, offering promising potential for the accurate assessment of in vivo physiological and pathological conditions. However, current hyperspectral endoscopy suffers from low frame rate, hindering the clear capture of in vivo tissues in motion, restricting in vivo diagnostics, efficacy assessment, or risk monitoring during minimally invasive procedures. Here we propose a hyperspectral endoscopy by developing a spatial‐temporal spectral encoding approach based on low‐frequency stochastic filters combined with an encoding‐guided spectral attention network (ESANet) to reconstruct the hyperspectral image with low latency. A prototype system is developed to achieve real‐time frame rate (20 Hz), high‐definition resolution (full pixels), 67 spectral channels spanning 420–750 nm. It can overcome the continuous motion of in vivo tissue to provide hyperspectral images with fine superficial features, including capillary as small as around 37 µm in diameter, reveal the distinct spectra characteristics for diverse types of organs, and enable visualization of rapid and subtle compositional changes in two representative processes: photodynamic therapy and hepatic ischemia. With minimal hardware modifications, the proposed scheme provides a cost‐efficient and easily adaptable solution for hyperspectral endoscopy as well as broader application scenarios.Keywords
Funding Information
- Key Technologies Research and Development Program (2024YFF1206703)
- National Natural Science Foundation of China (62020106002)
- National Natural Science Foundation of China (T2293751)
- National Natural Science Foundation of China (T2293752)
- National Natural Science Foundation of China (92250304)
- Natural Science Foundation of Zhejiang Province (LR23F050001)
This publication has 33 references indexed in Scilit:
- High‐Speed Hyperspectral Imaging for Near Infrared Fluorescence and Environmental MonitoringAdvanced Science, 2025
- PSF-engineered snapshot full-Stokes polarizing-spectral-imaging via metasurface with reciprocally encoded anisotropic detour phaseOptics & Laser Technology, 2024
- NIR-II imaging-guided precise photodynamic therapy for augmenting tumor-starvation therapy by glucose metabolism reprogramming interferenceScience Bulletin, 2024
- High-precision hemoglobin detection based on hyperspectral reconstruction of RGB imagesBiomedical Signal Processing and Control, 2024
- Ultraspectral Imaging Based on Metasurfaces with Freeform Shaped Meta‐AtomsLaser & Photonics Reviews, 2022
- High‐Throughput, Label‐Free and Slide‐Free Histological Imaging by Computational Microscopy and Unsupervised LearningAdvanced Science, 2021
- First experience in clinical application of hyperspectral endoscopy for evaluation of colonic polypsJournal of Biophotonics, 2021
- Deep‐Learned Broadband Encoding Stochastic Filters for Computational Spectroscopic InstrumentsAdvanced Theory and Simulations, 2021
- Tissue classification of oncologic esophageal resectates based on hyperspectral dataInternational Journal of Computer Assisted Radiology and Surgery, 2019
- Evaluation of hyperspectral imaging (HSI) for the measurement of ischemic conditioning effects of the gastric conduit during esophagectomySurgical Endoscopy, 2019