Pengcheng Jia, Sida Gao, Ziyang Li, Zhengyu Wu, Guancheng Huang, Yao Wu, Yutong Li, Shutian Liu, Jinghan Li, Zhengjun Liu
{"title":"Physics-embedded neural state-space module for single-shot lens-free on-chip microscopy.","authors":"Pengcheng Jia, Sida Gao, Ziyang Li, Zhengyu Wu, Guancheng Huang, Yao Wu, Yutong Li, Shutian Liu, Jinghan Li, Zhengjun Liu","doi":"10.1364/OL.571248","DOIUrl":null,"url":null,"abstract":"<p><p>Lens-free on-chip microscopy (LFOCM) enables large-field-of-view, high-throughput quantitative imaging by capturing diffraction holograms directly at the sensor plane, eliminating the need for bulky optics and mechanical scanning. Conventional reconstruction pipelines, however, suffer from inherent noise amplification due to their primary reliance on physics-based priors. To overcome this limitation, we developed a physics-embedded neural state-space framework that incorporates diffraction physics for single-shot LFOCM reconstruction. This physics-constrained approach integrates a dual-branch architecture that combines local inductive bias with global modeling, enabling unsupervised recovery of high-fidelity quantitative amplitude and phase distributions. Comprehensive validation demonstrates state-of-the-art noise robustness and reconstruction fidelity, achieving simultaneous artifact suppression and resolution preservation.</p>","PeriodicalId":19540,"journal":{"name":"Optics letters","volume":"50 20","pages":"6357-6360"},"PeriodicalIF":3.3000,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics letters","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1364/OL.571248","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Lens-free on-chip microscopy (LFOCM) enables large-field-of-view, high-throughput quantitative imaging by capturing diffraction holograms directly at the sensor plane, eliminating the need for bulky optics and mechanical scanning. Conventional reconstruction pipelines, however, suffer from inherent noise amplification due to their primary reliance on physics-based priors. To overcome this limitation, we developed a physics-embedded neural state-space framework that incorporates diffraction physics for single-shot LFOCM reconstruction. This physics-constrained approach integrates a dual-branch architecture that combines local inductive bias with global modeling, enabling unsupervised recovery of high-fidelity quantitative amplitude and phase distributions. Comprehensive validation demonstrates state-of-the-art noise robustness and reconstruction fidelity, achieving simultaneous artifact suppression and resolution preservation.
期刊介绍:
The Optical Society (OSA) publishes high-quality, peer-reviewed articles in its portfolio of journals, which serve the full breadth of the optics and photonics community.
Optics Letters offers rapid dissemination of new results in all areas of optics with short, original, peer-reviewed communications. Optics Letters covers the latest research in optical science, including optical measurements, optical components and devices, atmospheric optics, biomedical optics, Fourier optics, integrated optics, optical processing, optoelectronics, lasers, nonlinear optics, optical storage and holography, optical coherence, polarization, quantum electronics, ultrafast optical phenomena, photonic crystals, and fiber optics. Criteria used in determining acceptability of contributions include newsworthiness to a substantial part of the optics community and the effect of rapid publication on the research of others. This journal, published twice each month, is where readers look for the latest discoveries in optics.