Scholarlink

<p>Structured light beams carrying orbital angular momentum (OAM), such as Laguerre–Gaussian modes, are promising tools for high-capacity optical communications and advanced biomedical imaging. However, multiple scattering in turbid media distorts their phase and amplitude, complicating the retrieval of topological charge. Using experimentally acquired three-channel intensity and interference measurements from 25 independent acquisition sessions, we evaluate signed 11-class and unsigned 6-class topological-charge classification with a matched CNN baseline, an Angular Fourier Transform CNN (AFT-CNN), and a pretrained ResNet18 baseline. The best-performing models achieve high accuracy in the low-scattering regime, with the CNN and ResNet18 remaining near 95% at <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(z/l^* = 2,\)</EquationSource></InlineEquation> but accuracy drops sharply around <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(z/l^* \approx 4.\)</EquationSource></InlineEquation> These results indicate that sign-dependent OAM information can survive multiple scattering in the low-scattering regime and can be decoded from three-channel measurements with deep learning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding orbital angular momentum in turbid tissue-like scattering medium with deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月25日

查看全文
  • Avraham Yosovich,
  • Anton Sdobnov,
  • Alexander Doronin,
  • Alexander Bykov,
  • Igor Meglinski,
  • Zeev Zalevsky

摘要

Structured light beams carrying orbital angular momentum (OAM), such as Laguerre–Gaussian modes, are promising tools for high-capacity optical communications and advanced biomedical imaging. However, multiple scattering in turbid media distorts their phase and amplitude, complicating the retrieval of topological charge. Using experimentally acquired three-channel intensity and interference measurements from 25 independent acquisition sessions, we evaluate signed 11-class and unsigned 6-class topological-charge classification with a matched CNN baseline, an Angular Fourier Transform CNN (AFT-CNN), and a pretrained ResNet18 baseline. The best-performing models achieve high accuracy in the low-scattering regime, with the CNN and ResNet18 remaining near 95% at \(z/l^* = 2,\) but accuracy drops sharply around \(z/l^* \approx 4.\) These results indicate that sign-dependent OAM information can survive multiple scattering in the low-scattering regime and can be decoded from three-channel measurements with deep learning.