Scholarlink

<p>This work presents a terahertz (THz) biosensor based on a hybrid graphene–black phosphorus (BP) structure for early breast cancer detection. The proposed device employs a compact square split-ring resonator with a central sensing region to maximize electromagnetic field interaction with biological samples. Cancer discrimination is achieved through resonance frequency shifts induced by refractive index variations of healthy and malignant tissues. Sensitivity is quantified in THz/RIU and further evaluated using the figure of merit (FOM) to assess spectral resolution. To enhance sensing performance, a Random Forest regression model is integrated with full-wave WCIP electromagnetic simulations to optimize the graphene chemical potential and BP electron doping concentration. Under optimal conditions, the sensor achieves sensitivities of 20.4&#xa0;THz/RIU for healthy cells and 24.6&#xa0;THz/RIU for cancerous cells, with a FOM of 21.52&#xa0;RIU<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(^{-1}\)</EquationSource> </InlineEquation>. The synergistic combination of tunable 2D materials and machine learning-driven optimization enables high sensitivity while maintaining strong spectral selectivity. Owing to its structural simplicity, high performance, and compatibility with scalable fabrication techniques, the proposed biosensor demonstrates strong potential for advanced THz biomedical diagnostics.</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

Artificial Intelligence-Driven Optimization of Graphene–Black Phosphorus Terahertz Biosensor for Breast Cancer Diagnosis

  • 期刊论文

  • 发表日期：

    2026年3月24日

查看全文
  • Hamza Wertani,
  • Hamza Ben Krid,
  • Aymen Hlali,
  • Hassen Zairi

摘要

This work presents a terahertz (THz) biosensor based on a hybrid graphene–black phosphorus (BP) structure for early breast cancer detection. The proposed device employs a compact square split-ring resonator with a central sensing region to maximize electromagnetic field interaction with biological samples. Cancer discrimination is achieved through resonance frequency shifts induced by refractive index variations of healthy and malignant tissues. Sensitivity is quantified in THz/RIU and further evaluated using the figure of merit (FOM) to assess spectral resolution. To enhance sensing performance, a Random Forest regression model is integrated with full-wave WCIP electromagnetic simulations to optimize the graphene chemical potential and BP electron doping concentration. Under optimal conditions, the sensor achieves sensitivities of 20.4 THz/RIU for healthy cells and 24.6 THz/RIU for cancerous cells, with a FOM of 21.52 RIU \(^{-1}\) . The synergistic combination of tunable 2D materials and machine learning-driven optimization enables high sensitivity while maintaining strong spectral selectivity. Owing to its structural simplicity, high performance, and compatibility with scalable fabrication techniques, the proposed biosensor demonstrates strong potential for advanced THz biomedical diagnostics.