Skip to content

Deep Learning-Assisted Terahertz Metasurface Biosensing for Rapid Ex Vivo Molecular Assessment of Diffuse Glioma Frozen Sections.

Sep 2026 · ACS Sensors · 0 citations · 41 references
Medicine

TL;DR

These findings support metasurface-enhanced THz sensing with full-spectrum deep learning as a rapid ex vivo adjunct for molecularly relevant assessment of diffuse glioma specimens.

Abstract

Molecularly informed maximal safe resection of diffuse glioma requires rapid assessment of surgical specimens, but conventional molecular assays are not suited to repeated ex vivo testing. We developed a deep learning-assisted terahertz (THz) metasurface workflow in which a K/I-patterned aluminum metasurface both serves as the cryosection-receiving substrate and converts tissue-induced dielectric perturbations into multi-resonance THz responses. After preliminary thickness optimization, 50 μm sections were prepared directly on the active sensing area. The study included 53 patients, 59 tissue specimens, and 590 nested block-level spectra. A SEResNet1D model analyzed the complete 0.50-1.12 THz transmittance curve using a patient/specimen-grouped hold-out design. Distinct from prior conventional THz molecular studies and metasurface studies focused mainly on tumor-normal contrast, cultured cells, or animal imaging, the workflow integrates direct on-metasurface cryosectioning, resonant multi-mode THz transduction, full-spectrum deep learning, and leakage-aware grouped validation for five-class molecularly relevant assessment of human diffuse glioma frozen sections. Across five independently initialized runs, SEResNet1D achieved a mean five-class accuracy of 97.48 ± 0.87%. One THz spectrum required approximately 8 s, and a ready-to-scan tissue-sensor unit could be prepared in approximately 3 min. These findings support metasurface-enhanced THz sensing with full-spectrum deep learning as a rapid ex vivo adjunct for molecularly relevant assessment of diffuse glioma specimens.

View source

Similar papers

Open access Oct 2026

Quad-Band Terahertz Metamaterial Sensor Based on Dual Near-Perfect Absorption for Fingerprint Identification of Cancer Cells

Early and accurate cancer diagnosis remains a critical challenge in clinical oncology due to the limitations of traditional, destructive labeling methods. To address this gap, this study proposes a novel, label-free quad-band terahertz (THz) metamaterial biosensor designed for high-precision fingerprint identification...

Aykut Coşkun, A. Özmen · 0 citations
Review Oct 2026

Point terahertz source technology for multiscale bio-imaging and sensing

Terahertz (THz) biophotonics offers unique capabilities for label-free and non-destructive analysis of biological samples. However, its widespread application has been limited by the diffraction limit of THz waves and their strong absorption by water. To address these challenges, we developed a point THz source generat...

K. Serita · 0 citations
Open access 2027

Deep-Learning-Assisted Inverse Design of Pixelated Ultra-Wideband Terahertz Metasurface Absorbers With Refractive-Index Sensing Capability

Terahertz (THz) metasurface absorbers have attracted significant interest for wideband energy harvesting, electromagnetic stealth, and sensing applications. However, the design of ultra-wideband THz absorbers still relies heavily on empirical optimization and time-consuming full-wave simulations, particularly when high...

Pin Wen, Jin-Yu Liu, Kun Zhan et al. · 0 citations
Review Oct 2026

Deep Learning and Engineered Biomaterials-Enhanced Imaging-Guided Cancer Immunotherapy.

The clinical success of immunotherapies is hindered by the absence of robust methodologies for the early and accurate assessment of antitumor immune responses. Integrating engineered biomaterials with artificial intelligence (AI)-driven molecular imaging technology offers a powerful approach for predicting immune effic...

Kai-Wei Lv, Bin Li, Bing Xiao et al. · 0 citations
#edge computing Open access Sep 2026

Multiplex K‑Edge Nanoprobe Imaging Enables 3D Volumetric Molecular Phenotyping of Human Hematoma Membranes

Spectral photon-counting computed tomography (SPCCT) enables material-resolved imaging through K-edge discrimination, yet its application to multiplexed molecular mapping of human surgical specimens remains underexplored. Here, we report a clinically relevant multiplex K-edge imaging strategy and demonstrate its utilit...

Nivetha Gunaseelan, Pranay Saha, Moumita Moitra et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.