AI-driven label-free Raman spectromics for intraoperative spinal tumor assessment - Summary - MDSpire

AI-driven label-free Raman spectromics for intraoperative spinal tumor assessment

  • By

  • David Reinecke

  • Nina Müller

  • Anna-Katharina Meissner

  • Gina Fürtjes

  • Lili Leyer

  • Claire Wang

  • Adrian Ion-Margineanu

  • Nader Maarouf

  • Andrew Smith

  • Todd C. Hollon

  • Cheng Jiang

  • Xinhai Hou

  • Abdulkader Al-Shughri

  • Lisa I. Körner

  • Georg Widhalm

  • Thomas Roetzer-Pejrimovsky

  • Matija Snuderl

  • Sandra Camelo-Piragua

  • John G. Golfinos

  • Roland Goldbrunner

  • Daniel A. Orringer

  • Niklas von Spreckelsen

  • Volker Neuschmelting

  • March 17, 2026

  • 0 min

Share

Objective:

To develop and validate SpineXtract, an innovative AI-powered system for rapid intraoperative spinal tumor diagnosis using stimulated Raman histology (SRH).

Key Findings:
  • SpineXtract achieved a 92.9% macro-average balanced accuracy (95% CI: 85.5–98.2) within 5 minutes.
  • Tumor-specific accuracy ranged from 84.2% to 98.6%, with confidence intervals provided.
  • Performance remained consistent across institutions with macro balanced accuracy between 91.4% and 92.0%.
  • SpineXtract outperformed existing brain tumor classifiers by 15.6%.
Interpretation:

The results indicate that SpineXtract can facilitate rapid and accurate intraoperative diagnosis of spinal tumors, potentially transforming surgical workflows by reducing diagnosis time and reliance on specialized expertise.

Limitations:
  • The study was conducted using existing SRH datasets, which may not fully represent real-time surgical conditions, potentially affecting the applicability of results.
  • The cohort was limited to 44 patients, which may affect generalizability and the robustness of the findings.
Conclusion:

SpineXtract demonstrates significant potential for improving intraoperative diagnostics in spinal tumor surgeries, offering a faster and more accurate alternative to traditional methods, which could lead to better patient outcomes.

Original Source(s)

AI-driven label-free Raman spectromics for intraoperative spinal tumor assessment

  • by David Reinecke, Nina Müller, Anna-Katharina Meissner, Gina Fürtjes, Lili Leyer, Claire Wang, Adrian Ion-Margineanu, Nader Maarouf, Andrew Smith, Todd C. Hollon, Cheng Jiang, Xinhai Hou, Abdulkader Al-Shughri, Lisa I. Körner, Georg Widhalm, Thomas Roetzer-Pejrimovsky, Matija Snuderl, Sandra Camelo-Piragua, John G. Golfinos, Roland Goldbrunner, Daniel A. Orringer, Niklas von Spreckelsen, Volker Neuschmelting

  • March 17, 2026

Related Content

Equity and representation in oncology clinical evidence for FDA-approved treatments and the impact of COVID-19

Continuity of Cancer Treatment Amidst the 2026 Gulf Regional Conflict: Insights and a Resilience Model from Gulf States

Mapping Lipid Rewiring During Drug-Induced Cell Death

Fiber-based imaging platform reveals nanoscale heterogeneity and drug-specific metabolic fingerprints in cancer cells

  • March 31, 2026

  • 2 min