EUVIMEDEUVIMED entdecken
Open Access

Optical microscopy predictions of focal recurrence in glioblastoma

Sanjeev Herr iD, Niels Olshausen iD, Melike Pekmezci iD, Jasleen Kaur, Youssef Sibih iD, Vardhaan Ambati iD, Abraham Dada iD, Katie Scotford, Amit Persad, Thiebaud Picart iD, Akhil Kondepudi, Gabrielle Malte und 14 weitere

Science Advances · 2026

DOI: 10.1126/sciadv.aec8202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2026. Verfasst von Sanjeev Herr und 25 weiteren Autor:innen. Beteiligte Einrichtung: Drexel University College of Medicine, Philadelphia, PA 19129, USA. Hauptthemen laut MEDLINE: Glioblastoma, Neoplasm Recurrence, Local, Brain Neoplasms, Microscopy. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NIGMS NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A hallmark of glioblastoma (GBM) is disease recurrence that occurs in all patients despite resection, radiation, and chemotherapy. A critical challenge in GBM treatment is the management of recurrent disease for which no standard of care exists. Predicting the location of GBM recurrence may improve the efficiency of advanced-stage therapies. We present an artificial intelligence (AI)–based model to predict the recurrence risk of unprocessed surgical tissues at initial resection. AI-informed label-free optical microscopy was used to generate a normalized tumor infiltration value (AI-infiltration) for optical images of samples taken from resection cavity margins. These values, in combination with clinical, radiographic, and molecular variables, were used to build a predictive model of focal recurrence. In a cohort of 80 patients, comprising 367 samples and 133,454 unique images, GBM infiltration was significantly higher in margin samples from recurrent sites ( P = 0.03) compared with those from nonrecurrent sites. A random forest machine learning classifier predicted site recurrence with an average area under the receiver operating characteristic curve of 87% ± 10.0 for the training cohort and 80% (95% confidence interval: 0.64 to 0.97) for the validation cohort. AI-infiltration was the strongest contributor to recurrence prediction, outperforming tumor molecular features. Model performance remained high regardless of tumor location, resulting in random forest model predictions of recurrence at 5 and 10 millimeters of each sample. These findings represent the potential of AI to predict sites of tumor recurrence, thereby improving accessibility to targeted, precision, and multimodal therapy for the highest-risk areas of disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlioblastomaNeoplasm Recurrence, LocalBrain NeoplasmsMicroscopyHumansArtificial IntelligenceRandom ForestFemaleROC CurveMachine Learning

Autor:innen und Institutionen

  • Drexel University College of Medicine, Philadelphia, PA 19129, USA.
  • Department of Neurological Surgery, University of California, San Francisco, San Francisco, CA 94143, USA.
  • Department of Pathology, University of California, San Francisco, San Francisco, CA 94143, USA.
  • Machine Learning in Neurosurgery Laboratory, Department of Neurosurgery, University of Michigan, Ann Arbor, MI 48105, USA.
  • Department of Neurosurgery, Medical University of Vienna, Vienna, Austria.
  • Department of Neurology, University of California, San Francisco, San Francisco, CA 94143, USA.

ORCID-Profile: Sanjeev Herr, Niels Olshausen, Melike Pekmezci, Youssef Sibih, Vardhaan Ambati, Abraham Dada, Thiebaud Picart, Albert Kim, Jacob Young, Mitchel S Berger, Ammar Mallouhi, Barbara Kiesel, Georg Widhalm, Lisa Körner, Madhumita Sushil, Todd Hollon, Shawn L Hervey-Jumper

Förderung

  • NCI NIH HHS
  • NIGMS NIH HHS
  • NINDS NIH HHS
  • NIH Office of the Director
  • Shurl and Kay Curci Foundation
  • NINDS
  • Ian’s Friends Foundation
  • Chan Zuckerberg Foundation (CZI) Advancing Imaging

Zitieren

APA

Herr, S., Olshausen, N., Pekmezci, M., Kaur, J., Sibih, Y., Ambati, V., Dada, A., Scotford, K., Persad, A., Picart, T., Kondepudi, A., Malte, G., Vulakh, G., Pechmann, J., Makolli, J., Oberheim-Bush, N. A., Kim, A., Young, J., Berger, M. S., …, & Hervey-Jumper, S. L. (2026). Optical microscopy predictions of focal recurrence in glioblastoma. Science Advances. https://doi.org/10.1126/sciadv.aec8202

Vancouver

Herr S, Olshausen N, Pekmezci M, Kaur J, Sibih Y, Ambati V, et al. Optical microscopy predictions of focal recurrence in glioblastoma. Science Advances. 2026. doi:10.1126/sciadv.aec8202

BibTeX
@article{Herr2026,
  author = {Herr, Sanjeev and Olshausen, Niels and Pekmezci, Melike and Kaur, Jasleen and Sibih, Youssef and Ambati, Vardhaan and Dada, Abraham and Scotford, Katie and Persad, Amit and Picart, Thiebaud and Kondepudi, Akhil and Malte, Gabrielle and Vulakh, Gabriella and Pechmann, Johanna and Makolli, Jessica and Oberheim-Bush, Nancy Ann and Kim, Albert and Young, Jacob and Berger, Mitchel S and Mallouhi, Ammar and Kiesel, Barbara and Widhalm, Georg and Körner, Lisa and Sushil, Madhumita and Hollon, Todd and Hervey-Jumper, Shawn L},
  title = {Optical microscopy predictions of focal recurrence in glioblastoma},
  journal = {Science Advances},
  year = {2026},
  doi = {10.1126/sciadv.aec8202}
}
Kostenlos starten →