Back to all papers

Spatially identifying regions of tumor recurrence in patients with suspected recurrent glioma using physiologic MRI and machine learning.

June 25, 2026pubmed logopapers

Authors

Ellison J,Tran N,Luks TL,Singh P,Jakary A,Ngan T,Cluceru J,Phillips JJ,Li Y,Molinaro AM,Pedoia V,Shai A,Nair D,Villanueva-Meyer JE,Berger MS,Hervey-Jumper SL,Aghi M,Chang SM,Lupo JM

Affiliations (8)

  • Department of Radiology and Biomedical Imaging, UCSF, San Francisco, CA, USA.
  • Center for Intelligent Imaging, UCSF, San Francisco, CA, USA.
  • UCSF-UC Berkeley Graduate Program in Bioengineering, San Francisco and Berkeley, CA, USA.
  • Department of Neurological Surgery, University of California, San Francisco, San Francisco, CA, USA.
  • Department of Pathology, University of California, San Francisco, San Francisco, CA, USA.
  • Department of Radiology and Biomedical Imaging, UCSF, San Francisco, CA, USA. [email protected].
  • Center for Intelligent Imaging, UCSF, San Francisco, CA, USA. [email protected].
  • UCSF-UC Berkeley Graduate Program in Bioengineering, San Francisco and Berkeley, CA, USA. [email protected].

Abstract

Despite prior success in classifying recurrent glioma noninvasively with multi-parametric MRI and AI, clinical applicability has yet to be demonstrated due to a lack of robust model evaluation and spatial preservation of tumor characteristics. This study develops, robustly evaluates, and clinically validates an interpretable model for predicting recurrent tumors from spatially varying, histopathologically-confirmed tissue samples. Machine learning models were developed using 254 pre-surgical multi-parametric MRI patches surrounding coordinates of tissue samples taken during recurrent surgery. A test AUROC of 0.74 ± 0.08 for distinguishing recurrent tumors, and 0.99 ± 0.01 for normal-appearing brain, demonstrated the feasibility of spatially mapping heterogeneity. Important features were consistent with current literature, and uncertainty was correlated with model failures (p ≤ 0.05). Volumetrics derived from prediction maps of recurrent tumors generated using a separate cohort of 56 patients with recurrent high-grade gliomas were significantly associated with survival. These results demonstrate a step towards clinical applicability of spatially mapping glioma recurrence.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.