About

John G. Golfinos, MD, is a professor in the Department of Neurosurgery at NYU Grossman School of Medicine and also holds a professorship in the Department of Otolaryngology-Head and Neck Surgery at the same institution. He is the Gray Foundation Chair of Neurosurgery, Co-Director of the Brain Tumor Center at Perlmutter Cancer Center, and Chair of the Department of Neurosurgery. Dr. Golfinos specializes in neurosurgery with a focus on brain tumors, including benign and cancerous tumors that can occur in the brain. He has devoted a significant part of his career to researching neurofibromatosis type 2, a genetic disease that causes complex tumors to grow in the brain and spinal cord, affecting nerves responsible for hearing and balance. He is also at the forefront of stereotactic surgery, which allows for precise viewing and removal of brain tumors during surgery. Dr. Golfinos has been recognized as one of America's top doctors by Castle Connolly for more than 10 years. He is the founder of NYU Langone Gamma Knife Radiosurgery and has contributed extensively to the field of neurosurgery through his research and clinical practice.

Research topics

• Medicine
• Internal medicine
• Biology
• Pathology
• Oncology
• Genetics
• Medical physics
• Cancer research
• Radiology
• Bioinformatics
• Nuclear medicine

Selected publications

• Localization and Performance of Auditory Brainstem Implants Based on MRI Measures of Paddle Placement

  Journal of Neurological Surgery Part B Skull Base · 2026-02-27

  article
  PublisherDOI

• SIGNAL: A Scalable, Real-World Model for Rapid Intraoperative Molecular Classification of Gliomas Using Stimulated Raman Histology

  medRxiv · 2026-05-13

  article

  Abstract Background Previous machine learning models to intraoperatively predict the molecular status of gliomas using stimulated Raman histology (SRH), such as DeepGlioma, have achieved high performance (91.5% accuracy) on curated datasets. However, when used intraoperatively, DeepGlioma (162M parameters) runs slowly on current SRH hardware and underperforms due to its lack of an image rejection mechanism and its validation on curated images. Here, we introduce SRH-Informed Glioma classificatioN with Attention Learning (SIGNAL) (27M parameters), a lighter model with a built-in attention-based rejection mechanism that outperforms DeepGlioma on uncurated clinical datasets. Methods SIGNAL was developed using 1.56 million SRH fields-of-view from 967 adult diffuse glioma patients collected between December 2017 and July 2025. We used 412 patients from NYU for training and internal validation and a multi-institutional, international cohort of 555 patients for testing. SIGNAL uses a ResNet50 backbone pretrained using a hierarchical contrastive loss function followed by a multi-head multi-layer perceptron (MLP). Using a patch-based attention threshold of 0.6, a final MLP was trained to predict glioma subtypes: glioblastoma, oligodendroglioma, or astrocytoma. Results SIGNAL outperformed DeepGlioma, achieving greater overall accuracy (90.10% vs. 72.59%) while running faster (16.0 vs. 6.7 patches/s). SIGNAL also outperformed DeepGlioma on all three molecular classification tasks, including IDH mutation (accuracy: 93.51% vs. 79.22%), 1p19q codeletion (93.51% vs. 88.31%), and ATRX loss (89.61% vs. 83.98%). SIGNAL’s attention mechanism had a strong positive linear correlation with mean patch cellularity (r=0.96, p<0.001) and a strong negative correlation with patch blood coverage (r=-0.99,p<0.001). Finally, subtype and molecular accuracy between tumor core and margin samples were equivalent despite significantly lower patch retention in tumor margins (44.5% vs 60.2%, p<0.0001). Conclusion SIGNAL is a lightweight model for intraoperative molecular classification of gliomas using SRH imaging. Its attention-based image quality filter allows for excellent performance, quick processing, and highly interpretable outputs critical for reliable use in intraoperative workflows. Brief 1-2 Sentence Description We present SIGNAL, a lightweight machine learning model for intraoperative molecular classification of diffuse gliomas using stimulated Raman histology, whose core innovation is a learned attention mechanism that filters diagnostically uninformative tissue, such as blood and acellular regions, before classification, enabling robust real-world generalizability. Validated on 555 patients across four international centers, SIGNAL outperforms the previous state-of-the-art model DeepGlioma on glioma subtype classification (90.10% vs. 72.59% accuracy) while running 2.4 times faster on intraoperative hardware.

  PublisherDOI

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

  npj Digital Medicine · 2026-03-17

  articleOpen access

  Spinal tumor surgery requires rapid tissue diagnosis to guide surgical decisions and further treatment strategies, yet current intraoperative methods are time-intensive and require specialized expertise. No AI systems exist for real-time spinal tumor classification during surgery. We developed SpineXtract, the first AI-powered system for rapid intraoperative spinal tumor diagnosis using stimulated Raman histology (SRH) - a label-free Raman spectromics imaging technique without tissue processing available during surgery. We created a transformer-based classifier optimized for spinal tissue characteristics to identify common tumor types: meningioma, schwannoma, ependymoma, and metastasis. The system was tested in an international, multicenter, simulated, single-arm study using existing SRH datasets (44 patients, 142 slide-images) from three international institutions, with final pathological diagnosis as reference standard. SpineXtract achieved a 92.9% macro-average balanced accuracy (95% CI: 85.5-98.2) within 5 minutes (tumor-specific accuracy range, 84.2-98.6%), while providing quantitative microscopic feedback for granular tissue analysis. Performance remained consistent across institutions (macro balanced accuracy 91.4-92.0%) and outperformed existing brain tumor classifiers by 15.6%. Our results demonstrate clinical applicability, enabling rapid intraoperative diagnosis with performance exceeding current methods, potentially transforming intraoperative diagnostic workflows in spinal tumor surgery.

  PublisherDOI

• Identification of Auditory Brainstem Paddle Migration Arising from Fat Atrophy Utilizing MRI

  Journal of Neurological Surgery Reports · 2026-04-01

  articleOpen access

  Abstract Objective To demonstrate magnetic resonance imaging’s (MRI’s) utility in investigating auditory brainstem implant (ABI) performance degradation. Design Case study. Setting Academic medical center. Participant This report presents a patient with neurofibromatosis type 2 and an ABI with durable, limited open-set speech who developed nonauditory side effects and a complete lack of auditory perception. ABI paddle placement was assessed with 1.5 Tesla (T) Siemens MRI, and device function was assessed utilizing integrity tests. Main Outcome Measure The etiology of ABI performance degradation utilizing 1.5 T Siemens MRI. Results On initial postoperative 1.5 T Siemens MRI, the ABI paddle approximated the cochlear nucleus. Approximately 1 year later, the patient experienced ABI performance degradation and dizziness. Although ABI device integrity testing was normal, follow-up 1.5 T Siemens MRI revealed lateral ABI paddle migration from the foramen of Luschka toward the flocculus, likely due to observed fat atrophy from the prior craniotomy reconstruction, suggesting a possible etiology for the observed ABI degradation. Conclusion This report presents MRI’s ability to successfully delineate postoperative fat atrophy, ABI paddle migration in relation to the brainstem, and residual tumor in a patient with ABI degradation.

  PublisherOA PDFDOI

• Endoscopic Trans-Orbital Approach with a Modified Lateral Orbitotomy for Spheno-Orbital Meningioma Resection

  Journal of Neurological Surgery Part B Skull Base · 2026-02-27

  article
  PublisherDOI

• First Artificial Intelligence System to Support Clinical Decision Making for Patients with Vestibular Schwannomas

  Journal of Neurological Surgery Part B Skull Base · 2026-02-27

  article
  PublisherDOI

• Anatomic Predilection of Isocitrate Dehydrogenase-Mutant Gliomas: A Multi-Institutional Spatial Analysis

  Neurosurgery · 2026-04-03

  article

  BACKGROUND AND OBJECTIVES: Interactions between cancer cells and their microenvironment are central to tumor formation. Regional microenvironmental variability in the brain may offer insights into essential factors in tumorigenesis. Surprisingly, a granular assessment of regional patterns of gliomagenesis has not been undertaken in the molecular era. The aim of this study was to quantitatively establish the anatomic distribution of the major molecular subtypes of adult diffuse glioma. METHODS: We retrospectively analyzed 204 isocitrate dehydrogenase (IDH)-mutant and 200 IDH-wildtype gliomas. Reproducibility was assessed in an external cohort (190 IDH-mutant, 227 IDH-wildtype), and microarray expressions from Allen Human Brain Atlas were used to compare transcriptomic profiles between IDH-mutant hotspots and coldspots. RESULTS: A total of 50.5% (103/204) of IDH-mutant tumors arose with the superior and middle frontal gyri, indicating a 3.1-fold regional enrichment relative to the volume of these gyri (P < .001). Totally, 9.5% (19/200) of IDH-wildtype tumors arose in the superior temporal gyrus with a 2.1-fold enrichment (P = .01). IDH-mutant and wildtype tumors were enriched by 4 and 4.5-fold, respectively, in the insula (both P < .001). Overall, 23.3% (24/103) of astrocytomas occurred disproportionately higher in the insula compared with oligodendrogliomas (P < .001). Transcriptomic analysis comparing the lobar hotspot (frontal lobe) to the coldspot (occipital lobe) revealed frontal enrichment of cholesterol (normalized enrichment score = 1.78) and fatty acid (normalized enrichment score = 1.94) metabolism pathways, paralleling the observed regional enrichment of IDH-mutant gliomas. CONCLUSION: This study identifies molecular subtype-specific glioma hotspots and may suggest that regional metabolic differences may underlie the brain's variable vulnerability to gliomagenesis. These findings provide a framework for investigating additional microenvironmental factors that drive human glioma formation.

  PublisherDOI

• 459 Regional Variability in Gliomagenesis: A Multi-Institutional Spatial Analysis

  Neurosurgery · 2026-03-26

  article
  PublisherDOI

• Implications of Tumor Size on Auditory Brainstem Implant Performance

  Journal of Neurological Surgery Part B Skull Base · 2026-02-27

  article
  PublisherDOI

• Enhanced Recovery Protocols Reduce Length of Stay and Readmission Rate After Endoscopic Endonasal Resection of Pituitary Adenomas

  Journal of Neurological Surgery Part B Skull Base · 2026-02-27

  article
  PublisherDOI

Frequent coauthors

• Matija Snuderl

  New York University

  134 shared

• David Zagzag

  134 shared

• Douglas Kondziolka

  New York University

  112 shared

• Dimitris G. Placantonakis

  NYU Langone’s Laura and Isaac Perlmutter Cancer Center

  88 shared

• J. Thomas Roland

  NYU Langone Health

  76 shared

• Donato Pacione

  NYU Langone Health

  70 shared

• Meng Law

  Monash University

  64 shared

• Matthias A. Karajannis

  Memorial Sloan Kettering Cancer Center

  64 shared

Awards & honors

• Named one of America’s top doctors by Castle Connolly for mo…