Intraoperative brain tumor classification via laser-induced fluorescence spectroscopy and machine learning.
Date
2025-08
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Attention Stats
Abstract
Objective
To optimize neurosurgical tumor resection, tissue types and borders must be appropriately identified. Authors of this study established the use of a nondestructive laser-based endogenous fluorescence spectroscopy device, "TumorID," to almost immediately classify a specimen as glioma, meningioma, pituitary adenoma, or nonneoplastic tissue in the operating room, utilizing a machine learning algorithm.Methods
TumorID requires only 0.5 seconds to collect data, without the need for any dyes or tissue manipulation, and utilizes a 100-mW, 405-nm laser that does not damage the tissue. The system was used in the operating room to scan ex vivo specimens from 46 patients (mean age 52 years) with glioma (8 patients), meningioma (10 patients), pituitary adenoma (23 patients), and nonneoplastic tissue resected during an epilepsy operation (5 patients). A support vector machine algorithm was trained to distinguish between these lesions and classify them in near real time. Statistical significance was determined through a generalized estimating equation on the area under the known fluorophore emission regions for free reduced nicotinamide adenine dinucleotide (NADH), bound NADH, flavin adenine dinucleotide, and neutral porphyrins.Results
Ultimately, the machine learning model showed a high degree of classification power with a multiclass area under the receiver operating characteristic curve of 0.809 ± 0.002. The areas under the curve for neutral porphyrins were found to be statistically significant (p < 0.001) and to have the largest impact on model output.Conclusions
This initial ex vivo clinical study demonstrated the ability of TumorID to rapidly differentiate and classify various pathologies and surrounding brain in a configuration that can be easily translated to scan in vivo. This classification power could allow TumorID to augment surgical decision-making by enabling rapid intraoperative tissue diagnostics and border delineation, potentially improving patient outcomes by allowing for a more informed and complete resection.Type
Department
Description
Provenance
Subjects
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Zachem, Tanner J, Jacob E Sperber, Sully F Chen, Syed M Adil, Benjamin D Wissel, Gregory Chamberlin, Edwin Owolo, Annee Nguyen, et al. (2025). Intraoperative brain tumor classification via laser-induced fluorescence spectroscopy and machine learning. Journal of neurosurgery, 143(2). pp. 313–322. 10.3171/2024.12.jns242041 Retrieved from https://hdl.handle.net/10161/33733.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Tanner Zachem
Annee Nguyen
Annee is a graduate student in Duke's Department of Pharmacology, a joint program with Molecular Cancer Biology. She is excited to identify therapeutic molecules and elucidate therapeutic mechanisms of antitumor efficacy that may also target secondary comorbid conditions, such as pain or neurological deficits. She is passionate about scientific education and communication and hopes to remain in academia with the goal of cultivating the next generation of scientists.
In 2017, Annee graduated from the University of California, San Diego, from Warren College, with a Bachelor of Science in Human Biology (double minoring in Psychology and Theatre) as magna cum laude and as part of the Sigma Chapter of the Phi Beta Kappa Society and obtained a contiguous Master of Science in Biology in 2018, concentrating in Neuropathology and Scientific Communication.
Since 2014, her prior research experience includes working with various preclinical models of peripheral neuropathy (with Dr. Nigel Calcutt and Dr. Christina Sigurdson of UC San Diego’s Department of Pathology), equine and murine models of neuroaxonal dystrophy (with Dr. Carrie Finno of UC Davis’s School of Veterinary Medicine), and CNS tumor preclinical models of recurrent glioblastoma and spine tumors and metastases at Duke University Medical Center with Dr. Rory Goodwin of the Duke Center for Brain and Spine Metastasis and the Department of Neurosurgery. In each lab, she sought to identify therapeutics that could prevent, reverse, or abate the neurodegenerative diseases of focus and explored mechanisms of disease development and therapeutic impact. Throughout her experiences, Annee has continually focused on developing projects driven by clinical impact and focused on taking science from bench to bedside and back.
James Emmett Herndon
Current research interests have application to the design and analysis of cancer clinical trials. Specifically, interests include the use of time-dependent covariables within survival models, the design of phase II cancer clinical trials which minimize some of the logistical problems associated with their conduct, and the analysis of longitudinal studies with informative censoring (in particular, quality of life studies of patients with advanced cancer).
Ralph Abi Hachem
David W Jang
My clinical expertise is in diseases of the nose, sinuses, and skull base. I perform endoscopic sinus surgery, nasal airway surgery, and minimally invasive endonasal surgery of the pituitary and skull base.
Thomas John Cummings
Clinical and Research interests: Neuropathology; Ophthalmic pathology; Orthopaedic pathology; Neuromuscular pathology; General surgical pathology; Leprosy; Tropical diseases.
Margaret Johnson
I am a neuro-oncologist, neurologist, and palliative care physician at the Preston Robert Tisch Brain Tumor Center. I also provide neuro-oncology expertise for the National Tele-Oncology Program and National Precision Oncology Program at the Veteran's Health Administration. My clinical and research interests encompass supportive care and palliative care with a special interest in older adults with brain tumors. The incidence of malignant brain tumors like glioblastoma and non-malignant tumors like meningioma affect aging populations and it is crucial to be able to provide better care for these patients.
William Curtis Eward
I am an Orthopaedic Oncologist, with dual clinical degrees (MD and DVM). I treat complex sarcomas in people and animals. My laboratory studies comparative oncology - discoveries we can make about cancer by analyses across different species.
Anoop Patel
Jordan Komisarow
Derek Southwell
I am a surgeon-scientist specialized in the treatment of epilepsy and movement disorders. My laboratory conducts basic and translational neuroscience research on cortical inhibitory circuits. We are interested in 1) understanding the cellular design of inhibitory circuits in mice and humans, and, 2) advancing interneuron transplantation as a therapeutic strategy for inhibitory circuit repair.
Allan Howard Friedman
At the present time, I am participating in collaborative research in the areas of primary malignant brain tumors, epilepsy and subarachnoid hemorrhage.
Primary malignant brain tumors are increasing in frequency. Patients harboring glioblastoma, the most malignant primary brain tumor, have a life expectancy of less than one year. In collaboration with the Division of Neurology and the Department of Pathology, clinical and laboratory trials have been initiated to identify better treatment for this condition. At present, trials of monoclonal antibodies and novel chemotherapeutic agents are being carried out.
Although physicians have been interested in seizures since the time of Hippocrates, the origin of seizures remains obscure. At Duke University we have treated approximately thirty seizure patients a year by removing abnormal portions of brain. Tissue from these resections is being analyzed for genetics and receptor abnormalities. Positron emission tomography and magnetic resonance imaging are being used to ferret out the origin of the patient's seizures.
Approximately 28,000 patients each year suffer a ruptured intracranial aneurysm. Approximately ten percent of these patients have a genetic predisposition to forming intracranial aneurysms. In conjunction with the Division of Neurology, we are screening candidate genes searching for the cause of intracranial aneurysms.
Courtney Rory Goodwin
Associate Professor of Neurosurgery, Radiation Oncology, Orthopedic Surgery.
Director of Spine Oncology,
Associate Residency Program Director
Third Year Study Program Director Neurosciences, Duke University School of Medicine
Director of Spine Metastasis, Duke Center for Brain and Spine Metastasis, Department of Neurosurgery
Duke Cancer Institute, Duke University Medical Center
Patrick James Codd
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.