Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning.

Autor:	Reinecke D; Department of Stereotactic and Functional Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Ruess D; Department of Stereotactic and Functional Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Centre for Integrated Oncology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Meissner AK; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Fürtjes G; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., von Spreckelsen N; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Ion-Margineanu A; Invenio Imaging Inc., Santa Clara, California., Khalid F; Invenio Imaging Inc., Santa Clara, California., Blau T; Institute for Neuropathology, University of Essen, Essen, Germany., Stehle T; Institute for Neuropathology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Al-Shugri A; Institute for Neuropathology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Büttner R; Institute for Neuropathology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Institute of General Pathology and Pathological Anatomy, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Goldbrunner R; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Centre for Integrated Oncology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Ruge MI; Department of Stereotactic and Functional Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Centre for Integrated Oncology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Neuschmelting V; Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Centre for Integrated Oncology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
Jazyk:	angličtina
Zdroj:	Clinical cancer research : an official journal of the American Association for Cancer Research [Clin Cancer Res] 2024 Sep 03; Vol. 30 (17), pp. 3824-3836.
DOI:	10.1158/1078-0432.CCR-23-3842
Abstrakt:	Purpose: Recent artificial intelligence algorithms aided intraoperative decision-making via stimulated Raman histology (SRH) during craniotomy. This study assesses deep learning algorithms for rapid intraoperative diagnosis from SRH images in small stereotactic-guided brain biopsies. It defines a minimum tissue sample size threshold to ensure diagnostic accuracy. Experimental Design: A prospective single-center study examined 121 SRH images from 84 patients with unclear intracranial lesions undergoing stereotactic brain biopsy. Unprocessed, label-free samples were imaged using a portable fiber laser Raman scattering microscope. Three deep learning models were tested to (i) identify tumorous/nontumorous tissue as qualitative biopsy control; (ii) subclassify into high-grade glioma (central nervous system World Health Organization grade 4), diffuse low-grade glioma (central nervous system World Health Organization grades 2-3), metastases, lymphoma, or gliosis; and (iii) molecularly subtype IDH and 1p/19q statuses of adult-type diffuse gliomas. Model predictions were evaluated against frozen section analysis and final neuropathologic diagnoses. Results: The first model identified tumorous/nontumorous tissue with 91.7% accuracy. Sample size on slides impacted accuracy in brain tumor subclassification (81.6%, κ = 0.72 frozen section; 73.9%, κ = 0.61 second model), with SRH images being smaller than hematoxylin and eosin images (4.1 ± 2.5 mm2 vs. 16.7 ± 8.2 mm2, P < 0.001). SRH images with more than 140 high-quality patches and a mean squeezed sample of 5.26 mm2 yielded 89.5% accuracy in subclassification and 93.9% in molecular subtyping of adult-type diffuse gliomas. Conclusions: Artificial intelligence-based SRH image analysis is non-inferior to frozen section analysis in detecting and subclassifying brain tumors during small stereotactic-guided biopsies once a critical squeezed sample size is reached. Beyond frozen section analysis, it enables valid molecular glioma subtyping, allowing faster treatment decisions in the future; however, refinement is needed for long-term application. (©2024 American Association for Cancer Research.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu