Machine learning assisted intraoperative assessment of brain tumor margins using HRMAS NMR spectroscopy

Abstract

Complete resection of the tumor is important for survival in glioma patients. Even if the gross total resection was achieved, left-over micro-scale tissue in the excision cavity risks recurrence. High Resolution Magic Angle Spinning Nuclear Magnetic Resonance (HRMAS NMR) technique can distinguish healthy and malign tissue efficiently using peak intensities of biomarker metabolites. The method is fast, sensitive and can work with small and unprocessed samples, which makes it a good fit for real-time analysis during surgery. However, only a targeted analysis for the existence of known tumor biomarkers can be made and this requires a technician with chemistry background, and a pathologist with knowledge on tumor metabolism to be present during surgery. Here, we show that we can accurately perform this analysis in real-time and can analyze the full spectrum in an untargeted fashion using machine learning. We work on a new and large HRMAS NMR dataset of glioma and control samples (n = 565), which are also labeled with a quantitative pathology analysis. Our results show that a random forest based approach can distinguish samples with tumor cells and controls accurately and effectively with a median AUC of 85.6% and AUPR of 93.4%. We also show that we can further distinguish benign and malignant samples with a median AUC of 87.1% and AUPR of 96.1%. We analyze the feature (peak) importance for classification to interpret the results of the classifier. We validate that known malignancy biomarkers such as creatine and 2-hydroxyglutarate play an important role in distinguishing tumor and normal cells and suggest new biomarker regions. The code is released at http://github.com/ciceklab/HRMAS_NC.

Intraoperative tissue classification methods in orthopedic and neurological surgeries: A systematic review

“…Spectroscopic sensing methods found in the reviewed articles can be categorized into the following technologies: optical scattering spectroscopy probe ( 19 ), high-resolution magic angle spinning nuclear resonance spectrometer ( 21 ), Raman spectrometers (i.e. coherent anti- Stokes Raman scattering, visible resonance Raman, stimulated Raman scattering) ( 11 , 20 , 22 – 27 ), diffuse reflectance spectroscopy ( 30 , 31 ), selective narrow-band imaging ( 32 ), clinical endomicroscopy ( 28 ), and fluorescence imaging ( 33 ).…”

Advances in the intraoperative delineation of malignant glioma margin

“…To promote the popularization of these new technology, it requires to be compatible with common operating rooms. One possible solution to strike balance between accuracy and economic efficiency is to establish a large-sample multimodal database and use artificial intelligence algorithms to improve the original imaging resolution (91)(92)(93).…”

The future of artificial intelligence in neurosurgery: A narrative review

“…[ 41 , 48 ] Recently, Cakmakci et al ., using a random forest model, accurately determined the metabolic profile of intraoperatively resected tissue, detected residual neoplastic tissue in excision cavity, and guided the surgeon to perform maximal resection. [ 9 ] Finally, Qiao et al . found that convolutional neural network-based model can predict the extent to which tumor resection should be proceeded in endoscopic transnasal surgery with a comparable human accuracy of 87.4%, thus preventing optic nerve injury and reducing surgeons’ cognitive workload.…”