Hyperspectral Imaging for Glioblastoma Surgery: Improving Tumor Identification Using a Deep Spectral-Spatial Approach
Authors:
- Francesca ManniFMFrancesca Manni
- Fons van der SommenFons van der Sommen
- Himar FabeloHimar Fabelo
- Svitlana ZingerSZSvitlana Zinger
- Caifeng ShanCSCaifeng Shan
- Erik EdströmEEErik Edström
- Adrian Elmi-TeranderAEAdrian Elmi-Terander
- Samuel OrtegaSamuel Ortega
- Gustavo Marrero CallicóGustavo Marrero Callicó
- Peter H. N. de WithPWPeter H. N. de With
Open Access
Abstract
The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal resection may result in neurological deficits. On the other hand, accurate intraoperative identification of the tumor boundaries may be very difficult, resulting in subtotal resections. Histological examination of biopsies can be used repeatedly to help achieve gross total resection but this is not practically feasible due to the turn-around time of the tissue analysis. Therefore, intraoperative techniques to recognize tissue types are investigated to expedite the clinical workflow for tumor resection and improve outcome by aiding in the identification and removal of the malignant lesion. Hyperspectral imaging (HSI) is an optical imaging technique with the power of extracting additional information from the imaged tissue. Because HSI images cannot be visually assessed by human observers, we instead exploit artificial intelligence techniques and leverage a Convolutional Neural Network (CNN) to investigate the potential of HSI in twelve in vivo specimens. The proposed framework consists of a 3D–2D hybrid CNN-based approach to create a joint extraction of spectral and spatial information from hyperspectral images. A comparison study was conducted exploiting a 2D CNN, a 1D DNN and two conventional classification methods (SVM, and the SVM classifier combined with the 3D–2D hybrid CNN) to validate the proposed network. An overall accuracy of 80% was found when tumor, healthy tissue and blood vessels were classified, clearly outperforming the state-of-the-art approaches. These results can serve as a basis for brain tumor classification using HSI, and may open future avenues for image-guided neurosurgical applications.Keywords
Funding Information
- Electronic Components and Systems for European Leadership (692470)
- Agencia Canaria de Investigación, Innovación y Sociedad de la Información (2017010164)
This publication has 44 references indexed in Scilit:
- Medical hyperspectral imaging: a reviewJournal of Biomedical Optics, 2014
- Review of spectral imaging technology in biomedical engineering: achievements and challengesJournal of Biomedical Optics, 2013
- Hyperspectral imaging and quantitative analysis for prostate cancer detectionJournal of Biomedical Optics, 2012
- Tongue Tumor Detection in Medical Hyperspectral ImagesSensors, 2011
- Counterbalancing risks and gains from extended resections in malignant glioma surgery: a supplemental analysis from the randomized 5-aminolevulinic acid glioma resection studyJournal of Neurosurgery, 2011
- Comparison of 18F-FET PET and 5-ALA fluorescence in cerebral gliomasEuropean Journal of Nuclear Medicine and Molecular Imaging, 2010
- GLIOMA EXTENT OF RESECTION AND ITS IMPACT ON PATIENT OUTCOMENeurosurgery, 2008
- Quantification of, Visualization of, and Compensation for Brain Shift Using Intraoperative Magnetic Resonance ImagingNeurosurgery, 2000
- Hyperspectral Diagnostic Imaging of the Cervix: Report on a New Investigational DeviceJournal of Lower Genital Tract Disease, 2000
- Quantifizierung von Brain-Shift-Effekten in MR-AufnahmenBiomedical Engineering / Biomedizinische Technik, 1997