Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations
Himar Fabelo, Samuel Ortega, Daniele Ravi, B Ravi Kiran, Coralia Sosa, Diederik Bulters, Gustavo M Callicó, Harry Bulstrode, Adam Szolna, Juan F Piñeiro, Silvester Kabwama, Daniel Madroñal, Raquel Lazcano, Aruma J-O'Shanahan, Sara Bisshopp, María Hernández, Abelardo Báez, Guang-Zhong Yang, Bogdan Stanciulescu, Rubén Salvador, Eduardo Juárez, Roberto Sarmiento, Himar Fabelo, Samuel Ortega, Daniele Ravi, B Ravi Kiran, Coralia Sosa, Diederik Bulters, Gustavo M Callicó, Harry Bulstrode, Adam Szolna, Juan F Piñeiro, Silvester Kabwama, Daniel Madroñal, Raquel Lazcano, Aruma J-O'Shanahan, Sara Bisshopp, María Hernández, Abelardo Báez, Guang-Zhong Yang, Bogdan Stanciulescu, Rubén Salvador, Eduardo Juárez, Roberto Sarmiento
Abstract
Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.
Conflict of interest statement
Competing Interests: The authors have declared that no competing interests exist.
Figures
References
- Excellence NI for H and C. Improving Outcomes for People with Brain and Other CNS Tumours. In: Cancer service guideline [CSG10]. 2016.
- Sanai N, Berger MS. Glioma extent of resection and its impact on patient outcome. Neurosurgery. 2008. pp. 753–764. doi:
- Sanai N, Berger MS. Operative Techniques for Gliomas and the Value of Extent of Resection. Neurotherapeutics. 2009;6: 478–486. doi:
- Petrecca K, Guiot M, Panet-Raymond V, Souhami L. Failure pattern following complete resection plus radiotherapy and temozolomide is at the resection margin in patients with glioblastoma. J Neurooncol. 2013;111: 19–23. doi:
- Stummer W, Tonn JC, Mehdorn HM, Nestler U, Franz K, Goetz C, et al. Counterbalancing risks and gains from extended resections in malignant glioma surgery: A supplemental analysis from the randomized 5-aminolevulinic acid glioma resection study: Clinical article. J Neurosurg. 2011;114: 613–623. doi:
- Kast RE, Auner GW, Rosenblum ML, Mikkelsen T, Yurgelevic SM, Raghunathan A, et al. Raman molecular imaging of brain frozen tissue sections J Neurooncol. Springer New York LLC; 2014;120: 55–62. doi:
- Reinges MHT, Nguyen HH, Krings T, Hütter BO, Rohde V, Gilsbach JM, et al. Course of brain shift during microsurgical resection of supratentorial cerebral lesions: Limits of conventional neuronavigation. Acta Neurochir (Wien). 2004;146: 369–377. doi:
- Ganser KA, Dickhaus H, Staubert A, Bonsanto MM, Wirtz CR, Tronnier VM, et al. Quantification of brain shift effects in MRI images. Biomed Tech (Berl). 1997;42 Suppl: 247–248. Available:
- Stummer W, Pichlmeier U, Meinel T, Wiestler OD, Zanella F, Reulen HJ. Fluorescence-guided surgery with 5-aminolevulinic acid for resection of malignant glioma: a randomised controlled multicentre phase III trial. Lancet Oncol. 2006;7: 392–401. doi:
- Floeth FW, Sabel M, Ewelt C, Stummer W, Felsberg J, Reifenberger G, et al. Comparison of 18F-FET PET and 5-ALA fluorescence in cerebral gliomas. Eur J Nucl Med Mol Imaging. 2011;38: 731–741. doi:
- Colarusso P, Kidder LH, Levin IW, Fraser JC, Arens JF, Lewis EN. Infrared spectroscopic imaging: From planetary to cellular systems. Appl Spectrosc. 1998;52 doi:
- Lu G, Fei B. Medical hyperspectral imaging: a review. J Biomed Opt. 2014;19: 10901 doi:
- Han Z, Zhang A, Wang X, Sun Z, Wang MD, Xie T. In vivo use of hyperspectral imaging to develop a noncontact endoscopic diagnosis support system for malignant colorectal tumors. J Biomed Opt. 2016;21: 16001 doi:
- Akbari H, Halig L V, Schuster DM, Osunkoya A, Master V, Nieh PT, et al. Hyperspectral imaging and quantitative analysis for prostate cancer detection. J Biomed Opt. SPIE-Intl Soc Optical Eng; 2012;17: 760051 doi:
- Akbari H, Uto K, Kosugi Y, Kojima K, Tanaka N. Cancer detection using infrared hyperspectral imaging Cancer Sci. Wiley-Blackwell; 2011;102: 852–857. doi:
- Panasyuk S V, Yang S, Faller D V, Ngo D, Lew RA, Freeman JE, et al. Medical hyperspectral imaging to facilitate residual tumor identification during surgery. Cancer Biol Ther. 2007;6: 439–446. doi:
- Liu Z, Wang H, Li Q. Tongue tumor detection in medical hyperspectral images. Sensors. 2012;12: 162–174. doi:
- Zherdeva LA, Bratchenko IA, Alonova M V, Myakinin OO, Artemyev DN, Moryatov AA, et al. Hyperspectral imaging of skin and lung cancers [Internet]. Proc. SPIE. 2016. p. 98870S–98870S–10. doi:
- Lu G, Qin X, Wang D, Muller S, Zhang H, Chen A, et al. Hyperspectral imaging of neoplastic progression in a mouse model of oral carcinogenesis. Prog Biomed Opt Imaging—Proc SPIE. 2016;9788: 978812 doi:
- Regeling B, Laffers W, Gerstner AOH, Westermann S, Müller NA, Schmidt K, et al. Development of an image pre-processor for operational hyperspectral laryngeal cancer detection J Biophotonics. WILEY-VCH Verlag; 2016;9: 235–245. doi:
- Akbari H, Halig L V, Zhang H, Wang D, Chen ZG, Fei B. Detection of Cancer Metastasis Using a Novel Macroscopic Hyperspectral Method. Proc SPIE. 2012;8317: 831711 doi:
- Lu G, Halig L, Wang D, Chen ZG, Fei B. Spectral-Spatial Classification Using Tensor Modeling for Cancer Detection with Hyperspectral Imaging. Proc SPIE-the Int Soc Opt Eng. 2014;9034: 903413 doi:
- Lu G, Qin X, Wang D, Chen ZG, Fei B. Quantitative wavelength analysis and image classification for intraoperative cancer diagnosis with hyperspectral imaging. Progress in Biomedical Optics and Imaging—Proceedings of SPIE. SPIE; 2015. doi:
- Lu G, Wang D, Qin X, Halig L, Muller S, Zhang H, et al. Framework for hyperspectral image processing and quantification for cancer detection during animal tumor surgery. J Biomed Opt. SPIE-Intl Soc Optical Eng; 2015;20: 126012 doi:
- Pike R, Lu G, Wang D, Chen ZG, Fei B. A Minimum Spanning Forest-Based Method for Noninvasive Cancer Detection With Hyperspectral Imaging. IEEE Trans Biomed Eng. 2016;63: 653–663. doi:
- Fabelo H, Ortega S, Kabwama S, Callico GM, Bulters D, Szolna A, et al. HELICoiD project: A new use of hyperspectral imaging for brain cancer detection in real-time during neurosurgical operations. Proceedings of SPIE—The International Society for Optical Engineering. 2016. doi:
- Huang K, Li S, Kang X, Fang L. Spectral–Spatial Hyperspectral Image Classification Based on KNN. Sens Imaging. 2016;17: 1–13. doi:
- Ravi D, Fabelo H, Callico GM, Yang G. Manifold Embedding and Semantic Segmentation for Intraoperative Guidance with Hyperspectral Brain Imaging. IEEE Trans Med Imaging. IEEE; 2017;
- Tarabalka Y, Benediktsson J, Chanussot J. Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques. IEEE Trans Geosci Remote Sens. 2009;47: 2973–2987. doi:
- Fabelo H, Ortega S, Guerra R, Callicó G, Szolna A, Piñeiro JF, et al. A novel use of hyperspectral images for human brain cancer detection using in-vivo samples. BIOSIGNALS 2016—9th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. 2016.
- Van Der Maaten LJP, Postma EO, Van Den Herik HJ. Dimensionality Reduction: A Comparative Review. J Mach Learn Res. 2009;10: 1–41. doi:
- Peason K. On lines and planes of closest fit to systems of point in space. Philos Mag. 1901;2: 559–572.
- Tenenbaum JB, de Silva V, Langford JC. A global geometric framework for nonlinear dimensionality reduction. Science. 2000;290: 2319–23. doi:
- Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. Science. 2000;290: 2323–6. doi:
- Donoho DL, Grimes C. Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc Natl Acad Sci U S A. 2003;100: 5591–5596. doi:
- Belkin M, Niyogi P. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. Nips. 2001;14: 585–591.
- Van Der Maaten LJP, Hinton GE. Visualizing high-dimensional data using t-sne. J Mach Learn Res. 2008;9: 2579–2605. doi:
- Lekadir K, Elson DS, Requejo-Isidro J, Dunsby C, McGinty J, Galletly N, et al. Tissue characterization using dimensionality reduction and fluorescence imaging. 9th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI’06). 2006. pp. 586–593.
- Zhang YD, Yang ZJ, Lu HM, Zhou XX, Phillips P, Liu QM, et al. Facial emotion recognition based on biorthogonal wavelet entropy, fuzzy support vector machine, and stratified cross validation. IEEE Access. 2016;4: 8375–8385. doi:
- Camps-Valls G, Bruzzone L. Kernel-based methods for hyperspectral image classification. IEEE Trans Geosci Remote Sens. 2005;43: 1351–1362. doi:
- Zhang Y, Lu S, Zhou X, Yang M, Wu L, Liu B, et al. Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine. Simulation. 2016;92: 861–871. doi:
- Wang S, Yang M, Du S, Yang J, Liu B, Gorriz JM, et al. Wavelet entropy and directed acyclic graph support vector machine for detection of patients with unilateral hearing loss in MRI scanning. Front Comput Neurosci. 2016;10: 1–11.
- Kong SG, Du Z, Martin M, Vo-Dinh T. Hyperspectral fluorescence image analysis for use in medical diagnostics. In: Vo-Dinh T, Grundfest WS, Benaron DA, Cohn GE, editors. Advanced Biomedical and Clinical Diagnostic Systems III. SPIE-Intl Soc Optical Eng; 2005. doi:
- Kong SG, Park L-J. Hyperspectral Image Analysis for Skin Tumor Detection. Augmented Vision Perception in Infrared. 2009. pp. 155–171. doi:
- Zhi L, Zhang D, Yan J qi, Li QL, Tang Q lin. Classification of hyperspectral medical tongue images for tongue diagnosis. Comput Med Imaging Graph. 2007;31: 672–678. doi:
- Rajpoot K, Rajpoot N. SVM Optimization for Hyperspectral Colon Tissue Cell Classification. Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2004. Springer Nature; 2004. pp. 829–837. doi:
- Chang C, Lin C. LIBSVM: A Library for Support Vector Machines. ACM Trans Intell Syst Technol. 2013;2: 1–39. doi:
- Masood K, Rajpoot N, Rajpoot K, Qureshi H. Hyperspectral Colon Tissue Classification using Morphological Analysis. International Conference on Emerging Technologies. 2006. pp. 735–741. doi:
- Regeling B, Thies B, Gerstner AOH, Westermann S, Müller NA, Bendix J, et al. Hyperspectral Imaging Using Flexible Endoscopy for Laryngeal Cancer Detection. Sensors. 2016;16: 1288 doi:
- Kiran BR, Stanciulescu B, Angulo J. Unsupervised clustering of hyperspectral images of brain tissues by hierarchical non-negative matrix factorization. BIOIMAGING 2016. 2016. p. 8.
- Banerjee A, Dhillon I, Ghosh J, Sra S. Generative model-based clustering of directional data. Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. 2003. pp. 19–28.
- Salvador R, Fabelo H, Lazcano R, Ortega S, Madroñal D, Callicó GM, et al. Demo: HELICoiD tool demonstrator for real-time brain cancer detection. Conference on Design and Architectures for Signal and Image Processing, DASIP. 2017. doi:
- De Dinechin BD, Ayrignac R, Beaucamps PE, Couvert P, Ganne B, De Massas PG, et al. A clustered manycore processor architecture for embedded and accelerated applications. 2013 IEEE High Performance Extreme Computing Conference, HPEC 2013. 2013. doi:
Source: PubMed