Supervised Machine Learning Methods and Hyperspectral Imaging Techniques Jointly Applied for Brain Cancer Classification

Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

[1]  Guolan Lu,et al.  Medical hyperspectral imaging: a review , 2014, Journal of biomedical optics.

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  J. Chin,et al.  Evaluation of hyperspectral technology for assessing the presence and severity of peripheral artery disease. , 2011, Journal of vascular surgery.

[4]  Frank Lindseth,et al.  Ultrasound imaging in neurosurgery: approaches to minimize surgically induced image artefacts for improved resection control , 2013, Acta Neurochirurgica.

[5]  Jill S. Barnholtz-Sloan,et al.  Epidemiologic and Molecular Prognostic Review of Glioblastoma , 2014, Cancer Epidemiology, Biomarkers & Prevention.

[6]  Mitchel S Berger,et al.  An extent of resection threshold for newly diagnosed glioblastomas. , 2011, Journal of neurosurgery.

[7]  Aksone Nouvong,et al.  Hyperspectral Imaging in Diabetic Foot Wound Care , 2010, Journal of diabetes science and technology.

[8]  Guo Cao,et al.  Cascaded Random Forest for Hyperspectral Image Classification , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Massimiliano Pontil,et al.  Support Vector Machines: Theory and Applications , 2001, Machine Learning and Its Applications.

[10]  Kunal Roy,et al.  The “double cross-validation” software tool for MLR QSAR model development , 2016 .

[11]  Daniel U. Campos-Delgado,et al.  Classification of Hyperspectral In Vivo Brain Tissue Based on Linear Unmixing , 2020, Applied Sciences.

[12]  Robert P. Francis,et al.  Active DLP hyperspectral illumination: a noninvasive, in vivo, system characterization visualizing tissue oxygenation at near video rates. , 2011, Analytical chemistry.

[13]  N.M. Rajpoot,et al.  Wavelet based segmentation of hyperspectral colon tissue imagery , 2003, 7th International Multi Topic Conference, 2003. INMIC 2003..

[14]  Hongjun Wang,et al.  Tongue Tumor Detection in Medical Hyperspectral Images , 2011, Sensors.

[15]  Colm P. O'Donnell,et al.  Hyperspectral imaging – an emerging process analytical tool for food quality and safety control , 2007 .

[16]  E. Livingston,et al.  Intraoperative bile duct visualization using near-infrared hyperspectral video imaging. , 2008, American Journal of Surgery.

[17]  Sung K. Chang,et al.  Multispectral digital colposcopy for in vivo detection of cervical cancer. , 2003, Optics express.

[18]  Rajashree U Gandhe,et al.  Intraoperative magnetic resonance imaging for neurosurgery – An anaesthesiologist's challenge , 2018, Indian journal of anaesthesia.

[19]  Roberto Sarmiento,et al.  HELICoiD project: a new use of hyperspectral imaging for brain cancer detection in real-time during neurosurgical operations , 2016, SPIE Commercial + Scientific Sensing and Imaging.

[20]  Gustavo Marrero Callicó,et al.  Deep Learning-Based Framework for In Vivo Identification of Glioblastoma Tumor using Hyperspectral Images of Human Brain , 2019, Sensors.

[21]  R. Gillies,et al.  Systemic effects of shock and resuscitation monitored by visible hyperspectral imaging. , 2003, Diabetes technology & therapeutics.

[22]  S. Eljamel,et al.  Risk factors for developing oral 5-aminolevulinic acid-induced side effects in patients undergoing fluorescence guided resection. , 2013, Photodiagnosis and photodynamic therapy.

[23]  Karel J. Zuzak,et al.  Visible spectroscopic imaging studies of normal and ischemic dermal tissue , 2000, BiOS.

[24]  Sanyam Shukla,et al.  Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification , 2016, 2016 IEEE 6th International Conference on Advanced Computing (IACC).

[25]  Naoto Yokoya,et al.  Random Forest Ensembles and Extended Multiextinction Profiles for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[26]  César Sanz,et al.  Multiclass Brain Tumor Classification Using Hyperspectral Imaging and Supervised Machine Learning , 2020, 2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS).

[27]  Guang-Zhong Yang,et al.  Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations , 2018, PloS one.

[28]  Stephen Marshall,et al.  Effective Feature Extraction and Data Reduction in Remote Sensing Using Hyperspectral Imaging [Applications Corner] , 2014, IEEE Signal Processing Magazine.

[29]  Haida Liang,et al.  Advances in multispectral and hyperspectral imaging for archaeology and art conservation , 2012 .

[30]  Michael I. Miga,et al.  Clinical evaluation of a model-updated image-guidance approach to brain shift compensation: experience in 16 cases , 2016, International Journal of Computer Assisted Radiology and Surgery.

[31]  Gustavo Marrero Callicó,et al.  Hyperspectral Imaging for Glioblastoma Surgery: Improving Tumor Identification Using a Deep Spectral-Spatial Approach , 2020, Sensors.

[32]  Yukio Kosugi,et al.  Hyperspectral Image segmentation and its application in abdominal surgery , 2009, Int. J. Funct. Informatics Pers. Medicine.

[33]  Shiqin Liu,et al.  Leave- $p$ -Out Cross-Validation Test for Uncertain Verhulst-Pearl Model With Imprecise Observations , 2019, IEEE Access.

[34]  José Antonio Lozano,et al.  Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  A. Acharya,et al.  Sampling: why and how of it? , 2013 .

[36]  Guangyao Shi,et al.  Dimensionality Reduction of Hyperspectral Image Based on Local Constrained Manifold Structure Collaborative Preserving Embedding , 2021, Remote. Sens..

[37]  J. Cadeddu,et al.  Assessment of renal oxygenation during partial nephrectomy using hyperspectral imaging. , 2010, Journal of Urology.

[38]  Dana Ron,et al.  Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation , 1997, Neural Computation.

[39]  Alexandra J. Golby,et al.  Applications of Ultrasound in the Resection of Brain Tumors , 2017, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[40]  Guang-Zhong Yang,et al.  An Intraoperative Visualization System Using Hyperspectral Imaging to Aid in Brain Tumor Delineation , 2018, Sensors.

[41]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[42]  Ricardo J. Komotar,et al.  The role of 5-aminolevulinic acid in brain tumor surgery: a systematic review , 2016, Neurosurgical Review.

[43]  Daniel W. Wilson,et al.  Snapshot hyperspectral imaging in ophthalmology. , 2007, Journal of biomedical optics.

[44]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[45]  Frank Hutter,et al.  Fixing Weight Decay Regularization in Adam , 2017, ArXiv.

[46]  Eustace L. Dereniak,et al.  Hyperspectral imaging for astronomy and space surviellance , 2004, SPIE Optics + Photonics.

[47]  Amir Gandjbakhche,et al.  Hyperspectral imaging of Kaposi's Sarcoma for disease assessment and treatment monitoring , 2002, Applied Imagery Pattern Recognition Workshop, 2002. Proceedings..

[48]  Ferenc Jolesz,et al.  Neuronavigation in the surgical management of brain tumors: current and future trends , 2012, Expert review of medical devices.

[49]  Rahul Chauhan,et al.  Convolutional Neural Network (CNN) for Image Detection and Recognition , 2018, 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC).

[50]  P. Black,et al.  Intra-operative magnetic resonance imaging in neurosurgery , 2004, Acta Neurochirurgica.

[51]  D. Ferris,et al.  Multimodal Hyperspectral Imaging for the Noninvasive Diagnosis of Cervical Neoplasia , 2001, Journal of lower genital tract disease.