Hyperspectral Imaging for Major Neurocognitive Disorder Detection in Plasma Samples

Neurocognitive disorders (NCD) affect over 50 million people globally. The detection biomarkers using brain imaging or cerebrospinal fluid are expensive procedures. Blood-based biomarkers such as plasma or serum present a cost-effective alternative. The work presented in this paper is focused on the use of hyperspectral (HS) imaging (HSI) to classify plasma samples in order to discriminate between patients with major NCD and healthy control subjects. HS images of plasma samples were obtained using a SWIR (Short-Wave Infrared) camera able to capture 273 bands within the 900-2,500 nm spectral range. A preliminary HSI database was obtained with 20 major NCD samples and 20 control samples. This data was segmented and classified using pixel-wise supervised classification algorithms, achieving 75% sensitivity and 100% specificity results with the best classifier in the test set.

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

[2]  Dongrong Xu,et al.  Review of spectral imaging technology in biomedical engineering: achievements and challenges , 2013, Journal of biomedical optics.

[3]  John Muschelli,et al.  ROC and AUC with a Binary Predictor: a Potentially Misleading Metric , 2019, Journal of Classification.

[4]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[5]  Shutao Li,et al.  Spectral–Spatial Hyperspectral Image Classification Based on KNN , 2016 .

[6]  Guolan Lu,et al.  Hyperspectral imaging of neoplastic progression in a mouse model of oral carcinogenesis , 2016, SPIE Medical Imaging.

[7]  Anastasios Koulaouzidis,et al.  Use of Hyperspectral/Multispectral Imaging in Gastroenterology. Shedding Some–Different–Light into the Dark , 2019, Journal of clinical medicine.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  C. Jack,et al.  NIA-AA Research Framework: Toward a biological definition of Alzheimer’s disease , 2018, Alzheimer's & Dementia.

[10]  Lorenzo Bruzzone,et al.  Kernel-based methods for hyperspectral image classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[11]  A. Cheema,et al.  The critical need for defining preclinical biomarkers in Alzheimer's disease , 2014, Alzheimer's & Dementia.

[12]  Roberto Sarmiento,et al.  Detecting brain tumor in pathological slides using hyperspectral imaging. , 2018, Biomedical optics express.

[13]  J. Simpson,et al.  DSM-5 and neurocognitive disorders. , 2014, The journal of the American Academy of Psychiatry and the Law.

[14]  Wei Shen,et al.  Blood drop patterns: Formation and applications. , 2016, Advances in colloid and interface science.

[15]  Christine T. O. Nguyen,et al.  Non-invasive in vivo hyperspectral imaging of the retina for potential biomarker use in Alzheimer’s disease , 2019, Nature Communications.

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

[17]  Xiaofeng Ma,et al.  Optimal Threshold Determination for Discriminating Driving Anger Intensity Based on EEG Wavelet Features and ROC Curve Analysis , 2016, Inf..

[18]  Baowei Fei,et al.  In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer , 2019, Cancers.

[19]  T. Yen,et al.  Plasma amyloid assay as a pre-screening tool for amyloid positron emission tomography imaging in early stage Alzheimer’s disease , 2019, Alzheimer's Research & Therapy.

[20]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .