Discrimination of blood species using Raman spectroscopy combined with a recurrent neural network

Species identification of human and animal blood is of critical importance in the areas of custom inspection, forensic science, wildlife preservation, and veterinary purpose. In this study, the combination of Raman spectroscopy and a recurrent neural network (RNN) is proposed for the discrimination of 20 kinds of blood species including human, poultry, wildlife, and experimental animals. The chemometric multi-classification model based on RNN was established and optimized by hyperparameter tuning and structure selection. The performance scores of the bidirectional RNN model with GRU for 20 kinds of species are as follows: accuracy 97.7%, precision 97.8%, recall 97.8% and F1-score 97.7%. The model resistant to wavenumber drift and cross-instrumental model were also studied for practical application purpose using a subset of Raman spectra by both commercial and laboratory-built Raman spectrometers. The evaluation shows an accuracy of 98.2%. These results indicate that our approach has great potential for blood species identification in real application scenarios.

[1]  Jing Sui,et al.  Discriminating schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data , 2019, EBioMedicine.

[2]  Xuejie Zhang,et al.  Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification , 2019, Cancers.

[3]  H Georg Schulze,et al.  A Fast, Automated, Polynomial-Based Cosmic Ray Spike–Removal Method for the High-Throughput Processing of Raman Spectra , 2013, Applied spectroscopy.

[4]  Xiangquan Zheng,et al.  A practical convolutional neural network model for discriminating Raman spectra of human and animal blood , 2019, Journal of Chemometrics.

[5]  Nicole M. Ralbovsky,et al.  Towards development of a novel universal medical diagnostic method: Raman spectroscopy and machine learning. , 2020, Chemical Society reviews.

[6]  E. Espinoza,et al.  Electrospray ionization mass spectrometric analysis of blood for differentiation of species. , 1999, Analytical biochemistry.

[7]  Yoshitaka Maeno,et al.  Species identification of blood and bloodstains by high-performance liquid chromatography , 2005, International Journal of Legal Medicine.

[8]  I. Lednev,et al.  Forensic Identification of Blood in the Presence of Contaminations Using Raman Microspectroscopy Coupled with Advanced Statistics: Effect of Sand, Dust, and Soil , 2013, Journal of forensic sciences.

[9]  Margarita Osadchy,et al.  Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution , 2017, The Analyst.

[10]  Mechthild Prinz,et al.  Body fluid identification by mass spectrometry , 2013, International Journal of Legal Medicine.

[11]  I. Lednev,et al.  Identification of species’ blood by attenuated total reflection (ATR) Fourier transform infrared (FT-IR) spectroscopy , 2015, Analytical and Bioanalytical Chemistry.

[12]  Kyle C. Doty,et al.  Differentiation of human blood from animal blood using Raman spectroscopy: A survey of forensically relevant species. , 2018, Forensic science international.

[13]  Haibo Zhou,et al.  Understanding the learning mechanism of convolutional neural networks in spectral analysis. , 2020, Analytica chimica acta.

[14]  Igor K Lednev,et al.  Blood species identification for forensic purposes using Raman spectroscopy combined with advanced statistical analysis. , 2009, Analytical chemistry.

[15]  Jing Gao,et al.  Discrimination of Human and Nonhuman Blood by Raman Spectroscopy and Partial Least Squares Discriminant Analysis , 2017 .

[16]  Manhua Liu,et al.  A hybrid Convolutional and Recurrent Neural Network for Hippocampus Analysis in Alzheimer's Disease , 2019, Journal of Neuroscience Methods.

[17]  Igor K Lednev,et al.  Raman spectroscopic signature of blood and its potential application to forensic body fluid identification , 2010, Analytical and bioanalytical chemistry.

[18]  Peter Giere,et al.  Import and export of biological samples from tropical countries–considerations and guidelines for research teams , 2012, Organisms Diversity & Evolution.

[19]  Jürgen Popp,et al.  Model transfer for Raman‐spectroscopy‐based bacterial classification , 2018 .

[20]  Gang Li,et al.  Blood species identification using Near-Infrared diffuse transmitted spectra and PLS-DA method ☆ , 2016 .

[21]  T. Yasuda,et al.  Blood identification and discrimination between human and nonhuman blood using portable Raman spectroscopy , 2017, International Journal of Legal Medicine.

[22]  Jean-Francois Masson,et al.  Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering , 2020, TrAC Trends in Analytical Chemistry.

[23]  Aaron Park,et al.  Baseline correction using asymmetrically reweighted penalized least squares smoothing. , 2015, The Analyst.

[24]  Stefano Ermon,et al.  Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning , 2019, Nature Communications.

[25]  H. Y. Bian,et al.  Fourier based partial least squares algorithm: new insight into influence of spectral shift in "frequency domain". , 2019, Optics express.

[26]  Hao Chen,et al.  Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection , 2017, IEEE Transactions on Biomedical Engineering.

[27]  Ling Lin,et al.  Identification of blood species based on diffuse reflectance and transmission joint spectra with machine learning method , 2018 .

[28]  I. Lednev,et al.  Circumventing substrate interference in the Raman spectroscopic identification of blood stains. , 2013, Forensic science international.

[29]  Nicole M. Ralbovsky,et al.  Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid. , 2020, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[30]  Michalis E. Zervakis,et al.  A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals , 2018, Comput. Biol. Medicine.

[31]  M. Blades,et al.  Raman Spectroscopy of Blood and Blood Components , 2017, Applied spectroscopy.

[32]  Cornelius Courts,et al.  Differentiation of five body fluids from forensic samples by expression analysis of four microRNAs using quantitative PCR. , 2016, Forensic science international. Genetics.

[33]  Vishal Sharma,et al.  Trends of chemometrics in bloodstain investigations , 2018, TrAC Trends in Analytical Chemistry.

[34]  I. Lednev,et al.  Discrimination between human and animal blood by attenuated total reflection Fourier transform-infrared spectroscopy , 2020, Communications Chemistry.

[35]  Kyle C. Doty,et al.  Raman spectroscopy of blood for species identification. , 2014, Analytical chemistry.

[36]  L. Barberini,et al.  1H NMR metabolite fingerprinting as a new tool for body fluid identification in forensic science , 2013, Magnetic resonance in chemistry : MRC.

[37]  Yibin Ying,et al.  Deep learning for vibrational spectral analysis: Recent progress and a practical guide. , 2019, Analytica chimica acta.

[38]  Pengli Bai,et al.  Dual-model analysis for improving the discrimination performance of human and nonhuman blood based on Raman spectroscopy. , 2018, Biomedical optics express.

[39]  Sadasivan Puthusserypady,et al.  An end-to-end deep learning approach to MI-EEG signal classification for BCIs , 2018, Expert Syst. Appl..

[40]  Xinyu Xu,et al.  Fluorescence imaging and Raman spectroscopy applied for the accurate diagnosis of breast cancer with deep learning algorithms. , 2020, Biomedical optics express.

[41]  Lili Zhang,et al.  Rapid histology of laryngeal squamous cell carcinoma with deep-learning based stimulated Raman scattering microscopy , 2019, Theranostics.

[42]  Peng Wang,et al.  Blood species identification based on deep learning analysis of Raman spectra. , 2019, Biomedical optics express.