ИК-спектрография и томография тканей человека и их анализ методами машинного обучения тема диссертации и автореферата по ВАК РФ 05.13.12, кандидат наук Коэн Янив

• Коэн Янив
• кандидат наук
• 2022

Оглавление диссертации кандидат наук Коэн Янив

Contents

LIST OF ABBREVIATIONS

ACKNOLEDGMENTS

INTRODUCTION

The Relevance of the Research

The Objectives and Goals of Dissertation

The Scientific Novelty of the Study

The Practical Significance

The Key Findings of the Thesis to Be Defended

Methodology used in Dissertation

Authenticity of the results

The author's personal contribution

Approbation of Research Results

The list of the published articles where the main scientific results of the thesis are reflected

The Structure of Dissertation

CHAPTER 1. IR TOMOGRAPHY

1.1 Overview

1.2 Current State of the Art

1.3 Theoretical Background of the IR Tomography and IR Spectroscopy of Cancerous and Anomalous Biological Structures Detection and Identification

1.4 Cooling and heating of cancerous structures

1.5 Diameter and depth of the tumor

1.6 Experimental Clinical Tests

1.7 In-Vitro thermal imaging by use of Laparoscopic procedure

1.8 Results and Discussion

1.9 Conclusion

CHAPTER 2. DEVICES AND INSTRUMENTS

2.1 Field and background

2.2 Basic principles of FTIR-ATR detection

2.3 Information yielded

2.4 The means of operation

2.5 Brief Description of Medical I.R.O.S

2.6 Flow chart and short explanation

2.7 DATA BASE AND CLOUD PRESENTATION AND DESCRIPTION

CHAPTER 3. FTIR-ATR DATA CLASSIFICATION

3.1 Problem description: Cancer Detection

3.2 Data preparation and pre-processing

3.3 Machine Learning approach for classification

3.4 Partial least square regression (PLSR) and Principal component regression (PCR)

3

3.5 Training, calibration and validation

3.6 PCR/PLSR Summary

3.7 Linear Discriminant Analysis (LDA)

3.8 Naive Bayes classifier (NBC)

3.9 Conclusions of Machine Learning classifiers

3.10 Spectral biomarkers for discrimination between Normal and Malignant cells

CHAPTER 4. ARTIFICIAL NEURAL NETWORK

4.1 ANN concept - BASIC DEFINITIONS

4.2 Biological Neuron

4.3 Artificial Neuron

4.4 Multi-layer feed forward network

4.5 Feedforward error back-propagation Network

4.6 Basic MLFF network configuration

4.7 Feed-forward ANN classifier design

4.8 Network training Algorithms

4.9 Preliminary practical results

4.10 Conclusions

CHAPTER 5. SUMMARY

CHAPTER 6. PRACTICAL APPLICATIONS

CONCLUSION

REFERENCES

ANNEX: BACKGROUND TO THE SUBJECT

Введение диссертации (часть автореферата) на тему «ИК-спектрография и томография тканей человека и их анализ методами машинного обучения»

Introduction

The Relevance of the Research

Cancer diagnostics is a particularly active area with publications including cervical [1-3], lung [4, 5], prostate [6, 7], colon [8-11], esophageal [12-15], gastric [11], brain [16, 17] and skin [3] cancers, etc. [18-21]. During the recent decades, it was stated by the scientific society some common intrinsic cancers related to openings (orifices) and the current art diagnostic methods.

Nowadays the gold standard for diagnosis involves histopathology based on sectioning and staining of tissues. However, the main problem with this method is that it takes rather long time (several days to several weeks) to obtain pathology results, due to lengthy procedures for preparation of tissues and thorough procedure for pathology evaluation. Furthermore, during the biopsy session, elaborate removal of tissue is required, which can be dolorous and expensive; however, a limited number of samples can be taken. No less important are the problems associated with storage, transportation and further expert analysis of biopsy samples in a laboratory; this increases the expenditures, increases the likelyhood that samples will be mismanaged, contaminated or wasted, and also introduces a significant deceleration in the process of receiving results. Finally, to interprete the biopsy results, microscopic analysis is usually used, leading to qualitative judgemental results that cannot be interpreted consistently.

Therefore, the medical society seeks to elaborate safe diagnosis technologies with more efficient sensitivity, for non-operative detection of internal cancers in their primary phases and differentiation between cancer, neoplasms benign and unspecified malformations of internal tissue (including cysts and polyps).

An important area of investigation in this area is currently the search for opportunities for the earliest possible and non-invasive detection of damaged tissue areas for their prompt removal. Different methods involving optical, acoustical, magnetic and X-ray devices and dedicated techniques have been used in recent studies. In the works by Minsky, confocal Scanning Microscopy was developed, that is an optical imaging technique for increasing optical resolution and contrast. Godfrey Hounsfield presented X-ray computed tomography, CT Scan, that is a medical imaging technique to be used in radiology to get detailed images of the body noninvasively for diagnostic purposes. In the works by Mansfield and Lauterbur, magnetic resonance imaging (MRI) was developed, that is a medical imaging technique to be used in radiology to form pictures of the anatomy and the physiological processes of the body.

For example, in Barrett's and ulcerative colitis, the hallmark for carcinogenesis is flat dysplasia. The current state of the art in this case is taking random biopsy specimens in multiple spots going on a proverbial wild-goose chase. However, obtaining the great amount of biopsy

specimens taken in instinctive spots is overlong, high cost, adds potential complexity, and results in possible false negatives (because typically <5% of mucosa is sampled).

As another example, endeavors to refine detection of adenoma were applied towards endoscopic blind spots (to the rear of folds, flexures) or visualized subtle lesions in the regions of vision (eg, flat and depressed lesions). Active efforts at present have been directed toward improving the endoscope (high-definition, narrow-band imaging, autofluorescence, etc.) or contrast agents (molecular imaging, chromoendoscopy). The mentioned attempts improve the detecting ability but do not destroy the problem completely.

Mid-infrared (MIR) spectroscopy has been recognized as an important analytical technique, and is widely applied for qualitative and quantitative analysis of materials with an increasing interest in addressing complex organic or biologic constituents [22]. IR spectra can be used as a sensitive marker of structural changes of cells and of reorganization occurring in cells and most biomolecules give rise to IR absorption bands between 1800 and 700 cm-1, that are known as the "fingerprint region" or primary absorption region. FTIR spectroscopy and imaging have been applied in medical diagnostic research for many years and the literature is expanding rapidly [1]. The technology has been applied to disease biomarker detection in body fluids such as urine and blood. For example, glucose and cholesterol have been measured in whole blood and serum using IR spectroscopy, offering simple alternatives for monitoring patients with diabetes [4, 23]; similarly, glucose and lactic acid, as potential cancer biomarkers, have been measured in plasma samples [24]; protein and urea have also been measured in blood, and uric acid, phosphate and creatinine have been measured in urine [25]. FTIR spectroscopy has been applied in reproductive biology to assess oocyte quality and in biomarker detection in synovial fluid to diagnose arthritis [25-28]. Renal stone composition has also been determined using FTIR spectroscopy [29-31].

Miscellaneous works testify that ATR-FTIR is useful in analyzing the salivary exosomes from oral cancer patients [29]. FTIR microspectroscopy has also been applied to the detection of stem cells in cancer research [23-25,27] and to the characterization of cell-cycle variations [19]. The two techniques: Fourier-transform infrared spectroscopy and imaging spectroscopy of frozen sections (cryosections) have gained wide research interest aiming for malignancy diagnostics. Achieved results are to a great extent similar to the routine frozen section (FS) pathology examination [27]. These methods received the recognition among the professional society, but still they have not entered the clinical practice due to their shortcomings. Though the field has advanced greatly in the latest years, the principal task remains to develop, translate and implement in the clinical practice a rapid and reliable method that can be used for diagnosis of cancer during the operation. These methods are generally complex and time-consuming, and so are difficult to translate to a clinical setting. It is only relatively recently that major improvements in technology have afforded the sensitivity required to study biological molecules and it is only within the last decade or so that FTIR imaging has become available [21, 16]. Some of the most important technological developments include the interferometer, highly sensitive detectors and array detectors, powerful light sources and attenuated total reflection (ATR) technology [16, 32].

Advances in computing power have also enabled rapid processing of large datasets. Thus developments should be implemented in the Medical IROS (Medical Infra Red Optical system) [32].

The approach to diagnostic process involving ATR-FTIR seems very promising. However, the following issues remain unresolved: a) methods of identification of spectral patterns that distinguish cancerous from healthy tissue; b) methods of datasets analysis; c) simple and stable instrumentations.

The Objectives and Goals of Dissertation

Thus, the objective of this work is to provide a non-invasive, fast, compact, remote, portable and highly sensitive intraoperative diagnostic methodology and the corresponding tool. To resolve this issue, we plan to employ measurements of the contrast of the temperature difference against the background involving ATR-FTIR.

It is only relatively recently that major improvements in technology have afforded the sensitivity required to study biological molecules and it is only within the last decade or so that FTIR imaging has become available. Some of the most important technological developments include the interferometer, highly sensitive detectors and array detectors, powerful light sources and attenuated total reflection (ATR) technology. Advances in computing power have also enabled rapid processing of large datasets. Thus, developments are implemented in the in Medical Infra-Red Optical System (IROS).

To achieve this goal, it is necessary to solve the following tasks:

1. To develop reproducible IR imaging and spectroscopy techniques that might be developed into clinical tools for earlier non-invasive diagnosis of human inner tissue anomalies -tumors and diseases.

2. To select and find more attractive from existing current diagnostic analytical and statistical methods to obey and mitigate some of lacking, and propose more optimal techniques for raw data analysis observed experimentally.

3. To use a thermal IR-camera and FTIR spectrometer in order to make such selection of existing techniques, which can be simple and stable instrumentations enough for future hospital and clinical installation.

4. To develop the attractive and optimal machine learning methods that are sufficiently simple and inexpensive so that translation into clinical usage could become feasible.

5. To explore and find the best machine-learning tool for use with spectral analysis of human tissue earlier non-invasive diagnosis and differentiation of cancerous and non-cancerous skin anomalous.

The Scientific Novelty of the Study

The present thesis contributes to solving problems of earlier non-invasive diagnosis of human tissue anomalies - tumors and diseases, based on the theoretical framework of IR tomography and spectrography, on more attractive instrumentation usage for this purposes, on the analytical and statistical methods of raw data analysis, and on elements of Artificial Neural Networks (ANN) and Machine Learning algorithms. Thus:

1. we employed a cloud data base with machine learning methods in the area of cancerous skin identification and classification, where this has not previously been applied, which allows to increase the ability of the system to improve the identification and classification rate of different biochemical composition of tissues and to help the physician as a real time on-site decision support system;

2. we experimentally established the heat signatures of different human body tissues corresponding to normal and abnormal states;

3. we proposed a new method of detecting and identification of gastric, colorectal and cervical cancers, that is different with respect to other methods in that the conventional methods are based on the subjective inspection in the visible spectral range of the physician, whereas in our method we are based on the overheated characteristic of cancerous tissues and detecting these anomalies with a NIR or MIR camera;

4. we proposed a new method of preliminary classification of anomalies, that is different with respect to other methods in that it is done using IR optical band in the range of 3-12 ^m;

5. we proposed a new method for early detection or Cancer removal by thermal IR approach based on passive imaging of heat signature changes in tumors due to minute changes of environmental temperatures around these tumors by applying heating and cooling methods on the tissue, this method allows for screening and for characterizing of these tumors more accurately at the earlier stages of their spatial-temporal evolution which cannot be detected by human or conventional machine vision systems . These new methods of heating and cooling are important as they show that cancer removal can be monitor non-invasively to ensure complete removal of cancer inside/outside of the human body.

The Practical Significance

1. The practical applications of the proposed approach, based on combined platform of multidisciplinary techniques, theoretical and experimental, resulted in creation of a Medical IROS that is a tabletop device for real-time tissue diagnosis that utilizes FTIR spectroscopy and the ATR principle to accurately diagnose the tissue.

2. Within the scope of our findings, we developed a new endoscope based on an array of infrared and visual optic micro detectors operating in the waveband range of 3-12 p,m

working both in integral and spectral regimes based on the sign and amplitude of the contrast of cancerous anomalies with respect to those for normal living tissues.

3. A trained Artificial Neural Network was created serving to predict cancer and other pathologies based on measurements by FTIR-ATR device. The reliability of the proposed neural network method was examined on the data collected through Medical IROS (FTIR-ATR) device and obtained by a biopsy.

4. By using a combination of IR thermal imaging and machine learning spectral analysis, a decision support system for real time, on site, early detection and identification of cancer was built.

5. The medical IROS along with the decision support system serve as a basis to perform a realtime optical biopsy or spectral histopathology (SHP) of tissues on-site in the operation room. This is a powerful tool for real-time, on-site, cost-effective, simple-to-use, non-destructive, non-operator, early non-invasive detection and identification of different kinds of human tissue inner cancers.

The Key Findings of the Thesis to Be Defended

1. A new approach to IR tomography and spectrography with the corresponding theoretical and conceptual background.

2. An improved method of early detection by thermal IR approach based on passive imaging of heat signature changes in tumors due to minute changes of environmental temperatures around these tumors after applying heating and cooling methods on the tissue, which allows for screening and for characterizing of these tumors more accurately at the earlier stages of their spatial-temporal evolution.

3. New experimental techniques based on usage of ATR-FTIR spectroscopy as a diagnostic tool for quick identification of cancerous diseases during operation.

4. Adaptation of Artificial Neural Network structure algorithms to investigation of tissue anomalies - tumors, cancers, and metastases, for express analysis of such kinds of anomalies.

5. A unified platform for combination of elements of theoretical framework, ATR-FTIR spectroscopy, neuron structure algorithms and elements of machine learning, which allows a specialist in medicine to obtain a simple but powerful inexpensive tool for early non-contact detection and identification of tumors and the ability to monitor tumor removal during the operation by using a sensitive thermal camera and by heating or cooling technique.

Заключение диссертации по теме «Системы автоматизации проектирования (по отраслям)», Коэн Янив

Conclusion

The human body sometimes develops tumors and other internal lesions, which destroys the functionality of affected organs and ultimately lead to death. Their early detection and identification is critical for the health and survival of the patients.

1) A new approach to IR tomography and spectrography with the corresponding theoretical and conceptual background.

2) An improved method of early detection by thermal IR approach based on passive imaging of heat signature changes in tumors due to minute changes of environmental temperatures around these tumors after applying heating and cooling methods on the tissue, which allows for screening and for characterizing of these tumors more accurately at the earlier stages of their spatial-temporal evolution.

3) New experimental techniques based on usage of ATR-FTIR spectroscopy as a diagnostic tool for quick identification of cancerous diseases during operation.

4) Adaptation of Artificial Neural Network structure algorithms to investigation of tissue anomalies - tumors, cancers, and metastases, for express analysis of such kinds of anomalies.

5) A unified platform for combination of elements of theoretical framework, ATR-FTIR spectroscopy, neuron structure algorithms and elements of machine learning, which allows a specialist in medicine to obtain a simple but powerful inexpensive tool for early non-contact detection and identification of tumors and the ability to monitor tumor removal during the operation by using a sensitive thermal camera and by heating or cooling technique.

Список литературы диссертационного исследования кандидат наук Коэн Янив, 2022 год

References

To Introduction

1. Dekel, B.-Z,. A. Zilberman, N. Blaunstein, Y. Cohen, M.B. Sergeev,L.L. Varlamova and G.S. Polishchuk (2016), Method of Infrared Thermography for Earlier Diagnostics of Gastric Colorectal and Cervical Cancer. In: Chen YW., Tanaka S., Howlett R., Jain L. (eds) Innovation in Medicine and Healthcare 2016. InMed 2016. Smart Innovation, Systems and Technologies, Springer, Cham. vol. 60. pp. 83-92, DOI: https://doi.org/10.1007/978-3-319-39687-3_8

2. Lewis PD, Lewis KE, Ghosal R, Bayliss S, et al., "Evaluation of FTIR spectroscopy as a diagnostic tool for lung cancer using sputum", BMC Cancer, vol. 10, pp. 640-649, 2010.

3. Baker M. J, Gazi E, Brown M. D, Shanks J. H, et. al., "FTIR based spectroscopic analysis in the identication of clinically aggressive prostate cancer", British Journal of Cancer, vol. 99, pp. 1859-1866, 2008.

4. Cohen, Y., ,A. Zilberman, B.-Z. Dekel, E. Krouk, "Real-Time, On-Site, Machine Learning Identification Methodology of Intrinsic Human Cancers Based on Infra- Red Spectral Analysis - Clinical Results. Proceedings of The 11th International Multi-Conference on Complexity, Informatics and Cybernetics (IMCIC 2020) Orlando, USA, March, 2020.

5. Mackanos MA and Contag C. H., "FTIR microspectroscopy for improved prostate cancer diagnosis", Trends in Biotechnology, vol. 27, pp. 661-663, 2009.

6. Rigas B, Morgello S, Goldman I. S and Wong P. T. T., "Human colorectal cancers display abnormal Fourier-transform infrared spectra", Proceedings of the National Academy of Science of the United States of America, vol. 87, pp. 8140-8144, 1990.

7. Mackanos M. A, Hargrove J, Wolters R, Du C. B, et al., "Use of an endoscope compatible probe to detect colonic dysplasia with Fourier transform infrared spectroscopy", Journal of Biomedical Optics, vol. 14, 2009. 044006-1-044006-8.

8. Argov S, Ramesh J, Salman A, Sinelnikov, et al., "Diagnostic potential of Fourier-transform infrared microspectroscopy and advanced computational methods in colon cancer patients", Journal of Biomedical Optics , vol. 7, pp. 248-254, 2002.

9. Kallenbach-Thieltges A, GroBeruschkamp F, Mosig A, Diem M, et al., "Immunohistochemistry, histopathology and infrared spectral histopathology of colon cancer tissue sections", Journal of Biophotonics, vol. 6, pp. 88-100, 2013.

10. Wang J. S, Shi J. S, Xu Y. Z, Duan X. Y, Zhang L, et al. "FT-IR spectroscopic analysis of normal and cancerous tissues of esophagus", World Journal of Gastroenterology, vol. 9, pp. 1897-1899, 2003.

11. Maziak D. E, Do M. T, Shamj i F. M, Sundaresan S. R, et al. "Fourier-transform infrared spectroscopic study of characteristic molecular structure in cancer cells of esophagus: an exploratory study", Cancer Detection and Prevention, vol. 31, pp. 244-253, 2007.

12. Quaroni L and Casson A. G., "Characterization of Barrett esophagus and Esophageal adenocarcinoma by Fourier-transform infrared microscopy", Analyst, vol. 134, pp. 12401246, 2009.

13. Wang T. D, Triada_Lopoulos G, Crawford J. M, Dixon L.R, et. al., "Detection of endogenous biomolecules in Barrett's esophagus by Fourier transform infrared spectroscopy", Proceedings of the National Academy of Science of the United States of America, vol. 104, pp. 15864-15869, 2007.

14. Petibois C., and Déléris G. "Chemical mapping of tumor progression by FT-IR imaging: towards molecular histopathology", Trends in Biotechnology, vol. 24, pp. 455-462, 2006.

15. Heise H. M., and Bittner A., "Multivariate calibration for physiological samples using infrared spectra with choice of different intensity data", Journal of Molecular Structure, vol. 348, pp. 127-130, 1995.

16. https://www.lynred.com/produit/atto640

17. Walsh M. J, et al., "Fourier transform infrared micro spectroscopy identifies symmetric PO2- modifications as a marker of the putative stem cell region of human intestinal crypts", J. Stem Cells, vol. 26, pp. 108-118, 2008.

18. Siebert F., and Hildebrandt P., Vibrational Spectroscopy in Life Science, Weinheim, FRG: Wiley-VCH Verlag GmbH & Co. KGaA, 2003.

19. Wartewig S., "Basic principles of vibrational spectroscopy", in IR and Raman Spectroscopy, pp. 27-33, Weinheim, FRG: Wiley-VCH Verlag GmbH & Co. KGaA, 2006.

20. Goormaghtigh E, Raussens V., and Ruysschaert J. M., "Attenuated total reflection infrared spectroscopy of proteins and lipids in biological membranes", Biochimica et Biophysica Acta, vol. 1422, pp. 105-185, 1999.

21. Shussman, N., and Y. Mintz, "Laparoscopic Infrared Imaging — the Future Vascular Map", Journal of Laparoendoscopic & Advanced Surgical Techniques, 2011. http://doi.org/10.1089/lap.2010.0474

22. Lin, Shan-Yang, Li, Mei-Jane, Cheng, Wen-Ting, FT-IR and Raman vibrational microspectroscopies used for spectral biodiagnosis of human tissues (review), Journal of Spectroscopy, volume 21, 2007. DOI: https://doi.org/10.1155/2007/278765

23. Cohen, , Y., A. Zilberman, B.-Z. Dekel, E. Krouk, "Real-Time, On-Site, Machine Learning Identification Methodology of Intrinsic Human Cancers Based on Infra- Red Spectral Analysis - Clinical Results. Journal of Systemics, Cybernetics and Informatics (JSCI) , vol. 18, No. 2 , 2020.

24. Cohen Y., Zilberman A., Dekel B.Z., Krouk E. (2020) Artificial Neural Network in Predicting Cancer Based on Infrared Spectroscopy. In: Czarnowski I., Howlett R., Jain L. (eds), Intelligent Decision Technologies. IDT 2020. Smart Innovation, Systems and Technologies, Springer, Singapore, vol. 193, pp. 141-153, 2020. DOI: https://doi.org/10.1007/978-981-15-5925-9_12.

25. Petrich, W., "Mid-infrared and Raman spectroscopy for medical diagnostics". Applied Spectroscopy Reviews, vol. 36: pp. 181-237, 2001.

26. Zlotogorsk- Hurvitz, A., B-Z. Dekel, D. Malonek, R. Yahalom, M. Vered, "FTIR-based spectrum of salivary exosomes coupled with computational-aided discriminating analysis in the diagnosis of oral cancer" , Journal of Cancer Research and Clinical Oncology , Issue 145, pp. 685-693, 2019.

27. Mark S, Sahu R.K, Kantarovich K, Podshyvalov A, Guterman H, Goldstein J, Jagannathan R, Argov S and Mordechai S, "Fourier transform infrared microspectroscopy as a quantitative diagnostic tool for assignment of premalignancy grading in cervical neoplasia", Journal of Biomedical Optics vol. 9, pp. 558-567, 2004.

28. Bird B, Miljkovic M, Remiszewski S, et al., ""Infrared spectral histopathology (SHP): a novel diagnostic tool for the accurate classification of lung cancer", Laboratory Investigation, vol. 92, pp. 1358-1373, 2012.

29. Taylor, S., Cheung, K., Patel, I. et al., "Infrared spectroscopy with multivariate analysis to interrogate endometrial tissue: a novel and objective diagnostic approach", British Journal Cancer, vol. 104, pp. 790-797, 2011. https://doi.org/10.1038/sj.bjc.6606094

30. Sahu RK and Mordechai S., "Fourier transform infrared spectroscopy in cancer detection", Future Oncology, vol 1, pp. 635-647, 2005.

31. Mordechai S, Sahu RK, Hammody Z, Mark S, et al., "Possible common biomarkers from FTIR microspectroscopy of cervical cancer and melanoma", Journal of Microscopy, vol. 215, pp. 86-91, 2004.

32. Rogalski, A., "Next decade in infrared detectors," Proc. SPIE 10433, Electro-Optical and Infrared Systems: Technology and Applications XIV, 104330L, 9 October 2017, doi: 10.1117/12.2300779

33. Ahmed, S., Galle, P. R., & Neumann, H., "Molecular endoscopic imaging: the future is bright", Therapeutic Advances in Gastrointestinal Endoscopy, 2019. https://doi.org/10.1177/2631774519867175.

To Section 1

1. Bray, F. , Ferlay, J. , Soerjomataram, I. , Siegel, R. L., Torre, L. A. and Jemal, A., "Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries", CA: Cancer Journal for Clinicians, vol. 68, pp. 394-424, 2018, doi:10.3322/caac.21492 (2018).

2. Dekel, B.-Z., A. Zilberman, N. Blaunstein, Y. Cohen, M.B. Sergeev, L.L. Varlamova and G.S. Polishchuk, "Method of Infrared Thermography for Earlier Diagnostics of Gastric Colorectal and Cervical Cancer", in: Chen YW., Tanaka S., Howlett R., Jain L. (Editors) Innovation in Medicine and Healthcare 2016. InMed 2016. Smart Innovation, Systems and Technologies, vol. 60. Springer, Cham, pp. 83-92, 2016, DOI: https://doi.org/10.1007/978-3-319-39687-3 8 (2016).

3. Christodolos, S., and C. Christina, "Thermal Heterogeneity Constitutes A Marker for the Detection of Malignant Gastric Lesions In Vivo", Journal of Clinical Gastroenterology, vol. 36, pp 215-218, 2003.

4. Theophilou, G., K.M.G. Lima, P. L. Martin-Hirsch, H. F. Stringfellow and F.L. Martin, "ATR-FTIR spectroscopy coupled with chemometric analysis discriminates normal, borderline and malignant ovarian tissue: classifying subtypes of human cancer", Analyst, vol. 141, pp. 585-594, 2016.

5. Dekel, B.-Z., A. Zlotogorski-Hurvitz, D. Malonek, R. Yahalom, and M. Vered, "FTIR-based spectrum of\salivary exosomes coupled with computational-aided discriminating analysis in the diagnosis of oral cancer", Journal of Cancer Research and Clinical Oncology . https://doi.org/10.1007/s00432-018-02827-6 , 2019,

6. Shussman, N., and Y. Mintz, "Laparoscopic Infrared Imaging — The Future Vascular Map", Journal of Laparoendoscopic & Advanced Surgical Techniques. Nov. 2011. http://doi.org/10.1089/lap.2010.0474.

7. Rogalski, A., "Next decade in infrared detectors," Proc. SPIE 10433, Electro-Optical and Infrared Systems: Technology and Applications XIV, 104330L (9 October 2017); doi: 10.1117/12.2300779

8. Robert, P., et al , "Low power consumption infrared thermal sensor array forsmart detection and thermal imaging applications", AMA Conferences 2013 - SENSOR 2013, OPTO 2013, IRS 2 2013, DOI 10.5162/irs2013/i2.1

9. Xie, W. , McCahon, P. , Jakobsen, K. and Parish, C., "Evaluation of the ability of digital infrared imaging to detect vascular changes in experimental animal tumours", Int. J. Cancer, vol. 108, pp. 790-794, 2004, doi:10.1002/ijc.11618

10. Song, C. , Appleyard, V. , Murray, K. , Frank, T. , Sibbett, W. , Cuschieri, A. and Thompson, A., "Thermographic assessment of tumor growth in mouse xenografts", Int. J. Cancer, vol. 121, pp. 1055-1058, 2007, doi:10.1002/ijc.22808

11. Berz, Reinhold and Claus E.E. Schulte-Uebbing. "MammoVision (Active Functional Infrared Breast Thermography) Compared to X-Ray Mammography-114 Cases Evaluated", 2010

12. Lahiri, B.B., S. Bagavathiappan, T. Jayakumar, and John Philip, "Medical applications of infrared thermography: A review". Infrared Physics & Technology, vol. 55, No. 4, pp. 221235, 2012, https://doi.org/10.1016/unfrared.2012.03.007

13. Curkovic, S. et al., "Medical thermography (digital infrared thermal imaging - DITI) in pediatric forearm fractures - A pilot study Injury", vol. 46, pp. S36 - S39, 2015, DOI: https://doi.org/10.1016/uniury.2015.10.044

14. Sivanandam, S., Anburajan, M., Venkatraman, B. et al., "Medical thermography: a diagnostic approach for type 2 diabetes based on non-contact infrared thermal imaging", Endocrine, vol. 42pp. 343-345, 2012, https://doi.org/10.1007/s12020-012-9645-8

15. Magalhaes C, Vardasca R, and Mendes J., "Recent use of medical infrared thermography in skin neoplasms", Skin Res Technol vol. 10, pp. 1-5, 2018, https://doi.org/10.1111/srt.12469

16. Chaudhry, S., R. Fernando, H. Screen, and C. Waugh, "The use of medical infrared thermography in the detection of tendinopathy: a systematic review", Physical Therapy Reviews, Art Tucker & Dylan Morrissey, 2016, DOI:10.1080/10833196.2016.1223575

17. Breast Cancer Detection Using Infrared Thermal Imaging and a Deep Learning Model Sensors (Basel). 2018, vol. 18, No. 9 pp. 2799-2819, 2018, doi: 10.3390/s1809279

18. Kosus, N., Kosus, A, Duran, M., Simavli, S., and Turhan, N., "Comparison of standard mammography with Digital mammography and Digital infrared thermal imaging for breast cancer screening", J. Turk. Ger. Gynecol. Assoc. vol. 11, pp. 152-157, 2010.

19. Mambou, S., Maresova, P., Krejcar, O., Selamat, A., and Kuca, K. "Breast Cancer Detection Using Modern Visual IT Techniques", in Modern Approaches for Intelligent Information and Database Systems; Andrzej, S., Adrianna, K., Manuel, N., Quang Thuy, H., Eds.; Springer: Berlin, Germany, Vol. 769, pp. 397-407, 2018.

20. Roy, Hemant K. et al., "Spectroscopic Applications in Gastrointestinal Endoscopy Clinical Gastroenterology and Hepatology", vol. 10, Issue 12, pp. 1335 - 1341, 2011.

21. Murthy S, Goetz M, Hoffman A, et al., "Novel colonoscopic imaging", Clin Gastroenterol Hepatol , vol. 10, pp. 984-987, 2012.

22. https://www.lynred.com/produit/atto640

23. https://www.lynred.com/produit/m80

24. https://www.flir.com/flirone

25. Cohen, Y., B.-Z. Dekel, E. Krouk, and N. Blaunstein "Method of Infrared Thermography for Earlier Diagnostics of Gastric Colorectal and Cervical Cancer". EC Gastroenterology and Digestive System vol. 6, series 10 pp. 916-933, 2019.

To Section 3

1. Jackson, M., and Mantsch, H. H., Infrared Spectroscopy of Biological Molecules, New York: Wiley, 1996.

2. Naumann, D., "FT-infrared and FT-Raman spectroscopy in biomedical research", Appl. Spectrosc. Rev., vol. 36, pp. 239-298, 2001.

3. Petrich, W., "Mid-infrared and Raman spectroscopy for medical diagnostics", Appl. Spectrosc. Rev., vol. 36, pp. 181-237, 2001.

4. Lin, S.-Y., Li, M.-J., and Cheng, W.-T, "FT-IR and Raman vibrational microspectroscopies used for spectral biodiagnosis of human tissues", Spectroscopy, vol. 21, pp. 1-30, 2007.

5. Kraft, C., and Sergo, V., "Biomedical applications of Raman and infrared spectroscopy to diagnose tissues", Spectroscopy, vol. 20, pp. 195-218, 2006.

6. Ellis, D. I., and Goodacre, R., "Metabolic fingerprinting in disease diagnosis: biomedical applications of infrared and Raman spectroscopy", Analyst, vol. 131, pp. 875-885, 2006.

7. Sahu, R. K., and Moderdechai, M., "Infrared transform infrared spectroscopy in cancer detection", Future Oncology. vol. 1, pp. 635-647, 2005.

8. Cohen, Y. , A. Zilberman, B.-Z. Dekel, and E. Krouk, "Real-Time, On-Site, Machine Learning Identification Methodology of Intrinsic Human Cancers Based on Infra- Red Spectral Analysis - Clinical Results. Proceedings of The 11th International MultiConference on Complexity, Informatics and Cybernetics (IMCIC 2020), Orlando, USA, March, 2020, pp 72-77

9. Cohen, Y. , A. Zilberman, B.-Z. Dekel, and E. Krouk. "Real-Time, On-Site, Machine Learning Identification Methodology of Intrinsic Human Cancers Based on Infra- Red Spectral Analysis - Clinical Results", Journal of Systemic, Cybernetics and Informatics (JSCI), vol. 18, No. 2 , 2020.

To Section 4

1. Yang, H., Griffiths, P.R., Tate, J.D., "Comparison of partial least squares regression and multi-layer neural networks for quantification of non-linear systems and application to gas phase Fourier transform infrared spectra", Analytica Chimica Acta, vol. 489, pp. 125-136, 2003.

2. Lasch, P., Stammler, M., Zhang, M., Baranska, M., Bosch, A., Majzner, K., "FT-IR hyperspectral imaging and artificial neural network analysis for identification of pathogenic bacteria", Analytical Chemistry, vol. 90, No. 15, pp. 8896-8904, 2018.

3. Lasch, P., Diem, M., Hansch, W., Naumann, D.. "Artificial neural networks as supervised techniques for FT-IR microspectroscopic imaging". J. Chemom., vol. 20, No. 5, pp. 209220, 2006.

4. Cohen, Y., A. Zilberman, B.-Z. Dekel, and E. Krouk. "Artificial Neural Network in Predicting Cancer Based on Infrared Spectroscopy". Intelligent Decision Technologies, Smart Innovation, Systems and Technologies 193, Springer I. Czarnowski et al. (eds.), KES IDT 2020

5. DOI: https://doi.org/10.1007/978-981-15-5925-9_12.

To Section 6

1. Arcoptix S.A , http://www.arcoptix.com

2. Mark S, Sahu RK, Kantarovich K, Podshyvalov A, Guterman H, Goldstein J, Jagannathan R, Argov S and Mordechai S (2004). Fourier transform infrared microspectroscopy as a quantitative diagnostic tool for assignment of premalignancy grading in cervical neoplasia. Journal of Biomedical Optics 9: 558-567.

3. Bird B, Miljkovic M, Remiszewski S, Akalin A, KonMand DiemM(2012). Infrared spectral histopathology (SHP): a novel diagnostic tool for the accurate classication of lung cancer. Laboratory Investigation 92: 1358-1373.

4. Patel II, Harrison WJ, Kerns JG, Filik J,Wehbe K, Carmichael PL, Scott AD, Philpott MP, Frogley MD, Cinque G and Martin FL (2012). Isolating stem cells in the interfollicular epidermis employing synchrotron radiation-based Fourier-transform infrared microspectroscopy and focal plane array imaging. Analytical and Bioanalytical Chemistry 404:1745-1758.

5. Zhao R, Quaroni L and Casson AG (2010). Fourier transform infrared (FTIR ( spectromicroscopic characterization of stem-like cell populations in human esophageal normal and adenocarcinoma cell lines. Analyst 135: 53-61.

6. Petrich W (2001). Mid-infrared and Raman spectroscopy for medical diagnostics. Applied Spectroscopy Reviews 36: 181-237.204

7. Budinova G, Salva J and Volka K (1997). Application of molecular spectroscopy in the mid-infrared region to the determination of glucose and cholesterol in whole blood and in blood serum. Applied Spectroscopy 51: 631-635.

8. Hosaf<i G, Klein O, Oremek G and Mantele W (2007). Clinical chemistry without reagents? An infrared spectroscopic technique for determination of clinically relevant constituents of body _uids. Analytical and Bioanalytical Chemistry 387:1815-1822.

9. Petibois C, Gionnet K, Gon<alves M, Perromat A, MoennerMand Deleris G (2006). Analytical performances of FT-IR spectrometry and imaging for concentration measurements within biological _uids, cells, and tissues. Analyst 131: 640-647.

10. Ellis DI and Goodacre R (2006). Metabolic _ngerprinting in disease diagnosis: biomedical applications of infrared and Raman spectroscopy. Analyst 131: 875-885.

11. Channa NA, Ghangro AB, Soomro AM and Noorani L (2007). Analysis of kidney stones by FTIR spectroscopy. JLUMHS 6: 66-73.

12. Paluszkiewicz C, Jan Sciesinski and Galka M (1988). Analysis of renal stones by FTIR spectroscopy. Mikrochimica Acta I: 45-48.

13. Sahu RK and Mordechai S (2005). Fourier transform infrared spectroscopy in cancer detection. Future Oncology 1: 635-647.

14. Mordechai S, Sahu RK, Hammody Z, Mark S, Kantarovich K, Guterman H, Podshyvalov A, Goldstein J and Argov S (2004). Possible common biomarkers from FTIR microspectroscopy of cervical cancer and melanoma. Journal of Microscopy 215: 86-91.

15. Lewis PD, Lewis KE, Ghosal R, Bayliss S, Lloyd AJ, Wills J, Godfrey R, Kloer P and Mur LAJ (2010). Evaluation of FTIR spectroscopy as a diagnostic tool for lung cancer using sputum. BMC Cancer 10: 640-649.

16. Baker MJ, Gazi E, Brown MD, Shanks JH, Gardner P and Clarke NW(2008). FTIRbased spectroscopic analysis in the identi_cation of clinically aggressive prostate cancer. British Journal of Cancer 99: 1859-1866.

17. Mackanos MA and Contag CH (2009). FTIR microspectroscopy for improved prostate cancer diagnosis. Trends in Biotechnology 27: 661-663.205

18. Rigas B, Morgello S, Goldman IS andWong PTT (1990). Human colorectal cancers display abnormal Fourier-transform infrared spectra. Proceedings of the National Academy of Science of the United States of America 87: 8140-8144.

19. Mackanos MA, Hargrove J, Wolters R, Du CB, Friedland S, Soetikno RM, Contag CH, Arroyo MR, Crawford JM and Wang TD (2009). Use of an endoscopecompatible probe to detect colonic dysplasia with Fourier transform infrared spectroscopy. Journal of Biomedical Optics 14: 044006-1-044006-8.

20. Argov S, Ramesh J, Salman A, Sinelnikov I, Goldstein J, Guterman H and Mordechai S (2002). Diagnostic potential of Fourier-transform infrared microspectroscopy and advanced computational methods in colon cancer patients. Journal of Biomedical Optics 7: 248-254.

21. Kallenbach-Thieltges A, Großerüschkamp F, Mosig A, Diem M, Tannapfel A and Gerwert K (2013). Immunohistochemistry, histopathology and infrared spectral histopathology of colon cancer tissue sections. Journal of Biophotonics 6: 88-100.

22. Wang JS, Shi JS, Xu YZ, Duan XY, Zhang L,Wang J, Yang LM,Weng SF andWu JG (2003). FT-IR spectroscopic analysis of normal and cancerous tissues of esophagus. World Journal of Gastroenterology 9: 1897-1899.

23. Maziak DE, Do MT, Shamji FM, Sundaresan SR, Perkins DG andWong PTT (2007). Fourier-transform infrared spectroscopic study of characteristic molecular structure in cancer cells of esophagus: an exploratory study. Cancer Detection and Prevention 31: 244253.

24. Quaroni L and Casson AG (2009). Characterization of Barrett esophagus and esophageal adenocarcinoma by Fourier-transform infrared microscopy. Analyst 134: 1240-1246.

25. Wang TD, Triada_lopoulos G, Crawford JM, Dixon LR, Bhandari T, Sahbaie P, Friedland S, Soetikno R and Contag CH (2007). Detection of endogenous biomolecules in Barrett's esophagus by Fourier transform infrared spectroscopy. Proceedings of the National Academy of Science of the United States of America 104:15864-15869.

26. Petibois C and Deleris G (2006). Chemical mapping of tumor progression by FT-IR imaging: towards molecular histopathology. Trends in Biotechnology 24: 455-462.206

27. Walsh MJ, Fellous TG, Hammiche A, Lin WR, Fullwood NJ, Grude O, Bahrami F, Nicholson JM, Cotte M, Susini J, Pollock HM, Brittan M, Martin-Hirsch PL, Alison MR and Martin FL (2008). Fourier transform infrared microspectroscopy identifies symmetric PO2- modi_cations as a marker of the putative stem cell region of human intestinal crypts. Stem Cells 26: 108-118.

28. Boydston-White S, Romeo M, Chernenko T, Regina A, Miljkovic M and Diem M (2006). Cell-cycle-dependent variations in FTIR micro-spectra of single proliferating HeLa cells: principal component and arti_cial neural network analysis. Biochimica et Biophysica Acta 1758: 908-914.

29. Jessen TE, Höskuldsson AT, Bjerrum PJ, Verder H, S0rensen L, Bratholm PS, Christensen B, Jensen LS and Jensen MAB (2014). Simultaneous determination of glucose, triglycerides, urea, cholesterol, albumin and total protein in human plasma by Fourier transform infrared spectroscopy: direct clinical biochemistry without reagents. Clinical Biochemistry 47: 1306-1312.

30. Low-Ying S, Shaw RA, Leroux M and Mantsch HH (2002). Quantitation of glucose and urea in whole blood by mid-infrared spectroscopy of dry _lms. Vibrational Spectroscopy 28: 111-116.

31. Heise HM and Bittner A (1995). Multivariate calibration for physiological samples using infrared spectra with choice of different intensity data. Journal of Molecular Structure 348: 127-130.

32. PetrichW, Dolenko B, Früh J, Ganz M, Greger H, Jacob S, Keller F, Nikulin AE, Otto M, Quarder O, Somorjai RL, Staib A, Werner G and Wielinger H (2000). Disease pattern recognition in infrared spectra of human sera with diabetes mellitus as anexample. Applied Optics 39: 3372-3379.

33. Lacombe C, Untereiner V, Gobinet C, Zater M, Sockalingum GD and Garnotel R (2015). Rapid screening of classic galactosemia patients: a proof-of-concept study using high-throughput FTIR analysis of plasma. Analyst 140: 2280-2286.

34. Scaglia E, Sockalingum GD, Schmitt J, Gobinet C, Schneider N, Manfait M and Thie_n G (2011). Noninvasive assessment of hepatic _brosis in patients with chronic hepatitis C using serum Fourier transform infrared spectroscopy. Analytical and Bioanalytical Chemistry 401: 2919-2925.207

35. Fabian H, Lasch P and Naumann D (2005). Analysis of bio_uids in aqueous environment based on mid-infrared spectroscopy. Journal of Biomedical Optics 10:031103-1-03110310.

36. Ollesch J, Drees SL, Heise HM, Behrens T, Brüning T and Gerwert K (2013). FTIR spectroscopy of bio_uids revisited: an automated approach to spectral biomarker identification. Analyst 138: 4092-4102.

37. Hands JR, Abel P, Ashton K, Dawson T, Davis C, Lea RW, Mcintosh AJS and Baker MJ (2013). Investigating the rapid diagnosis of gliomas from serum samples usinginfrared spectroscopy and cytokine and angiogenesis factors. Analytical and Bioanalytical Chemistry 405:7347-7355.

38. Gajjar K, Trevisan J, Owens G, Keating PJ, Wood NJ, Stringfellow HF, Martin-Hirsch PL and Martin FL (2013). Fourier-transform infrared spectroscopy coupled with a classi_cation machine for the analysis of blood plasma or serum: a novel diagnostic approach for ovarian cancer. Analyst 138: 3917-10.

39. Khanmohammadi M, Garmarudi AB, Ramin M and Ghasemi K (2013). Diagnosis of renal failure by infrared spectrometric analysis of human serum samples and soft independent modeling of class analogy. Microchemical Journal 106: 67-72.

40. V. V. Tuchin, Lasers and Fibre Optics in Biomedical Science, 2nd ed., Fizmatlit, Moscow (2010).

41. Baker, M.J. et el., 2014. Using Fourier transform IR spectroscopy to analyze biological materials. Nature Protocols 9, 1771-1791.

42. Griffiths, P.R., De Haseth, J.A., 2007. Fourier transform infrared spectrometry, Second ed. John Wiley and Sons, New Jersey.

43. Williams, D.H., Fleming, I., Sykes, P., 1995. Spectroscopic methods in organic chemistry, Fifth ed. McGraw-Hill London.

44. Painter, P.C., Coleman, M.M., Koenig, J.L., 1982. Theory of vibrational spectroscopy and its application to polymeric materials. John Wiley and Sons, Inc., New York.

45. Movasaghi, Z., Rehman, S., Rehman, I.U., 2007. Raman Spectroscopy of Biological Tissues. Applied Spectroscopy Reviews 42, 493-541.

46. Movasaghi, Z., Rehman, S., ur Rehman, D.I., 2008. Fourier transform infrared (FTIR) spectroscopy of biological tissues. Applied Spectroscopy Reviews 43, 134-179.

47. Kelly, J.G., Trevisan, J.l., Scott, A.D., Carmichael, P.L., Pollock, H.M., Martin-Hirsch, P.L., Martin, F.L., 2011. Biospectroscopy to metabolically profile biomolecular structure: a multistage approach linking computational analysis with biomarkers. Journal of Proteome Research 10, 1437-1448.