Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Early-stage detection of cutaneous melanoma can vastly increase the chances of cure. Excision biopsy followed by histological examination is considered the gold standard for diagnosing the disease, but requires long high-cost processing time, and may be biased, as it involves qualitative assessment by a professional. In this paper, we present a new machine learning approach using raw data for skin Raman spectra as input. The approach is highly efficient for classifying benign versus malignant skin lesions (AUC 0.98, 95% CI 0.97-0.99). Furthermore, we present a high-performance model (AUC 0.97, 95% CI 0.95-0.98) using a miniaturized spectral range (896-1039 cm-1), thus demonstrating that only a single fragment of the biological fingerprint Raman region is needed for producing an accurate diagnosis. These findings could favor the future development of a cheaper and dedicated Raman spectrometer for fast and accurate cancer diagnosis.

[1]  Gregory W. Auner,et al.  Identification of Pediatric Brain Neoplasms Using Raman Spectroscopy , 2012, Pediatric Neurosurgery.

[2]  H. Wulf,et al.  Distinctive Molecular Abnormalities in Benign and Malignant Skin Lesions: Studies by Raman Spectroscopy , 1997, Photochemistry and photobiology.

[3]  P. O. Andrade,et al.  Study of normal colorectal tissue by FT-Raman spectroscopy , 2007, Analytical and bioanalytical chemistry.

[4]  G. Thonhauser,et al.  Diagnosing drilling problems using visual analytics of sensors measurements , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[5]  R. Hofmann-Wellenhof,et al.  Agreement of Dermatopathologists in the Evaluation of Clinically Difficult Melanocytic Lesions: How Golden Is the ‘Gold Standard’? , 2012, Dermatology.

[6]  I Olkin,et al.  A comparison of dermatologists' and primary care physicians' accuracy in diagnosing melanoma: a systematic review. , 2001, Archives of dermatology.

[7]  Brian W. Barry,et al.  Potential applications of FT-Raman spectroscopy for dermatological diagnostics , 1995 .

[8]  Mackie,et al.  Clinical accuracy of the diagnosis of cutaneous malignant melanoma , 1998, The British journal of dermatology.

[9]  S Zucker,et al.  Purification and characterization of a connective-tissue-degrading metalloproteinase from the cytosol of metastatic melanoma cells. , 1987, The Biochemical journal.

[10]  Gerhard Thonhauser,et al.  Distributed recognition system for drilling events detection and classification , 2014, Int. J. Hybrid Intell. Syst..

[11]  D. Slater.  Doubt and uncertainty in the diagnosis of melanoma , 2000, Histopathology.

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[13]  Dalip Singh Mehta,et al.  Low coherence quantitative phase microscopy with machine learning model and Raman spectroscopy for the study of breast cancer cells and their classification. , 2019, Applied optics.

[14]  David I. Ellis,et al.  Metabolic fingerprinting in disease diagnosis: biomedical applications of infrared and Raman spectroscopy. , 2006, The Analyst.

[15]  H. Barr,et al.  Raman spectroscopy for identification of epithelial cancers. , 2004, Faraday discussions.

[16]  M. Okun,et al.  What criteria reliably distinguish melanoma from benign melanocytic lesions? , 2000, Histopathology.

[17]  S. Lam,et al.  Near‐infrared Raman spectroscopy for optical diagnosis of lung cancer , 2003, International journal of cancer.

[18]  Xu Feng,et al.  Raman active components of skin cancer. , 2017, Biomedical optics express.

[19]  J. Strasswimmer,et al.  Raman spectroscopy differentiates squamous cell carcinoma (SCC) from normal skin following treatment with a high‐powered CO2 laser , 2014, Lasers in surgery and medicine.

[20]  P. V. van Diest,et al.  Association of Histologic Regression With a Favorable Outcome in Patients With Stage 1 and Stage 2 Cutaneous Melanoma. , 2020, JAMA dermatology.

[21]  T. B. Bakker Schut,et al.  Improving clinical diagnosis of early-stage cutaneous melanoma based on Raman spectroscopy , 2018, British Journal of Cancer.

[22]  R. Mendelsohn,et al.  Determination of molecular conformation and permeation in skin via IR spectroscopy, microscopy, and imaging. , 2006, Biochimica et biophysica acta.

[23]  R. Dasari,et al.  Prospects for in vivo Raman spectroscopy , 2000 .

[24]  Asifullah Khan,et al.  Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning. , 2018, Photodiagnosis and photodynamic therapy.

[25]  Lars Kai Hansen,et al.  Detection of skin cancer by classification of Raman spectra , 2004, IEEE Transactions on Biomedical Engineering.

[26]  Jens Petter Wold,et al.  Raman Spectra of Biological Samples: A Study of Preprocessing Methods , 2006, Applied spectroscopy.

[27]  R. MacKie,et al.  Malignant melanoma: clinical variants and prognostic indicators , 2000, Clinical and experimental dermatology.

[28]  Dorota Krasowska,et al.  SIAscopy--a new non-invasive technique of melanoma diagnosis. , 2004, Annales Universitatis Mariae Curie-Sklodowska. Sectio D: Medicina.

[29]  J C Bamber,et al.  Differentiation of common benign pigmented skin lesions from melanoma by high‐resolution ultrasound , 2000, The British journal of dermatology.

[30]  N. O’higgins,et al.  Positron emission tomography for staging and management of malignant melanoma , 2002, The British journal of surgery.

[31]  Ozan Akkus,et al.  Laser Wavelength Dependence of Background Fluorescence in Raman Spectroscopic Analysis of Synovial Fluid from Symptomatic Joints. , 2013, Journal of Raman spectroscopy : JRS.

[32]  Howell G. M. Edwards,et al.  Fourier transform Raman and infrared vibrational study of human skin: Assignment of spectral bands , 1992 .

[33]  Yukihiro Ozaki,et al.  Near‐infrared Fourier transform Raman spectroscopic study of human brain tissues and tumours , 1994 .

[34]  H. Lui,et al.  Real-time Raman spectroscopy for automatic in vivo skin cancer detection: an independent validation , 2015, Analytical and Bioanalytical Chemistry.

[35]  S. Lam,et al.  RAMAN SPECTROSCOPY FOR IN VIVO TISSUE ANALYSIS AND DIAGNOSIS, FROM INSTRUMENT DEVELOPMENT TO CLINICAL APPLICATIONS , 2008 .

[36]  P. Aegerter,et al.  Is dermoscopy (epiluminescence microscopy) useful for the diagnosis of melanoma? Results of a meta-analysis using techniques adapted to the evaluation of diagnostic tests. , 2001, Archives of dermatology.

[37]  Richard A. Mathies,et al.  Effective Rejection of Fluorescence Interference in Raman Spectroscopy Using a Shifted Excitation Difference Technique , 1992 .