• 2022-08
  • 2022-07
  • 2022-05
  • 2022-04
  • 2021-03
  • 2020-08
  • 2020-07
  • 2018-07
  • br b Center for Innovation Technology and


    b Center for Innovation, Technology and Education–CITE, Universidade Anhembi Morumbi–UAM, Parque Tecnológico de São José dos Campos, Estr. Dr. Altino Bondensan, 500, São José dos Campos, SP, 12247-016, Brazil
    c Laboratory of Cardiovascular Pathology, Department of Pathology–LIM22, University of Sao Paulo Medical School FMUSP, Av. Dr. Arnaldo, 455, São Paulo, 01246-903, SP, Brazil
    Raman spectroscopy
    Skin cancer
    Paraconsistent annotated logic Medical diagnosis 
    Analysis of the Raman data to obtain results in discrimination models is usually done with multivariate statistics based on principal component analysis (PCA). In this work, we present a technique based on a non-classical logic called paraconsistent logic (PL). The aim of this work is to use computational procedures capable of generating efficient expert systems to discriminate cutaneous tissue samples obtained by Raman spectroscopy. First, a set of algorithms originating from PL is presented, and then its application in discrimination analyses is described; the discrimination analysis was conducted using a database of PTK0796 tissue samples obtained ex vivo by Raman spectroscopy of spectrum range of 400–1800 cm−1 wavelengths. Data processing, pattern creation, and com-parisons were performed using the set of paraconsistent algorithms (SPA-PAL2v). The total number of samples was divided into four histopathological groups, with 115 spectra of basal cell carcinoma (BCC), 21 spectra of squamous cell carcinoma (SCC), 57 spectra of actinic keratosis (AK), and 30 normal skin (NO) spectra. An arrangement type was created for this study, and the samples were randomly selected and analyzed, and the NO group was compared with the group of non-melanoma cancer lesions (BCC + SCC) and the AK tumor lesion. Two analyses were performed. The first (SPA-PAL2v) Mode 1 (no cross-validation) achieved 76% of hits, and the second (SPA-PAL2v) Mode 2 (with cross-validation) achieved 75.78% of hits. These results were compared with discrimination using PCA statistical methods (PCA/DA) and presented superior percentages of hits, which proves the robustness of the SPA-PAL2v, confirming its potential for Raman spectrum data analysis.
    1. Introduction
    In the last decades, artificial intelligence has presented important improvements to support the diagnosis of cancer, an illness with a high mortality rate. For skin cancer, many of the studies in the literature involve new detection methods since treatment effectiveness is depen-dent on early diagnosis [1,2].
    Common tests for skin cancer confirmation are performed through the evaluation of pigmented skin lesions based on pre-established morphological models for each histopathological group [3,4]; however, diagnostic sensitivity and specificity are very dependent on the eva-luators' experience, which adds some degree of uncertainty in diagnosis [5–8]. Recently, research using new lesions analysis techniques to
    Corresponding author.
    E-mail address: [email protected] (J.I. da Silva Filho). 
    support the diagnosis has presented good results; among these techni-ques, the use of vibrational spectroscopy, particularly Raman spectro-scopy, has been highlighted [9–11]. The Raman spectroscopy technique presents advantages in terms of the extraction method of skin cancer information, especially considering that the biochemical composition of the samples is evaluated quickly, non-invasively, and without pre-paration or destruction of the sample [12,13].
    1.1. Raman spectroscopy
    In the medical field, Raman spectroscopy has the potential to di-agnose and analyze the evolution of human malignancies both in vitro and in vivo. This can be seen in [15], where this technique was used for
    Fig. 1. A) Lattice FOUR (Hasse diagram) associated with Paraconsistent Annotated Logic PAL. B) .Representation of μ and λ values in a unitary square on the Cartesian plane (USCP) to obtain Dc and Dct values in the associated PAL2v lattice.