• 2019-07
  • 2019-08
  • 2019-09
  • 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • br Introduction br In the last decades artificial intelligen


    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 VH-298 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 VH-298 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.
    prostate cancer diagnosis. In [16], this technique was used for stomach cancer analysis; in [8] and [17], it was used for lung cancer analysis; and in [18], it was used for breast cancer analysis and diagnosis.
    The Raman spectrum of a given molecule consists of a series of peaks or bands, each transferred by a characteristic vibrational fre-quency of that molecule [3,10,14]. The Raman information obtained is related to the spectral lines that are provided as frequencies denomi-nated in the Raman shifts, which are expressed in wavenumbers (cm −1). In skin cancer diagnosis applications, abnormal tissues are assumed to have differences in constitution compared to normal tissues, and this difference, when reflected in the observed Raman bands, in-dicates that each material responds to a given spectrum [13,14].
    1.2. Forms of Raman spectroscopy data analysis
    The data analysis methods to obtain diagnostic results in the dis-crimination models are usually based on multivariate statistics; the spectra are analyzed using all the spectral information combined with statistical algorithms based on principal component analysis (PCA) [3,13,19]. Despite the satisfactory results using multivariate statistics, a serious disease such as skin cancer requires a high confidence index in the diagnosis and precociousness in the results to obtain satisfactory treatment. Therefore, the need for a correct, reliable, and fast diagnosis motivates further research to find other models for the processed data analysis. Modern techniques that use artificial intelligence can obtain the spectral information of the Raman data in a shorter time, with easy-to-visualize analysis results and a greater reliability index [5,20–22].
    1.3. Computational methods and paraconsistent logic (PL)
    To offer increasingly reliable diagnostic support methods for modern medicine, several studies have been developed using compu-tational methods of analysis and data processing based on non-classical logics [23,24]. Non-classical logics do not obey the binary precepts of classical logic, and thus, with their extended limits, are more active, especially in analyses based on incomplete or diffuse knowledge. In many studies, non-classical logics have been shown to be better able to respond to situations of uncertainty [20–22]. In this research, we apply a new computational tool for data processing to model the Raman 
    intensity signals to extract the results that generate information to support skin cancer medical diagnosis using logical considerations of treatment of uncertainties. To achieve this objective, we present an adapted configuration or computational structure using algorithms based on a non-classical logic called PL. The PL main characteristic is to accept the contradiction in its logical foundations, without the existing conflict in the information signals invalidating the conclusions [24–26]. The PL application in data analyses is made through its extension called paraconsistent annotated logic with annotation of two values (PAL2v) [25,27].