Development of an Expert System as a Diagnostic Support of Cervical Cancer in Atypical Glandular Cells, Based on Fuzzy Logics and Image Interpretation
Table 3
Input variables “Inyury resolution (DL).”1
Input variables
Label
Geometric shape
Interval
Small
Trapezoid
(0 0 5000 6000)
Nucleus dimensión (DN)
Medium
Trapezoid
(4500 6800 9000 10000)
Large
Trapezoid
(9000 9900 25000 25000)
Clear
Trapezoid
(50 50 80 82)
Nuclei staining (TN)
Media
Trapezoid
(79 82 87 92)
Dark
Trapezoid
(87 92 150 150)
Homogeneous nucleation (HN)
Regular
Trapezoid
(0.5 0.5 0.74 0.77)
Irregular
Trapezoid
(0.75 0.8 1 1)
Null
Triangular
(0 0 2)
Nucleolus presence (PN)
Few
Trapezoid
(2 9 20 30)
Many
Trapezoid
(24 40 150 150)
Risk (R)
Negative
Triangular
(0.5 1 1.5)
Positive
Triangular
(1.51 2 2.5)
Normal
Trapezoid
(0 0 31 41)
(DL) Injury resolution
AGC
Trapezoid
(31 41 58 68)
Positive to malignity
Trapezoid
(58 68 100 100)
1The initials presented in each one of input and output variables come from the translation from Spanish since users are native Spanish speakers. The interface of the expert system is, for now, only available in Spanish.