FOURIER TRANSFORM INFRARED MICROSPECTROSCOPY AS A QUANTITATIVE DIAGNOSTIC TOOL FOR ASSIGNMENT OF PREMALIGNANCY GRADING IN CERVICAL NEOPLASIA.
Abstract
The early
diagnosis and proper identification of the cervical squamous intraepithelial
lesion plays an important role in a good prognosis for the patient. However the
present practice of screening based on PAP smear and also histopathology makes
it tedious and prone to human errors. In the present study we assess the
validity of FTIR microspectroscopy (FTIR-MSP) of biopsy as a method to properly
assign the correct stage of premalignancy in patients with symptoms of cervical
intraepithelial neoplasia. The study for the first time evaluates the biopsies
based on the FTIR spectra for different grades of neoplasia in tandem with
Probabilistic Neural Networks (PNN)
and histopathology. The results show that the grading of neoplasia based on
FTIR-MSP and PNN differentiates the normal from premalignant with a high level
of accuracy. The false positive identification of the normal as CIN1, CIN2 and
CIN 3 is 13.95%, 3.53% and 0.19% respectively. The false negative identification
of CIN2 as normal and CIN 1 is 0.04% and 3.65% respectively. Similarly, the
false negative identification of CIN3 as normal, CIN 1 and CIN 2
is 0.04%, 3.38% and 4.65% respectively. The small errors encountered in
the grading are comparable to the current methods encouraging advanced studies
for the development of mechanized equipments for diagnosis and grading of
premalignant cervical neoplasia.