N. Ramanujam et al., CERVICAL PRECANCER DETECTION USING A MULTIVARIATE STATISTICAL ALGORITHM-BASED ON LASER-INDUCED FLUORESCENCE-SPECTRA AT MULTIPLE EXCITATION WAVELENGTHS, Photochemistry and photobiology, 64(4), 1996, pp. 720-735
A portable fluorimeter was developed and utilized to acquire fluoresce
nce spectra from 381 cervical sites in 95 patients at 337, 380 and 460
nm excitation immediately prior to colposcopy, A multivariate statist
ical algorithm was used to extract clinically useful information from
tissue spectra acquired in vivo. Two full-parameter algorithms were de
veloped using tissue fluorescence emission spectra at all three excita
tion wavelengths (161 excitation-emission wavelength pairs) for cervic
al precancer (squamous intraepithelial lesion [SIL]) detection: a scre
ening algorithm that discriminates between SIL and non-SIL with a sens
itivity of 82 +/- 1.4% and specificity of 68 +/- 0.0%, and a diagnosti
c algorithm that differentiates high-grade SIL from non-high-grade SIL
with a sensitivity and specificity of 79 +/- 2% and 78 +/- 6%, respec
tively, Multivariate statistical analysis was also employed to reduce
the number of fluorescence excitation-emission wavelength pairs needed
to redevelop algorithms that demonstrate a minimum decrease in classi
fication accuracy, Two reduced-parameter algorithms that employ fluore
scence intensities at only 15 excitation-emission wavelength pairs wer
e developed: the screening algorithm differentiates SIL from non-SIL w
ith a sensitivity of 84 +/- 1.5% and specificity of 65 +/- 2% and the
diagnostic algorithm discriminates high-grade SIL from non-high-grade
SIL with a sensitivity and specificity of 78 +/- 0.7% and 74 +/- 2%, r
espectively, Both the full-parameter and reduced-parameter screening a
lgorithms discriminate between SIL and non-SIL with a similar specific
ity (+/-5%) and a substantially improved sensitivity relative to Pap s
mear screening. A comparison of the full-parameter and reduced-paramet
er diagnostic algorithms to colposcopy in expert hands indicates that
all three have a very similar sensitivity and specificity for differen
tiating high-grade SIL from non-high-grade SIL.