We report on the first stages of a clinical study designed to test elastic-
scattering spectroscopy, mediated by fiberoptic probes, for three specific
clinical applications in breast-tissue diagnosis: (1) a transdermal-needle
(interstitial) measurement for instant diagnosis with minimal invasiveness
similar to fine-needle aspiration but with sensitivity to a larger tissue v
olume, (2) a hand-held diagnostic probe for use in assessing tumor/resectio
n margins during open surgery, and (3) use of the same probe for real-time
assessment of the "sentinel" node during surgery to determine the presence
or absence of tumor (metastatic). Preliminary results from in vivo measurem
ents on 31 women are encouraging. Optical spectra were measured on 72 histo
logy sites in breast tissue, and 54 histology sites in sentinel nodes. Two
different artificial intelligence methods of spectral classification were s
tudied. Artificial neural networks yielded sensitivities of 69% and 58%, an
d specificities of 85% and 93%, for breast tissue and sentinel nodes, respe
ctively. Hierarchical cluster analysis yielded sensitivities of 67% and 91%
, and specificities of 79% and 77%, for breast tissue and sentinel nodes, r
espectively. These values are expected to improve as the data sets continue
to grow and more sophisticated data preprocessing is employed. The study w
ill enroll up to 400 patients over the next two years. (C) 2000 society of
Photo-Optical instrumentation Engineers. [S1083-3668(00)00302-6].