Photomedicine and Laser Surgery
Volume 27, Number 2, 2009
© Mary Ann Liebert, Inc.
Pp. 241–252
DOI: 10.1089/pho.2008.2255
Autofluorescence of Breast Tissues:
Evaluation of Discriminating Algorithms for Diagnosis
of Normal, Benign, and Malignant Conditions
M.V.P. Chowdary,
1
K.K. Mahato, Ph.D.,
2
K. Kalyan Kumar, M.Sc.,
1
Stanley Mathew, M.S., FRCS Ed.,
3
Lakshmi Rao, M.D.,
4
C. Murali Krishna, Ph.D.,
5
and Jacob Kurien, M.S., M.Ch.
6
Abstract
Objective: We evaluated different discriminating algorithms for classifying laser-induced fluorescence spectra
of normal, benign, and malignant breast tissues that were obtained with 325-nm excitation. Background Data:
Mammography and histopathology are the conventional gold standard methods of screening and diagnosis of
breast cancers, respectively. The former is prone to a high rate of false-positive results and poses the risk of re-
peated exposure to ionizing radiation, whereas the latter suffers from subjective interpretations of morpholog-
ical features. Thus the development of a more reliable detection and screening methodology is of great inter-
est to those practicing breast cancer management. Several studies have demonstrated the efficacy of optical
spectroscopy in diagnosing cancer and other biomedical applications. Materials and Methods: Autofluores-
cence spectra of normal, benign, and malignant breast tissues, with 325-nm excitation, were recorded. The data
were subjected to diverse discriminating algorithms ranging from intensities and ratios of curve-resolved bands
to principal components analysis (PCA)-derived parameters. Results: Intensity plots of collagen and NADPH,
two known fluorescent biomarkers, yielded accurate classification of the different tissue types. PCA was car-
ried out on both unsupervised and supervised methods, and both approaches yielded accurate classification.
In the case of the supervised classification, the developed standard sets were verified and evaluated. The limit
test approach provided unambiguous and objective classification, and this method also has the advantage of
being user-friendly, so untrained personnel can directly compare unknown spectra against standard sets to
make diagnoses instantly, objectively, and unambiguously. Conclusion: The results obtained in this study fur-
ther support the efficacy of 325-nm-induced autofluorescence, and demonstrate the suitability of limit test anal-
ysis as a means of objectively and unambiguously classifying breast tissues.
241
Introduction
B
REAST CANCER IS THE MOST COMMON FEMALE CANCER and
the second most common cancer overall, when both gen-
ders are considered together.
1
Occurrence of this cancer is
rare in subjects younger than 30 y, but the incidence rises
steadily up to age 50 y, after which the rate of increase slows.
A recent study conducted in 2000–2004 concluded that 95%
of new cases and 97% of breast cancer deaths occur in women
aged 40 and above.
2
Early diagnosis is associated with bet-
ter outcomes; the 5-y survival rate of 90% for stage I disease
drops to below 50% with later detection. Therefore, accurate
screening and early detection has great impact on success-
ful breast cancer management. Conventional screening by
mammography (the gold standard of screening) identifies
suspicious lesions, but carries a high rate of false-positive re-
sults.
3
Moreover, this methodology involves the risk of re-
peated exposure to harmful ionizing radiation. Histopathol-
ogy, the gold standard of diagnosis, is subject to subjective
interpretation. Fine-needle aspiration cytology, core biopsy,
or surgical excision are the most common sampling tech-
niques used to obtain cells or tissue for histopathologic anal-
1
Division of Laser Spectroscopy, Manipal Life Science Centre/Department of Surgical Oncology, Shirdi Sai Baba Cancer Hospital,
2
Di-
vision of Laser Spectroscopy, Manipal Life Science Centre,
3
Department of General Surgery, Kasturba Hospital,
4
Department of Pathology,
Kasturba Hospital,
5
Division of Laser Spectroscopy, Manipal Life Science Centre, and
6
Department of Surgical Oncology, Shirdi Sai Baba
Cancer Hospital, Manipal University, Manipal, Karnataka, India.