TY - JOUR
T1 - Accurate identification of breast cancer margins in microenvironments of ex-vivo basal and luminal breast cancer tissues using Raman spectroscopy
AU - Koya, S. Kiran
AU - Brusatori, Michelle
AU - Yurgelevic, Sally
AU - Huang, Changhe
AU - Werner, Cameron W.
AU - Kast, Rachel E.
AU - Shanley, John
AU - Sherman, Mark
AU - Honn, Kenneth V.
AU - Maddipati, Krishna Rao
AU - Auner, Gregory W.
N1 - Funding Information:
Support for this work was provided by the National Cancer Institute (Grant title: Comparison of Basal and Luminal A Breast Cancers by Raman Spectroscopy, National Cancer Institute) and through a Paul U. Strauss Endowed Chair- Wayne State University School of Medicine .
Publisher Copyright:
© 2020 Elsevier Inc.
PY - 2020/12
Y1 - 2020/12
N2 - Better knowledge of the breast tumor microenvironment is required for surgical resection and understanding the processes of tumor development. Raman spectroscopy is a promising tool that can assist in uncovering the molecular basis of disease and provide quantifiable molecular information for diagnosis and treatment evaluation. In this work, eighty-eight frozen breast tissue sections, including forty-four normal and forty-four tumor sections, were mapped in their entirety using a 250-μm-square measurement grid. Two or more smaller regions of interest within each tissue were additionally mapped using a 25 μm-square step size. A deep learning algorithm, convolutional neural network (CNN), was developed to distinguish histopathologic features with-in individual and across multiple tissue sections. Cancerous breast tissue were discriminated from normal breast tissue with 90 % accuracy, 88.8 % sensitivity and 90.8 % specificity with an excellent Area Under the Receiver Operator Curve (AUROC) of 0.96. Features that contributed significantly to the model were identified and used to generate RGB images of the tissue sections. For each grid point (pixel) on a Raman map, color was assigned to intensities at frequencies of 1002 cm−1 (Phenylalanine), 869 cm−1 (Proline, C–C stretching of hydroxyproline-collagen assignment, single bond stretching vibrations for the amino acids proline, valine and polysaccharides) and 1309 cm−1 (CH3/CH2 twisting or bending mode of lipids). The Raman images clearly associate with hematoxylin and eosin stained tissue sections and allow clear visualization of boundaries between normal adipose, connective tissue and tumor. We demonstrated that this simple imaging technique allows high-resolution, straightforward molecular interpretation of Raman images. Raman spectroscopy provides rapid, label-free imaging of microscopic features with high accuracy. This method has application as laboratory tool and can assist with intraoperative tissue assessment during Breast Conserving surgery.
AB - Better knowledge of the breast tumor microenvironment is required for surgical resection and understanding the processes of tumor development. Raman spectroscopy is a promising tool that can assist in uncovering the molecular basis of disease and provide quantifiable molecular information for diagnosis and treatment evaluation. In this work, eighty-eight frozen breast tissue sections, including forty-four normal and forty-four tumor sections, were mapped in their entirety using a 250-μm-square measurement grid. Two or more smaller regions of interest within each tissue were additionally mapped using a 25 μm-square step size. A deep learning algorithm, convolutional neural network (CNN), was developed to distinguish histopathologic features with-in individual and across multiple tissue sections. Cancerous breast tissue were discriminated from normal breast tissue with 90 % accuracy, 88.8 % sensitivity and 90.8 % specificity with an excellent Area Under the Receiver Operator Curve (AUROC) of 0.96. Features that contributed significantly to the model were identified and used to generate RGB images of the tissue sections. For each grid point (pixel) on a Raman map, color was assigned to intensities at frequencies of 1002 cm−1 (Phenylalanine), 869 cm−1 (Proline, C–C stretching of hydroxyproline-collagen assignment, single bond stretching vibrations for the amino acids proline, valine and polysaccharides) and 1309 cm−1 (CH3/CH2 twisting or bending mode of lipids). The Raman images clearly associate with hematoxylin and eosin stained tissue sections and allow clear visualization of boundaries between normal adipose, connective tissue and tumor. We demonstrated that this simple imaging technique allows high-resolution, straightforward molecular interpretation of Raman images. Raman spectroscopy provides rapid, label-free imaging of microscopic features with high accuracy. This method has application as laboratory tool and can assist with intraoperative tissue assessment during Breast Conserving surgery.
KW - Biomarkers
KW - Breast cancer detection
KW - Deep learning
KW - Ex vivo tumor analysis
KW - Interoperative tumor margin assessment
KW - Raman spectroscopy
UR - http://www.scopus.com/inward/record.url?scp=85089185716&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089185716&partnerID=8YFLogxK
U2 - 10.1016/j.prostaglandins.2020.106475
DO - 10.1016/j.prostaglandins.2020.106475
M3 - Article
C2 - 32711127
AN - SCOPUS:85089185716
SN - 1098-8823
VL - 151
JO - Journal of Lipid Mediators and Cell Signalling
JF - Journal of Lipid Mediators and Cell Signalling
M1 - 106475
ER -