Infrared spectroscopy with multivariate analysis potentially facilitates the segregation of different types of prostate cell

Abstract

The prostate gland is conventionally divided into zones or regions. This morphology is of clinical significance as prostate cancer (CaP) occurs mainly in the peripheral zone (PZ). We obtained tissue sets consisting of paraffin-embedded blocks of cancer-free transition zone (TZ) and PZ and adjacent CaP from patients (n = 6) who had undergone radical retropubic prostatectomy; a seventh tissue set of snap-frozen PZ and TZ was obtained from a CaP-free gland removed after radical cystoprostatectomy. Paraffin-embedded tissue slices were sectioned (10-mum thick) and mounted on suitable windows to facilitate infrared (IR) spectra acquisition before being dewaxed and air dried; cryosections were dessicated on BaF(2) windows. Spectra were collected employing synchrotron Fourier-transform infrared (FTIR) microspectroscopy in transmission mode or attenuated total reflection-FTIR (ATR) spectroscopy. Epithelial cell and stromal IR spectra were subjected to principal component analysis to determine whether wavenumber-absorbance relationships expressed as single points in "hyperspace" might on the basis of multivariate distance reveal biophysical differences between cells in situ in different tissue regions. After spectroscopic analysis, plotted clusters and their loadings curves highlighted marked variation in the spectral region containing DNA/RNA bands ( approximately 1490-1000 cm(-1)). By interrogating the intrinsic dimensionality of IR spectra in this small cohort sample, we found that TZ epithelial cells appeared to align more closely with those of CaP while exhibiting marked structural differences compared to PZ epithelium. IR spectra of PZ stroma also suggested that these cells are structurally more different to CaP than those located in the TZ. Because the PZ exhibits a higher occurrence of CaP, other factors (e.g., hormone exposure) may modulate the growth kinetics of initiated epithelial cells in this region. The results of this pilot study surprisingly indicate that TZ epithelial cells are more likely to exhibit what may be a susceptibility-to-adenocarcinoma spectral signature. Thus, IR spectroscopy on its own may not be sufficient to identify premalignant prostate epithelial cells most likely to progress to CaP.

FIGURE 1

Synchrotron FTIR microspectroscopy to interrogate prostate cells (epithelial versus stromal) in situ. Employing electron microscopy and light microscopy, prostatic glandular architecture was noted. Exploiting the phase contrast facility of the Thermo Nicolet continuum microscope, the location of the 10 μm × 10 μm aperture was tracked. Photomicrographs are of (A) electron microscopy of PZ glandular epithelial in cancer-free tissue (PEC4; scale bar = 5 μm); (B) electron microscopy of glandular epithelial cells in cancerous tissue (PEC4; scale bar = 10 μm); (C) H&E of glandular epithelial cells (PZ) derived from cancer-free tissue (PEC4); (D) H&E of glandular elements suspended in stroma (PZ) and derived from cancer-free tissue (PEC4); (E) H&E of a TZ glandular element derived from cancer-free tissue (PEC4); (F) phase contrast image of a glandular element (TZ) derived from cancer-free tissue (PEC4); (G) phase contrast image of glandular elements (TZ) derived from cancerous tissue (PEC4); and (H) phase contrast image of stroma (TZ) located in cancer-free tissue (PEC4). Images were obtained by employing conventional methods.

FIGURE 2

Epithelial cell spectra derived from different tissue regions employing either ATR spectroscopy (A, C, E, G, I, and K) or synchrotron FTIR microspectroscopy (B, D, F, H, J, and L). From paraffin-embedded blocks, 10-μm-thick sections were mounted on suitable windows to facilitate IR spectra acquisition before being dewaxed and air dried. Multiple spectra (each from a different location) were acquired from PZ (in black), TZ (in blue), or CaP (in red) regions of prostate tissue sets from six individuals (PEC1–PEC6, as detailed in each panel). Individual spectra were normalized to amide II (≈1533 cm⁻¹).

FIGURE 3

Stromal spectra derived from different tissue regions employing either ATR spectroscopy (A, C, E, G, I, and K) or synchrotron FTIR microspectroscopy (B, D, F, H, J, and L). From paraffin-embedded blocks, 10-μm-thick sections were mounted on suitable windows to facilitate IR spectra acquisition before being dewaxed and air dried. Multiple spectra (each from a different location) were acquired from PZ (in black), TZ (in blue), or CaP (in red) regions of prostate tissue sets from six individuals (PEC1–PEC6, as detailed in each panel). Individual spectra were normalized to amide II (≈1533 cm⁻¹).

FIGURE 4

Median spectra (A and C) and cluster vectors (B and D) for all spectra acquired either from epithelial cells lining glandular elements or stroma after ATR spectroscopy or synchrotron FTIR microspectroscopy. Spectra were collected and medians were derived from all the spectra acquired for a particular tissue region (PZ, black line; TZ, blue line; and CaP, red line). Cluster vectors examining loadings as a function of wavenumber were plotted as described (see Supplementary Material).

FIGURE 5

3-D scores plots on PCs selected to demonstrate best segregation of epithelial cell spectra derived from the different tissue regions. Spectra were collected using synchrotron FTIR microspectroscopy. Each spectrum for each tissue region (PZ, black circles; TZ, blue squares; CaP, red triangles) was expressed in terms of chosen PCs using Pirouette software and rotated to identify segregation of different clusters. Each symbol represents a single spectrum as a single point in “hyperspace”. The 3-D scores plots represent the following: (A) PEC1 on PC1, PC2, and PC4; (B) PEC2 on PC1, PC4, and PC5; (C) PEC3 on PC1, PC2, and PC6; (D) PEC4 on PC2, PC3, and PC4; (E) PEC5 on PC2, PC3, and PC5; and (F) PEC6 on PC1, PC4, and PC5.

FIGURE 6

2-D plots of the ratios for carbohydrate (quantified by the integrated absorbance in the 900–1185 cm⁻¹ region) to phosphates of nucleic acids (quantified by the integrated absorbance in the 1185–1300 cm⁻¹ region) versus RNA/DNA (based on the intensity at wavenumber 1121 cm⁻¹/intensity at 1020 cm⁻¹). Each symbol represents the mean ± SD of all the spectrally derived estimations for one tissue region (PZ, TZ, or CaP). The 2-D plots represent the following: (A) spectrally derived estimations for PZ; (B) spectrally derived estimations for TZ; and (C) spectrally derived estimations for CaP. These estimations were derived using OPUS software.

FIGURE 7

Median spectra and 3-D scores plots on PCs selected to demonstrate segregation of spectra derived from epithelial cells of PZ versus TZ isolated from a cystoprostatectomy specimen (PEC7). Spectra were collected using synchrotron FTIR microspectroscopy, and medians were derived from all the spectra acquired for a particular tissue region (PZ, black line; TZ, blue line). Each spectrum for each tissue region (PZ, black circles TZ, blue squares) were expressed in terms of chosen PCs using the Pirouette software and rotated to identify segregation of different clusters.