The study was approved by the ethical committee of the Northern Ostrobothnia hospital district (approval number 191/2000). Informed consent was obtained from all patients. Human AC samples (n = 16) were collected from patients (N = 12) undergoing total knee arthroplasty at Oulu University Hospital. Cylindrical osteochondral plugs were drilled from tibial plateaus of each tibia. Two plugs were prepared from four of the tibiae and one plug from the rest. Thus, sixteen osteochondral cores were used in the study. Subsequently, the plugs were fixed in formalin, decalcified in ethylenediaminetetraacetic acid (EDTA), dehydrated and embedded in paraffin for histological evaluation.

Sections (thickness = 3 μm) were cut and placed on standard microscopy slides, deparaffined and rehydrated. Removal of PGs has been earlier shown to improve the staining results for Picrosirius Red[10]. To further investigate this result, Picrosirius red staining was done with and without enzymatic removal of PGs. In order to evaluate the effect of the removal of PG on the Picrosirius red stain, staining was performed with and without digesting PGs using papain (Acros Organics, 0.5% papain, 0.05 M phosphate buffer, pH = 4.4) at 37°C for 18 hours, followed by hyaluronidase treatment (Sigma Aldrich, 1000 U/ml in 0.1 M phosphate buffer, pH = 6.9) at 37°C for 18 hours. All tissue sections were rinsed with phosphate buffer and immersed in 0.1% direct red 80 (Sigma-Aldrich) in saturated picric acid for 60 minutes. Samples were then washed with 0.01M hydrochloric acid, dehydrated and mounted.

Masson’s trichrome staining was conducted using ready–to-use kit (Trichrome Stain (Masson) Kit, HT15, Sigma-Aldrich). Briefly, the tissue sections (thickness = 5 μm) were cut and placed on standard microscopy slides. After deparaffinisation and rehydration, the slides were immersed in Bouin’s solution (HT 10132, Sigma-Aldrich) at 56°C for 15 minutes. Subsequently, the slides were washed with tap water for 5 minutes. Next, the sections were stained in Weigert’s hematoxylin for 5 minutes, and then washed again with tap water for 5 minutes and rinsed in distilled water. Next, the slides were stained in Biebrich scarlet-acid fuchsin for 5 minutes, rinsed in distilled water, incubated in phosphotungstic-phosphomolybdic acid for 5 minutes, dyed with aniline blue for 5 minutes, and fixed in 1% acetic acid for 2 minutes. Finally, the slides were rinsed in distilled water, dehydrated and mounted.

The Modified Masson’s trichrome staining was also conducted using ready–to-use kit (Trichrome Stain (Masson) Kit, HT15, Sigma-Aldrich), but the PGs were removed enzymatically in a similar way as in the Picrosirius red staining. Briefly, the tissue sections (thickness = 5 μm) were cut and placed on standard microscopy slides. After deparaffinisation and rehydration, the sections were digested with papain and hyaluronidase (0.5% papain, 0.05 M phosphate buffer, pH = 4.4 at 37°C for 18 hours followed by hyaluronidase (1000 U/ml in 0.1 M phosphate buffer, pH = 6.9) at 37°C for 18 hours). Sections were then immersed in Bouin’s solution (HT 10132, Sigma-Aldrich); stained in Weigert’s hematoxylin, incubated in phosphotungstic-phosphomolybdic acid, dyed with aniline blue and fixed in 1% acetic acid. Then, the slides were rinsed in distilled water, dehydrated and mounted. The Biebrich scarlet-acid fuchsin of the kit was not used, as it is not related to collagen, and may hinder the quantitation of the collagen stain. Otherwise, the procedure and staining durations were the same as described in previous section.

For the FTIR spectroscopic imaging measurements, 5-μm-thick sections were cut with a microtome (Thermo Scientific, Microm HM 355S) and transferred to microscope slides. Paraffin was dissolved with xylene before transferring the sections to 0.5-mm-thick Zinc-Selenide (ZnSe) windows (Crystran Ltd., Poole, United Kingdom). FTIR spectroscopic imaging measurements were conducted in transmission mode with a FTIR spectrometer (Tensor 27, Bruker Inc., Billerica, MA, USA) coupled with Bruker Hyperion 3000 microscope (Bruker Inc., Billerica, MA, USA) that is equipped with a focal plane array (FPA) 64x64 detector. The sample chamber was purged with dry air to minimize the atmospheric conditions. A rectangular region extending from the cartilage surface to subchondral bone was measured from each section. The spectral resolution was set to 4 cm^-1 and each spectrum was averaged on 16 scans. Pixel binning (2x2) was used to set the pixel size to be 5.4 μm (native pixel size of the system is 2.7 μm). Noise was further reduced from the spectra by using a principal component analysis (PCA)-based noise filter (data was reconstructed using 20 first principal components). The integrated absorbance of the amide I (1585–1720 cm^-1) peak was used to estimate the collagen content in AC. Furthermore, the absolute height of the collagen CH₂ side chain vibration[11] at 1338 cm^-1 was calculated from the 2^nd derivative spectrum to confirm the amide I peak results. Second derivative spectra were calculated using Savitzky-Golay algorithm with 9 smoothing points. Absolute value of the second derivative peak was used (2^nd derivative displays the absorbance peaks of original spectrum as negative peaks). All preprocessing and analysis of spectral data was performed with custom-made MATLAB (MathWorks Inc., MA, USA) scripts.

DD was used to quantify the amount of stain in the sections[6]. DD measurements were conducted using the Carl Zeiss Axio Scope A1 microscope (Carl Zeiss, Germany) and QImaging QICAM camera (QImaging, Surry, BC, Canada). Sections were analyzed with monochromatic light at 625 nm for Masson’s trichrome and 550 nm for Picrosirius red. The measured grayscale values were calibrated to optical density (OD) using neutral density filters (range: 0–3 OD units, Edmund Optics, Blackwood, NJ, USA). A 1-mm-wide region-of-interest extending from the cartilage surface to cartilage-bone interface was used to analyze the images.

Similarly to previous studies, birefringence of collagen measured with polarized light microscopy (PLM) was used to quantitate the collagen content with[12,13] and without[12,14,15] Picrosirius red staining. The unstained sections (thickness = 5 μm) were placed on standard microscope slides, and the removal of PGs was done for these sections similarly as described earlier. The sections were imaged with Abrio PLM system (CRi, Inc., Woburn, MA, USA) mounted on a conventional light microscope (Nikon Diaphot TMD, Nikon, Inc., Shinagawa, Tokyo, Japan). The Abrio system consists of a green bandpass filter, a circular polarizer, and a computer-controlled analyzer composed of two liquid crystal polarizers, and a CCD camera. The system can be used for automated measurement of the magnitude of retardance in birefringent materials such as tissue sections. A 1-mm-wide region-of-interest extending from the cartilage surface to cartilage-bone interface was used to analyze the images.

Regions of interests (ROIs) extending from the cartilage surface to cartilage-bone interface were manually selected from all (DD, PLM and FTIR spectroscopic imaging) images. Values on rows of the selected ROIs were averaged to obtain the mean value for different depths of the tissue. These depth-dependent profiles were scaled to 100 points to enable direct comparison between the methods. Comparisons were done in two ways: (i) One-tailed Pearson’s correlation analysis was conducted at all layers (1–100%) of rescaled depth-dependent DD or PLM profiles and FTIR spectroscopic imaging collagen profiles, and (ii) Pearson’s correlation coefficients were calculated sample-by-sample between the depth-dependent DD or PLM profiles and FTIR spectroscopic imaging collagen profiles. All statistical analyses were performed with (MathWorks Inc., MA, USA).

Collagen quantification was performed based on the DD results at 625 nm of Aniline Blue of Masson’s Trichrome stained tissue slides with and without removal of PGs. Without removal of PGs, significant correlations (r > 0.426) were observed at superficial layer and some parts of the deep layer, but the mean correlation (± standard deviation) was low with both the amide I (r = 0.25 ± 0.31) and CH₂ absorbances (r = 0.29 ± 0.27) (Fig 2A). On average, sample-by-sample correlations between the depth-dependent profiles of optical density of Masson’s staining and the amide I absorbance were strong (r = 0.65 ± 0.33) (Fig 3A), and slightly weaker in case of CH₂ absorbance (r = 0.51 ± 0.46) (Fig 4A).

The modified Masson protocol improved the correlations: significant correlation was observed with amide I in all but the most superficial (1–2%) layer (mean correlation: r = 0.72 ± 0.10) (Fig 2A). The average correlations between the modified Masson and amide I depth-dependent profiles were also strong (r = 0.87 ± 0.13) (Fig 3D). Significant correlations were also observed with CH₂ absorbance in all layers except a portion of middle layer (17–20%) and the deepest layer (98–100%) of cartilage (mean correlation: r = 0.59 ± 0.13) (Fig 2A). Furthermore, the sample-by-sample correlations with the CH₂ absorbance profiles were strong (r = 0.69 ± 0.27) (Fig 4D). Summaries of the correlation analyses are seen in Tables 1 and 2.

No significant correlation was found between the optical density of Picrosirius red and amide I or CH₂ at any layer when PGs were not removed before the staining (Fig 2B). Furthermore, the average correlations between the depth-dependent profiles of the optical density of Picrosirius red and the FTIR spectroscopic collagen parameters (amide I and CH₂) were negative (Figs 3B and 4B).

Removal of PGs enhanced the staining of deep cartilage and, thus, improved the mean correlations of optical density of Picrosirius red with amide I and CH₂ absorbances. However, significant correlations were found only between the optical density of Picrosirius red and amide I at some layers of deep cartilage (37–47%, 49%, and 71%) (Fig 2B). No significant correlation was observed between the optical density of Picrosirius red (after removal of PGs) and CH₂ absorbance (Fig 2B). Sample-by-sample correlations between the depth-dependent profiles of Picrosirius red (after removal of PGs) and amide I were strong (r = 0.87 ± 0.13) (Fig 3E), and slightly weaker with the CH₂ (r = 0.66 ± 0.26) (Fig 4E).

The retardance of Picrosirius red-stained sections with or without enzymatic removal of PGs displayed no correlation with the amide I or CH₂ absorbances (except in one case: there was a significant correlation between the retardance of Picrosirius red and amide I at layer 52%) (Fig 2C). Furthermore, the depth-dependent profiles of the retardance of Picrosirius red-stained sections did not correlate with the depth-dependent profiles of amide I (Fig 3C and 3F) or CH₂ (Fig 4C and 4F) absorbances.

The retardance of unstained AC sections showed a significant correlation with the amide I absorbance at certain depths (1–2%, 17–18%, 24–38%, 43%), but the mean correlation was low (r = 0.28 ± 0.18) (Fig 2C). Nevertheless, the correlations between the depth-dependent profiles were strong (r = 0.75 ± 0.19) (Fig 3G). Similarly, some significant correlations were observed between the retardance of unstained sections and CH₂ absorbance (1–2%, 33–39%, 43–45%, 53–56%) (Fig 2C). On average, the correlations between the depth-dependent profiles of retardance of unstained sections and CH₂ absorbance were moderate (r = 0.59 ± 0.25) (Fig 4G).