Full fingerprint hyperspectral imaging of prostate cancer tissue microarrays within clinical timeframes using quantum cascade laser microscopy

Abstract

One of the major limitations for clinical applications of infrared spectroscopic imaging modalities is the acquisition time required to obtain reasonable images of tissues with high spatial resolution and good signal-to-noise ratio (SNR). The time to acquire a reasonable signal to noise spectroscopic scan of a standard microscope slide region of tissue can take many hours. As a trade-off, systems can allow for discrete wavenumber acquisitions, sacrificing potentially vital chemical bands in order to reach specific acquisition targets. Recent instrumentation developments now allow for the full fingerprint imaging of entire microscope slides in under 30 minutes, enabling rapid, high quality spectroscopic imaging of tissues within clinical timeframes without sacrificing frequency bands. Here we compare the data from a novel QCL microscope to an FTIR microscope covering multiple aspects of spectroscopic imaging of a large, clinically relevant, prostate cancer tissue cohort (N = 1281). Comparisons of hyperspectral data acquisition quality in both achieved signal to noise and image contrast alongside the capacity for unsupervised and supervised modelling of tissue constituents are reported. We conclude that it is now possible to collect full fingerprint spectra and derive clinically relevant data in a timeframe suitable for translation into the pathology laboratory without the need to resort to discrete frequency imaging with subsequent loss of information.

Fig. 1. Comparison of amide I peak integration (1600–1700 cm⁻¹) images for 100 cores imaged on d FTIR and QCL instruments (left). A single core is highlighted (white dotted lines, left) in greater detail (centre), with four selections from within the core also plotted for comparison of image quality (right).

Fig. 2. Comparison of 20 randomly sampled raw (unprocessed) spectra collected on FTIR (top) and QCL (bottom) systems. Plots are generated for full fingerprint regions (1800–1000 cm⁻¹) and lower wavenumber regions (1400–1000 cm⁻¹).

Fig. 3. Comparison of integrated lower wavenumber spectral regions (1220–1240 cm⁻¹) for unprocessed data of four separate prostate cores imaged using FTIR and QCL systems, with H&E stained adjacent sections and key manually drawn pathological annotations for stroma and epithelial regions (pink and green respectively) provided for visual comparison.

Fig. 4. Unsupervised k-means clustering images (n = 4) for FTIR and QCL hyperspectral images of two cancerous prostate cores (a and b). Clusters are coloured blue, red, green, and orange. H&E stained adjacent sections are provided for each core, with pathological regions showing key stromal and epithelial boundaries (pink and green borders respectively) drawn for interpretation. Four key zoomed in regions of interest (ROI) are presented, with numbers 1 through to 4 corresponding to top left, top right, bottom left, and bottom right ROIs.

Fig. 5. A complex, tiered Random Forests classification architecture covering seven separate models: Model 1 for classifying stroma, epithelium, red blood cells and immune cell infiltration from corpora amylacea; Model 2 for classifying epithelium, red blood cells and immune cell infiltration from stroma; Model 3 for classifying epithelium and immune infiltration from red blood cells; Model 4 for classifying normal and cancer associated stroma; Model 5 for classifying epithelium from immune infiltration; Model 6 for classifying high grade cancerous epithelium (Gleason score 4 and 5) from low grade epithelium (benign and Gleason score 3); Model 7 for classifying benign epithelium and Gleason score 3 epithelium. The number of datapoints for model training for each class in both FTIR and QCL based models are provided.

Fig. 6. Comparison of the complex multi-tiered supervised classifications of multiple tissue constituents for 25 prostate cores imaged on FTIR (left) and QCL systems (right).