Deparaffinised tissue analysis using HCA spectroscopic imaging & supervised pattern recognition. (a) H&E stained image of a positive lymph node PN3. The positive node comprises a large region of cancerous breast tissue (1), macrophages (2), lymphocytes (4), adipose tissue (5), and a thin surrounding capsule (3). (b) HCA spectroscopic image of positive lymph node PN3. The IR imaged area (3.3 mm × 4.9 mm) was mapped using a step size and aperture of 25 μm for a total 25,676 individual IR spectra. The red colour in the image describes areas of cancerous breast tissue. In contrast, the remnant healthy tissues are depicted by the blue (lymphocytes), green (macrophages), brown (adipose tissue) and yellow (capsule) colours respectively. (c) ANN image of positive lymph node PN3. The red colour in the image describes regions correctly classified as cancerous by the analysis. In contrast, the blue colour depicts the remnant healthy tissues that were correctly classified. Black pixels within the image describe spectra that were not able to be classified by the neural net.
Bird et al. BMC Clinical Pathology 2008 8:8 doi:10.1186/1472-6890-8-8