Figure 5.

Deparaffinised tissue analysis using supervised pattern recognition. (a) H&E stained image of positive lymph node PN4. The IR imaged area (5.2 mm × 4.6 mm) was mapped using a step size and aperture of 25 μm for a total 37,856 individual IR spectra. The positive node comprises large regions of cancerous breast tissue (2) and remnants of healthy nodal tissue (1). (b) ANN image of positive lymph node PN4. The red and blue colours represent the correctly classified cancerous (2) and healthy nodal tissues (1) respectively. Black pixels within the image describe spectra that were not able to be classified by the neural net. (c) H&E stained image of negative lymph node PN5. The IR imaged area (6.5 mm × 6.5 mm) was mapped using a step size and aperture of 25 μm for a total 67,600 individual IR spectra. The positive node comprises both remnant healthy nodal tissue (1) and invading cancerous breast tissue (2). (d) ANN image of negative node PN5. The blue colour is representative of the correctly classified healthy nodal tissue. In contrast, the red colour depicts the regions of cancerous invasion that were correctly classified. Black pixels within the image describe spectra that were not able to be classified by the neural net.