|
It is often difficult to identify cancer tissue during brain cancer (glioma) surgery. Gliomas invade into areas of normal
brain, and this cancer invasion is frequently not detected using standard preoperative magnetic resonance imaging
(MRI). This results in enduring invasive cancer following surgery and leads to recurrence. A hand-held Raman
spectroscopy is able to rapidly detect cancer invasion in patients with grade 2-4 gliomas. However, ambient light sources
can produce spectral artifacts which inhibit the ability to distinguish between cancer and normal tissue using the spectral
information available. To address this issue, we have demonstrated that artificial neural networks (ANN) can accurately
classify invasive cancer versus normal brain tissue, even when including measurements with significant spectral artifacts
from external light sources. The non-parametric and adaptive model used by ANN makes it suitable for detecting
complex non-linear spectral characteristics associated with different tissues and the confounding presence of light
artifacts. The use of ANN for brain cancer detection with Raman spectroscopy, in the presence of light artifacts,
improves the robustness and clinical translation potential for intraoperative use. Integration with the neurosurgical
workflow is facilitated by accounting for the effect of light artifacts which may occur, due to operating room lights,
neuronavigation systems, windows, or other light sources. The ability to rapidly detect invasive brain cancer under these
conditions may reduce residual cancer remaining after surgery, and thereby improve patient survival.
|
