Description

The study will employ multispectral photoacoustic imaging in the spectral range between 680-970 nm to scan suspected skin tumors both in vivo and ex vivo. The hyperspectral data will then undergo rigorous spectral analysis with the objective to identify the spectral fingerprints associated with healthy tissue and tumor. Thereafter, a classification algorithm will be used to determine whether a pixel in the acquired image more likely identifies with healthy tissue or tumor, which is then repeated for all pixels in the images. As such, a 3D image can be reconstructed in which the tumor is visibly contrasted from healthy tissue. Achieving this goal will facilitate the diagnostic procedures and greatly reduce waiting times, clinical costs and potential patient suffering.