Dissertation Summary
A successfully defended dissertation tackles the global increase in skin cancer cases by exploring two innovative approaches.
First, it examines the potential of non-invasive 3D hyperspectral imaging (HSI) combined with convolutional neural networks (CNNs) for differentiating between malignant and benign skin lesions. The HSI-CNN system demonstrated promising accuracy in identifying various skin tumor types, offering a valuable tool for fast and precise skin cancer detection.
Second, it evaluates the efficacy and tolerability of two laser-mediated photodynamic therapy (PDT) methods for treating skin cancer precursors and field cancerization. The findings suggest that ablative fractional laser (AFXL)-mediated PDT, used with artificial daylight, is an effective single-visit treatment option for patients with extensive or severe photodamage.
Further research is recommended to refine these techniques and confirm their broader clinical applications.