Medical Image Analysis

  • Melanoma whole-slide histopathology image analysis

Melanoma is one of the most aggressive forms of skin cancer. Emerging data suggests that most mortality from melanoma occurs in patients who was first diagnosed with early-stage (stage I or II) melanoma and then experienced the recurrence years later. This recurrence is typically not detected until metastatic progression, which highlights the need for the development of prognostic tools to identify high-risk patients. This study is to examine the capability of deep learning for detecting prognostic signals of early-stage melanoma from whole-slide histopathology images.