LesionNet:使SIFT

Sarah A Alzakari1, Stephen Ojo2, James Wanliss2

  • 1Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia.

Frontiers in medicine
|November 5, 2024
PubMed
概括

这项研究介绍了LesionNet,这是一种用于检测皮肤病变的计算机辅助诊断工具. 通过将规模不变特征转换 (SIFT) 与定制卷积神经网络相结合,它在识别黑色细胞病变时达到99.28%的准确性.