BriefGPT.xyz
Jun, 2020
探究和利用图像分辨率进行基于迁移学习的皮肤病变分类
Investigating and Exploiting Image Resolution for Transfer Learning-based Skin Lesion Classification
HTML
PDF
Amirreza Mahbod, Gerald Schaefer, Chunliang Wang, Rupert Ecker, Georg Dorffner...
TL;DR
本文研究了使用不同输入图像尺寸 fine-tuned CNNs 进行皮肤病变分类的性能,提出了一种基于三级集成策略的新型融合方法,取得了比现有算法更好的分类结果。
Abstract
skin cancer
is among the most common cancer types.
dermoscopic image
analysis improves the diagnostic accuracy for detection of malignant melanoma and other pigmented skin lesions when compared to unaided visual
→