Assessing robustness of deep learning methods in dermatological workflow
S Mishra, S Chaudhury, H Imaizumi… - arXiv preprint arXiv …, 2020 - arxiv.org
arXiv preprint arXiv:2001.05878, 2020•arxiv.org
This paper aims to evaluate the suitability of current deep learning methods for clinical
workflow especially by focusing on dermatology. Although deep learning methods have
been attempted to get dermatologist level accuracy in several individual conditions, it has
not been rigorously tested for common clinical complaints. Most projects involve data
acquired in well-controlled laboratory conditions. This may not reflect regular clinical
evaluation where corresponding image quality is not always ideal. We test the robustness of …
workflow especially by focusing on dermatology. Although deep learning methods have
been attempted to get dermatologist level accuracy in several individual conditions, it has
not been rigorously tested for common clinical complaints. Most projects involve data
acquired in well-controlled laboratory conditions. This may not reflect regular clinical
evaluation where corresponding image quality is not always ideal. We test the robustness of …
This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology. Although deep learning methods have been attempted to get dermatologist level accuracy in several individual conditions, it has not been rigorously tested for common clinical complaints. Most projects involve data acquired in well-controlled laboratory conditions. This may not reflect regular clinical evaluation where corresponding image quality is not always ideal. We test the robustness of deep learning methods by simulating non-ideal characteristics on user submitted images of ten classes of diseases. Assessing via imitated conditions, we have found the overall accuracy to drop and individual predictions change significantly in many cases despite of robust training.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果