当前位置: X-MOL 学术IEEE Open J. Eng. Med. Biol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine Learning Approach for Biopsy-Based Identification of Eosinophilic Esophagitis Reveals Importance of Global features
IEEE Open Journal of Engineering in Medicine and Biology ( IF 2.7 ) Pub Date : 2021-06-16 , DOI: 10.1109/ojemb.2021.3089552
Tomer Czyzewski 1 , Nati Daniel 1 , Mark Rochman 2 , Julie M Caldwell 2 , Garrett A Osswald 2 , Margaret H Collins 3 , Marc E Rothenberg 2 , Yonatan Savir 1
Affiliation  

Deep convolutional neural network, together with a systematic downscaling and cropping approach, can classify esophageal biopsies with high accuracy and reveals a global nature of the histologic features of eosinophilic esophagitis. Our approach of systematic analysis of the image size versus downscaling tradeoff can be used to improve disease classification performance and insight gathering in digital pathology.

中文翻译:


基于活检的嗜酸粒细胞性食管炎识别的机器学习方法揭示了全局特征的重要性



深度卷积神经网络结合系统的降尺度和裁剪方法,可以高精度地对食管活检进行分类,并揭示嗜酸性食管炎组织学特征的整体性质。我们对图像大小与缩小尺度权衡进行系统分析的方法可用于提高数字病理学中的疾病分类性能和洞察力收集。
更新日期:2021-06-16
down
wechat
bug