Author: Xueyan Mei; Hao-Chih Lee; Kaiyue Diao; Mingqian Huang; Bin Lin; Chenyu Liu; Zongyu Xie; Yixuan Ma; Philip M. Robson; Michael Chung; Adam Bernheim; Venkatesh Mani; Claudia Calcagno; Kunwei Li; Shaolin Li; Hong Shan; Jian Lv; Tongtong Zhao; Junli Xia; Qihua Long; Sharon Steinberger; Adam Jacobi; Timothy Deyer; Marta Luksza; Fang Liu; Brent P. Little; Zahi A. Fayad; Yang Yang
Title: Artificial intelligence for rapid identification of the coronavirus disease 2019 (COVID-19) Document date: 2020_4_17
ID: 79tozwzq_65
Snippet: We designed a weakly supervised task to initialize weights of the CNN model. Specifically, we randomly selected image patches of lung regions from training images and labeled those patches as the label of the training images. The CNN is then pre-trained to classify these image patches for 1 epoch. This weakly supervised task accords with the idea that the CNN is classifying a local region in the CT image to be SARS-CoV-2 (+/-)......
Document: We designed a weakly supervised task to initialize weights of the CNN model. Specifically, we randomly selected image patches of lung regions from training images and labeled those patches as the label of the training images. The CNN is then pre-trained to classify these image patches for 1 epoch. This weakly supervised task accords with the idea that the CNN is classifying a local region in the CT image to be SARS-CoV-2 (+/-).
Search related documents:
Co phrase search for related documents- CNN model and local region: 1
- CNN model and train image: 1, 2
- CNN model and training image: 1
- CT image and local region: 1
- CT image and lung region: 1
- CT image and train image: 1
- CT image and training image: 1, 2, 3, 4, 5
- image patch and lung region: 1
- image patch and patch label: 1
- local region and lung region: 1
- lung region and training image: 1, 2, 3
Co phrase search for related documents, hyperlinks ordered by date