当前位置: X-MOL 学术J. Instrum. › 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.)
Study on the TB and non-TB diagnosis using two-step deep learning-based binary classifier
Journal of Instrumentation ( IF 1.3 ) Pub Date : 2020-10-13 , DOI: 10.1088/1748-0221/15/10/p10011
S.H. Yoo 1 , H. Geng 1 , T.L. Chiu 1 , S.K. Yu 1 , D.C. Cho 2 , J. Heo 2 , M.S. Choi 2 , I.H. Choi 2 , C.V. Cung 3 , N.V. Nhung 3 , B.J. Min 4
Affiliation  

A deep learning-based binary classifier was proposed to diagnose tuberculosis (TB) and non-TB disease using a chest X-ray radiograph. The proposed classifier comprised two-step binary decision trees, each trained by a deep learning model with convolution neural network (CNN) based on the PyTorch frame. Normal and abnormal images of chest X-ray was classified in the first step. The abnormal images were predicted to be classified into TB and non-TB disease by the second step of the process. The accuracies of first and second step were 98% and 80% respectively. Moreover, re-training could improve the stability of prediction accuracy for images in different data groups.

中文翻译:

基于两步深度学习的二元分类器对结核病和非结核病的诊断研究

提出了一种基于深度学习的二元分类器,以使用胸部X光片检查诊断结核病和非结核病。拟议的分类器包括两步二叉决策树,每个决策树都由具有基于PyTorch框架的卷积神经网络(CNN)的深度学习模型训练。第一步,对胸部X光的正常和异常图像进行分类。预计该过程的第二步会将异常图像分为TB和非TB疾病。第一步和第二步的准确性分别为98%和80%。此外,重新训练可以提高不同数据组中图像的预测精度的稳定性。
更新日期:2020-10-14
down
wechat
bug