A two-stage deep transfer learning model and its application for medical image processing in Traditional Chinese Medicine
作者：
Highlights：
• A designed two-stage deep transfer learning strategy with good explainability.
• The model of Traditional Chinese medicine tongue diagnosis is ingeniously realized.
• Corresponding optimized network structure for its computerization.
• Improve classifier to simulate important medical theories, improve the accuracy.
• Accurate and real-time auxiliary diagnosis in real collected clinical dataset.
摘要
•A designed two-stage deep transfer learning strategy with good explainability.•The model of Traditional Chinese medicine tongue diagnosis is ingeniously realized.•Corresponding optimized network structure for its computerization.•Improve classifier to simulate important medical theories, improve the accuracy.•Accurate and real-time auxiliary diagnosis in real collected clinical dataset.
论文关键词：Deep transfer learning,Deep neural networks,Medical image processing,Traditional Chinese Medicine,Tongue diagnosis
论文评审过程：Received 30 July 2021, Revised 13 December 2021, Accepted 24 December 2021, Available online 30 December 2021, Version of Record 13 January 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.108060
