An ensemble deep learning for automatic prediction of papillary thyroid carcinoma using fine needle aspiration cytology
作者：
Highlights：
• Deep learning for identifying papillary thyroid carcinomas and computing certainty.
• Ensemble technique combines multiple deep CNNs to significantly increase accuracies.
• GRAD-CAM method highlights dominant tissues for the discriminative decision-making.
• Effectiveness of stain normalization methods on predictive performances is evaluated.
• Proposed ensemble learning is superior to current models for automatic diagnosis.
摘要
•Deep learning for identifying papillary thyroid carcinomas and computing certainty.•Ensemble technique combines multiple deep CNNs to significantly increase accuracies.•GRAD-CAM method highlights dominant tissues for the discriminative decision-making.•Effectiveness of stain normalization methods on predictive performances is evaluated.•Proposed ensemble learning is superior to current models for automatic diagnosis.
论文关键词：Papillary thyroid carcinoma,Fine needle aspiration cytology,Computer-aided diagnosis,Deep CNN models,Ensemble learning,ThinPrep
论文评审过程：Received 5 January 2021, Revised 27 July 2021, Accepted 16 September 2021, Available online 2 October 2021, Version of Record 16 October 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115927
