18 June 2020 : Clinical Research
Ensemble Deep Learning Model for Multicenter Classification of Thyroid Nodules on Ultrasound Images
Xi Wei1ACDEG*, Ming Gao2BEF, Ruiguo Yu3BCD, Zhiqiang Liu3BCE, Qing Gu4BC, Xun Liu5BC, Zhiming Zheng6BC, Xiangqian Zheng2BC, Jialin Zhu1ABCDEF, Sheng Zhang1BDDOI: 10.12659/MSM.926096
Med Sci Monit 2020; 26:e926096
Table 3 Comparison of the diagnostic performance of EDLC-TN with radiologists.
| Accuracy | Sensitivity | Specificity | |
|---|---|---|---|
| EDLC-TN | 93.70% | 93.19% | 94.01% |
| Radiologist 1 | 91.55% | 91.45% | 91.71% |
| Radiologist 2 | 87.26% | 96.34% | 72.19% |
| Radiologist 3 | 93.07% | 92.56% | 93.92% |
| Average of radiologists | 90.63% | 93.45% | 85.94% |
| Radiologists and EDLC-TN | 96.54% | 97.11% | 95.58% |
| EDLC-TN – ensemble deep learning classification model of thyroid nodules. | |||