Lung Nodule Malignancy Prediction on In-house (test)
0.899AUC (<10mm)PARE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| PARELearning paradigm=multi-task learning, Ensemble of deep supervision heads=true2023.07 | 0.899 | 0.821 | 0.78 | 0.931 | |
| PARELearning paradigm=multi-task learning2023.07 | 0.892 | 0.817 | 0.783 | 0.927 | |
| CA-NetLearning paradigm=multi-task learning2023.07 | 0.878 | 0.786 | 0.779 | 0.918 | |
| nnUnetLearning paradigm=pure segmentation2023.07 | 0.863 | 0.804 | 0.75 | 0.911 | |
| MiTLearning paradigm=pure classification2023.07 | 0.858 | 0.784 | 0.751 | 0.904 | |
| ASPPLearning paradigm=pure classification2023.07 | 0.854 | 0.788 | 0.743 | 0.901 | |
| CNNLearning paradigm=pure classification2023.07 | 0.851 | 0.797 | 0.744 | 0.901 |