Research Article
Intelligent Segmentation Medical Assistance System for MRI Images of Osteosarcoma in Developing Countries
Table 3
Comparison of performance of different methods in MRI images of patients with osteosarcoma.
| Model | Pr | Re | F1 | IOU | DSC | Params | FLOPs |
| FCN-16s | 0.922 | 0.882 | 0.900 | 0.824 | 0.859 | 134.3M | 190.35G | FCN-8s | 0.941 | 0.873 | 0.901 | 0.830 | 0.876 | 134.3M | 190.08G | PSPNet | 0.856 | 0.888 | 0.872 | 0.772 | 0.870 | 49.07M | 101.55G | MSFCN [3] | 0.881 | 0.936 | 0.906 | 0.841 | 0.874 | 20.38M | 1524.34G | MSRN [4] | 0.893 | 0.945 | 0.918 | 0.853 | 0.887 | 14.27M | 1461.23G | FPN | 0.914 | 0.924 | 0.919 | 0.852 | 0.888 | 88.63M | 141.45G | UNet | 0.922 | 0.924 | 0.923 | 0.867 | 0.892 | 17.26M | 160.16G |
| Our (SepUNet) | 0.927 | 0.932 | 0.930 | 0.869 | 0.896 | 20.32M | 199.26G | Our (SepUNet+CRF) | 0.939 | 0.926 | 0.932 | 0.874 | 0.901 | 20.32M | 200.07G | Our (SepUNet+CRF +Prop) | 0.937 | 0.938 | 0.937 | 0.883 | 0.914 | 20.32M | 200.07G |
|
|