Table 2 Comparison between segmentation performance (IoU) of the proposed approach with other methods
From: Grayscale medical image segmentation method based on 2D&3D object detection with deep learning
Datasets | Proposed | FCN | UNet | UNet++ | Res-UNet | Attention Unet |
|---|---|---|---|---|---|---|
Musculoskeletal radiographs | 0.92 | 0.82 | 0.85 | 0.84 | 0.91 | 0.90 |
Chest radiographs | 0.88 | 0.76 | 0.81 | 0.83 | 0.88 | 0.86 |
Images from X-ray machine | 0.94 | 0.72 | 0.82 | 0.87 | 0.85 | 0.91 |