Table 3.
Related work overview for COVID-19 segmentation and comparison of resulting segmentation performances. The table categories the related work in terms of model architecture, training dataset information for comparability like source, dimension (Dim.), sample size as well as the presence of non-COVID-19 slices (Control) and their performance on a validation/testing set.
| Related Work |
Training Dataset |
Validation/Testing Performance |
|||||
|---|---|---|---|---|---|---|---|
| Author | Model Architecture | Source | Dim. | Sample Size | Control | DSC – COVID-19 | Sample Size |
| Amyar et al. [5] | U-Net (Standard) | Amyar et al. [5] | 2D | 1219 | Yes | 0.78 | 150 |
| Fan et al. [41] | Inf-Net (Attention U-Net) | Fan et al. [41] | 2D | 1650 | Yes | 0.764 | 50 |
| Qiu et al. [43] | MiniSeg (Attention U-Net) | Qiu et al. [43] | 2D | 3558 | Yes | 0.773 | 3558 |
| Saood et al. [37] | U-Net (Standard) | SIRM [66] | 2D | 80 | No | 0.733 | 20 |
| Saood et al. [37] | SegNet | SIRM [66] | 2D | 80 | No | 0.749 | 20 |
| Pei et al. [38] | MPS-Net (Supervision U-Net) | SIRM [66] | 2D | 300 | No | 0.833 | 68 |
| Zheng et al. [39] | MSD-Net | Zheng et al. [39] | 2D | 3824 | Yes | 0.785 | 956 |
| Wang et al. [40] | COPLE-Net (enhanced U-Net) | Wang et al. [40] | 2D | 59,045 | Yes | 0.803 | 17,205 |
| Ma et al. [16] | U-Net (Standard) | Ma et al. [16] | 3D | 20 | Yes | 0.608 | 20 |
| Ma et al. [16,57] | nnU-Net | Ma et al. [16] | 3D | 20 | Yes | 0.673 | 20 |
| Wang et al. [44] | U-Net (Standard) | Wang et al. [44] | 3D | 211 | Yes | 0.704 | 211 |
| Yan et al. [65] | COVID-SegNet | Yan et al. [65] | 3D | 731 | Yes | 0.726 | 130 |
| He et al. [42] | M2UNet (Segmentation only) | He et al. [42] | 3D | 666 | Yes | 0.759 | 666 |
| Our Pipeline | U-Net (Standard) | Ma et al. [16] | 3D | 20 | Yes | 0.804/0.661 | 20/100 |