Table 4. Evaluation metrics for RBC segmentation techniques.
A detailed overview of the segmentation methods used for the segmentation of red blood cells (RBCs). It also illustrates the performance accuracy obtained from each method.
| Work | Segmentation | Performance accuracy | Evaluation parameter |
|---|---|---|---|
| Aliyu et al. (2019) | Otsu threshold and binarization | 94.12% | Accuracy, specificity, and sensitivity |
| Chaudhary et al. (2019) | K-means algorithm | 89% | Accuracy |
| Tran et al. (2019) | SegNet and VGG-16 | 93% | Accuracy, boundary F1 |
| Miao & Xiao (2018) | Marker-controlled watershed | 97.2% and 94.8% | Over/under-segmentation and fault rate |
| Al-Hafiz, Al-Megren & Kurdi (2018) | Threshold value using detection operator | 87.9% | Sensitivity, precision, and F1-Score |
| Rehman et al. (2018) | Local maxima, circles drawing | 96%, 98%, and 4% | TPR, accuracy, ER, and TNR |
| Das, Maiti & Chakraborty (2018) | Marker-controlled watershed algorithm | 99.42% | Accuracy |
| Shirazi et al. (2016c) | Snake algorithm, ostu thresholding | 96% | Accuracy |
| Alomari et al. (2014) | Thresholding | 98.4% | Precision, Recall, and F-measurements |