Research Article
Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories
Table 4
Performance comparison between the proposed intelligent tool and related works based on the HAM1000 dataset.
| Article | Accuracy (%) | Sensitivity | Specificity | Precision | F1-score |
| [67] | 85.8 | — | — | — | — | [43] | 86.5 | 85.57% | — | 87.01% | 86.28% | [44] | 88.5 | — | — | 88.66% | 88.66% | [68] | 90.72 | — | — | — | — | [69] | 90.67 | 90.2% | — | — | — | [70] | 92.08 | 92.53% | — | 93.73% | 92.74 | [35] | 96.25 | — | — | — | — | [37] | 97.4 | 92% | 90% | — | — | Proposed tool | 99 | 98.54% | 99.69% | 98.84% | 98.83% |
|
|