Table 10 Comparison table of the proposed model with previous studies.
From: Privacy preserving skin cancer diagnosis through federated deep learning and explainable AI
Authors | Years | Method | XAI used | Accuracy | Misclassification rate |
|---|---|---|---|---|---|
Srinivasu et al.18 | 2021 | MobileNetV2 and LSTM | × | 85.34% | 14.66% |
Jayapriya & Jacob19 | 2020 | DL method | × | 85.3% | 14.7% |
Ding et al.21 | 2022 | Lesion segmentation method | × | 85.1% | 14.9% |
Lee et al.22 | 2021 | FL/conventional DL | × | 71% 77% 66% 76% 80% | 29% 23% 34% 24% 20% |
Agbley et al.23 | 2021 | FL/CL | × | 83.01% 83.74% | 16.98% 16.26% |
Gouda24 | 2022 | Resnet50-Inception InceptionV3 | × | 84.1% 85.7% | 15.9% 14.3% |
Sae-Lim25 | 2019 | MobileNet | × | 83.9% | 16.1% |
Purposed model | 2025 | VGG19 With FL and XAI | ✓ | 86.52% | 13.48% |
