Table 1.
Overview of pretrained models.
| Ref. | Year | Model | Findings | Modality | Accuracy |
|---|---|---|---|---|---|
| [50] | 2021 | VGG16 | Brain tumor classification | MRI | 95.71% |
| [51] | 2020 | ResNet50 | Brain tumor classification | MRI | 97.2% |
| [52] | 2020 | GoogleNet | Alzheimer's disease classification | MRI | 97.15% |
| [53] | 2020 | Ensemble of AlexNet, DenseNet121, ResNet18, GoogleNet, InceptionV3 | Pneumonia detection | X-ray | 96.4% |
| [54] | 2020 | AlexNet | Lung nodule classification | CT and X-ray | 99.6% |
| [55] | 2020 | ResNet50 | Breast tumor classification | Mammogram | 85.71% |
| [56] | 2020 | ResNet50 | Breast tumor classification | Histopathological images | 99% |
| [57] | 2021 | VGG16 | Breast tumor classification | Mammogram | 98.96% |
| [58] | 2020 | DenseNet201 | Skin lesion classification | Skin images | 96.18% |
| [59] | 2020 | GoogleNet | Skin image classification | Skin images | 99.29% |
| [60] | 2021 | VGG19 | Thyroid nodule cell classification | Cytology images | 93.05% |
| [61] | 2021 | GoogleNet | Thyroid nodule classification | Ultrasound | 96.04% |
| [36] | 2021 | GoogleNet | Colorectal polyps classification | Gastrointestinal polyp images | 98.44% |
| [62] | 2020 | Faster R-CNN+VGG16 | Brain tumor segmentation and classification | MRI | 77.60% |
| [63] | 2021 | U-Net+InceptionV3 | Breast tumor segmentation and classification | Mammogram | 98.87% |
| [64] | 2020 | Mask R-CNN+ResNet-50 | White blood cells detection and classification | Cytological images | 95.3% |