Table 1 The state of the art of prostate cancer diagnosis
From: Improved prostate cancer diagnosis using a modified ResNet50-based deep learning architecture
Year | Authors | Task | Model | Dataset | Metrics |
|---|---|---|---|---|---|
2023 | Yu et al. [26] | Prostate Cancer Diagnosis | UNet- 3D-Resnet | MRI dataset | Dice score = 44.9% |
2023 | Bygari et al. [9] | Prostate Cancer Grading | Xception, Resnet-50, EfficientNet-b7 | Prostate Cancer Grade Assessment Challenge | ACC = 92.38% |
2023 | Provenzano et al. [27] | Classification of ProstateMRI Lesions | ResNet | ProstateX-2 dataset | AUC = (0.82–0.98) |
2023 | Ikromjanov et al. [35] | Prostate Cancer Diagnosis | ResNet-UNet | WSI dataset | IoU = 0.811 |
2023 | Xiang et al. [28] | Prostate Cancer | self-supervised CNN | Prostate Cancer | AUC = 0.985% |
2023 | Zhu et al. [29] | Prostate Cancer Diagnosis | GoogLeNet,20 ResNet101,21 and VGG-net | WSI dataset | ACC = 93.85% |
2022 | Esteva et al. [30] | Prostate Cancer | MMAI Deep learning | Prostate dataset | Metrics = 9.2% to 14.6% |
2022 | Salman et al. [31] | Prostate Cancer Diagnosis | Yolo | Prostate dataset | Acc = 97% |
2021 | Hosseinzadeh et al. [33] | Prostate Cancer | Transfer Learning Models | PI-RADS dataset | AUC = 0.88% |
2021 | Vente et al. [16] | Prostate Cancer | 2D U-Net with MRI | ProstateX-2 challenge | DSC = 0.370 ± 0.046 |