First author [reference number] | Overall sample size | AI family | AI method | Public/external datasets used | Images used | Loss functions | AUC | Dice similarity coefficient |
---|---|---|---|---|---|---|---|---|
Wang [11] | 90 | Whole gland segmentation | 3D CNN + skip connections | PROMISE12 | T2-weighted | Cross-entropy + cosine loss |  | 0.86−0.88 |
Ushinsky [12] | 299 | Whole gland segmentation | Hybrid 2D-3D CNN + skip connections | Â | T2-weighted | Adam loss | Â | 0.88 |
Sanford [13] | 648 | Whole gland segmentation | Hybrid 2D-3D CNN | Five separate unaffiliated institutional independent datasets | T2-weighted | Dice similarity coefficient loss | Â | 0.931 |
Cao et al. [14] | 417 | Lesion detection | 3D CNN FocalNet | Â | T2-weighted, ADC maps, echo-planar | Mutual finding loss | 0.81 | Â |
Ishioka [15] | 335 | Lesion detection | U-net + ResNet50 (skip connections) |  | T2-weighted | Adam loss | 0.64–0.65 |  |
Le [16] | 364 | Lesion classification | Two parallel 2D CNNs | The Cancer Imaging Database (TCIA) | T2, ADC maps | Similarity loss | 0.91 | Â |
Liu et al. [17] | 341 | Lesion classification | 3D CNN XmasNet | PROSTATE-x | T2, ADC, diffusion-weighted, Ktrans | Adam loss | 0.84 | Â |