Table 3.
The mean apparent diffusion coefficient (ADC) values (×10-3 mm2/s) of the different ADC sets.
| Parameter | ADC value (×10-3 mm2/s) | |||
|---|---|---|---|---|
| Peripheral zone (n = 10) | Transitional zone (n = 10) | Benign lesions (n = 26) | Malignant lesions (n = 24) | |
| Reader 1 | ||||
| f-ADC | 1.90 ± 0.11 | 1.41 ± 0.13 | 1.40 ± 0.28 | 1.06 ± 0.25 |
| z-ADC | 1.43 ± 0.17 | 1.20 ± 0.16 | 0.98 ± 0.18 | 0.61 ± 0.11 |
| s-ADCb50 | 1.43 ± 0.25 | 1.20 ± 0.18 | 1.09 ± 0.23 | 0.68 ± 0.13 |
| s-ADCb1000 | 1.43 ± 0.16 | 1.20 ± 0.16 | 0.99 ± 0.18 | 0.61 ± 0.17 |
| s-ADCb1500 | 1.46 ± 0.18 | 1.26 ± 0.16 | 1.01 ± 0.17 | 0.67 ± 0.18 |
| Reader 2 | ||||
| f-ADC | 1.94 ± 0.14 | 1.39 ± 0.19 | 1.42 ± 0.29 | 1.06 ± 0.25 |
| z-ADC | 1.49 ± 0.16 | 1.22 ± 0.14 | 0.98 ± 0.18 | 0.61 ± 0.11 |
| s-ADCb50 | 1.44 ± 0.13 | 1.18 ± 0.14 | 1.02 ± 0.24 | 0.69 ± 0.13 |
| s-ADCb1000 | 1.48 ± 0.21 | 1.18 ± 0.13 | 0.99 ± 0.16 | 0.61 ± 0.15 |
| s-ADCb1500 | 1.45 ± 0.12 | 1.18 ± 0.09 | 1.00 ± 0.16 | 0.70 ± 0.10 |
The ADC values of the lesions were calculated using images from the patients in test set 1. The ADC values of the normal prostate tissues in the peripheral and transitional zones were calculated using images from the healthy volunteers in test set 2.
f-ADC, ADC map derived from full field-of-view (FOV) diffusion-weighted imaging (f-DWI) with all available b-values (b =50, 1,000, and 1,500 s/mm2); z-ADC, ADC map derived from the zoomed FOV diffusion-weighted imaging and all available b-values (b = 50, 1,000, and 1,500 s/mm2); s-ADCb50, ADC map synthesized using our proposed deep learning framework with input from the f-DWI (b = s/mm2); s-ADCb1000, ADC map synthesized using our proposed deep learning framework with input from the f-DWI (b =1,000 s/mm2); s-ADCb1500, ADC map synthesized using our proposed deep learning framework with input from the f-DWI (b =1,500 s/mm2).