The spherical interpolation approach is shown in Fig. 7. The left most and right most blue dots denote ADC encodings in the la- tent space derived from two real CS ADC maps. By interpolating additional dots between the two encodings, we could generate a set of new latent vectors (i.e. 2nd − 7th blue dots), based on which new fake ADC images can be generated via the decoder. A decoder learns a complete mapping relationship between latent vectors and ADC images should be able to generate smoothly transitional images from interpolated vectors between every two real images. To validate this, we purposely select two real ADC maps (i.e. the left- most and rightmost images of Fig. 7) from the TestSet with a single CS PCa lesion locating on the right (in the leftmost image) and the top (in the rightmost image) of the prostate gland respectively. The lesions are visually darker than surrounding tissues as denoted by the red circles. Fig. 7(a) and (b) show synthesized ADC maps based on interpolations by the semi-supervised and supervised synthesizers respectively. As seen in Fig. 7(a), the CS PCa lesion is gradually and smoothly transitioned from the right to the top in the prostate gland, while the first three images of CS PCa in Fig. 7(b) are almost identical to the leftmost real image and the transition from the 4th image (i.e. lesion on the right) to the 5th image (i.e. lesion at the top) is sudden and not smooth.