Background <p>Diffusion-weighted imaging with higher <i>b</i>-value improves detection rate for prostate cancer lesions. However, obtaining high <i>b</i>-value DWI requires more advanced hardware and software configuration. Here we use a novel deep learning network, NAFNet, to generate a deep learning reconstructed (DLR₁₅₀₀) images from 800 <i>b</i>-value to mimic 1500 <i>b</i>-value images, and to evaluate its performance and lesion detection improvements based on whole-slide images (WSI).</p> Methods <p>We enrolled 303 prostate cancer patients with both 800 and 1500 <i>b</i>-values from Fudan University Shanghai Cancer Centre between 2017 and 2020. We assigned these patients to the training and validation set in a 2:1 ratio. The testing set included 36 prostate cancer patients from an independent institute who had only preoperative DWI at 800 <i>b</i>-value. Two senior radiology doctors and two junior radiology doctors read and delineated cancer lesions on DLR₁₅₀₀, original 800 and 1500 <i>b</i>-values DWI images. WSI were used as the ground truth to assess the lesion detection improvement of DLR₁₅₀₀ images in the testing set.</p> Results <p>After training and generating, within junior radiology doctors, the diagnostic AUC based on DLR₁₅₀₀ images is not inferior to that based on 1500 <i>b</i>-value images (0.832 (0.788–0.876) vs. 0.821 (0.747–0.899), <i>P</i> = 0.824). The same phenomenon is also observed in senior radiology doctors. Furthermore, in the testing set, DLR₁₅₀₀ images could significantly enhance junior radiology doctors’ diagnostic performance than 800 <i>b</i>-value images (0.848 (0.758–0.938) vs. 0.752 (0.661–0.843), <i>P</i> = 0.043).</p> Conclusions <p>DLR₁₅₀₀ DWIs were comparable in quality to original 1500 <i>b</i>-value images within both junior and senior radiology doctors. NAFNet based DWI enhancement can significantly improve the image quality of 800 <i>b</i>-value DWI, and therefore promote the accuracy of prostate cancer lesion detection for junior radiology doctors.</p>