Deep learning network enhances imaging quality of low-b-value diffusion-weighted imaging and improves lesion detection in prostate cancer.
Authors
Affiliations (13)
Affiliations (13)
- Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
- Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China.
- Shanghai Genitourinary Cancer Institute, 200032, Shanghai, China.
- Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
- Department of Pathology, Fudan University Shanghai Cancer Center, 200032, Shanghai, China.
- Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China. [email protected].
- Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China. [email protected].
- Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China. [email protected].
- Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China. [email protected].
- Shanghai Genitourinary Cancer Institute, 200032, Shanghai, China. [email protected].
- Department of Urology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China. [email protected].
- Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China. [email protected].
- Shanghai Genitourinary Cancer Institute, 200032, Shanghai, China. [email protected].
Abstract
Diffusion-weighted imaging with higher b-value improves detection rate for prostate cancer lesions. However, obtaining high b-value DWI requires more advanced hardware and software configuration. Here we use a novel deep learning network, NAFNet, to generate a deep learning reconstructed (DLR<sub>1500</sub>) images from 800 b-value to mimic 1500 b-value images, and to evaluate its performance and lesion detection improvements based on whole-slide images (WSI). We enrolled 303 prostate cancer patients with both 800 and 1500 b-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 b-value. Two senior radiology doctors and two junior radiology doctors read and delineated cancer lesions on DLR<sub>1500</sub>, original 800 and 1500 b-values DWI images. WSI were used as the ground truth to assess the lesion detection improvement of DLR<sub>1500</sub> images in the testing set. After training and generating, within junior radiology doctors, the diagnostic AUC based on DLR<sub>1500</sub> images is not inferior to that based on 1500 b-value images (0.832 (0.788-0.876) vs. 0.821 (0.747-0.899), P = 0.824). The same phenomenon is also observed in senior radiology doctors. Furthermore, in the testing set, DLR<sub>1500</sub> images could significantly enhance junior radiology doctors' diagnostic performance than 800 b-value images (0.848 (0.758-0.938) vs. 0.752 (0.661-0.843), P = 0.043). DLR<sub>1500</sub> DWIs were comparable in quality to original 1500 b-value images within both junior and senior radiology doctors. NAFNet based DWI enhancement can significantly improve the image quality of 800 b-value DWI, and therefore promote the accuracy of prostate cancer lesion detection for junior radiology doctors.