Synthesizing High- b-Value Diffusion-weighted Imaging of the Prostate Using Generative Adversarial Networks

Lei Hu; Da-Wei Zhou; Yun-Fei Zha; Liang Li; Huan He; Wen-Hao Xu; Li Qian; Yi-Kun Zhang; Cai-Xia Fu; Hui Hu; Jun-Gong Zhao

doi:10.1148/ryai.2021200237

Synthesizing High- b-Value Diffusion-weighted Imaging of the Prostate Using Generative Adversarial Networks

Radiol Artif Intell. 2021 Jun 2;3(5):e200237. doi: 10.1148/ryai.2021200237. eCollection 2021 Sep.

Authors

Lei Hu¹, Da-Wei Zhou¹, Yun-Fei Zha¹, Liang Li¹, Huan He¹, Wen-Hao Xu¹, Li Qian¹, Yi-Kun Zhang¹, Cai-Xia Fu¹, Hui Hu¹, Jun-Gong Zhao¹

Affiliation

¹ Department of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, 600 Yi Shan Road, Shanghai 200233, China (L.H., W.H.X., J.G.Z.); State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi'an, China (D.W.Z.); Department of Radiology, Renmin Hospital, Wuhan University, Wuhan, China (Y.F.Z., L.L., H. He, L.Q., Y.K.Z.); MR Application Development, Siemens Shenzhen MR, Shenzhen, China (C.X.F.); and Department of Radiology, The Affiliated Renmin Hospital of Jiangsu University, Zhenjiang, China (H. Hu).

Abstract

Purpose: To develop and evaluate a diffusion-weighted imaging (DWI) deep learning framework based on the generative adversarial network (GAN) to generate synthetic high-b-value (b =1500 sec/mm²) DWI (SYN_b1500) sets from acquired standard-b-value (b = 800 sec/mm²) DWI (ACQ_b800) and acquired standard-b-value (b = 1000 sec/mm²) DWI (ACQ_b1000) sets.

Materials and methods: This retrospective multicenter study included 395 patients who underwent prostate multiparametric MRI. This cohort was split into internal training (96 patients) and external testing (299 patients) datasets. To create SYN_b1500 sets from ACQ_b800 and ACQ_b1000 sets, a deep learning model based on GAN (M₀) was developed by using the internal dataset. M₀ was trained and compared with a conventional model based on the cycle GAN (M_cyc). M₀ was further optimized by using denoising and edge-enhancement techniques (optimized version of the M₀ [Opt-M₀]). The SYN_b1500 sets were synthesized by using the M₀ and the Opt-M₀ were synthesized by using ACQ_b800 and ACQ_b1000 sets from the external testing dataset. For comparison, traditional calculated (b =1500 sec/mm²) DWI (CAL_b1500) sets were also obtained. Reader ratings for image quality and prostate cancer detection were performed on the acquired high-b-value (b = 1500 sec/mm²) DWI (ACQ_b1500), CAL_b1500, and SYN_b1500 sets and the SYN_b1500 set generated by the Opt-M₀ (Opt-SYN_b1500). Wilcoxon signed rank tests were used to compare the readers' scores. A multiple-reader multiple-case receiver operating characteristic curve was used to compare the diagnostic utility of each DWI set.

Results: When compared with the M_cyc, the M₀ yielded a lower mean squared difference and higher mean scores for the peak signal-to-noise ratio, structural similarity, and feature similarity (P < .001 for all). Opt-SYN_b1500 resulted in significantly better image quality (P ≤ .001 for all) and a higher mean area under the curve than ACQ_b1500 and CAL_b1500 (P ≤ .042 for all).

Conclusion: A deep learning framework based on GAN is a promising method to synthesize realistic high-b-value DWI sets with good image quality and accuracy in prostate cancer detection.Keywords: Prostate Cancer, Abdomen/GI, Diffusion-weighted Imaging, Deep Learning Framework, High b Value, Generative Adversarial Networks© RSNA, 2021 Supplemental material is available for this article.

Keywords: Abdomen/GI; Deep Learning Framework; Diffusion-weighted Imaging; Generative Adversarial Networks; High b Value; Prostate Cancer.

2021 by the Radiological Society of North America, Inc.