EUVIMEDEUVIMED entdecken
Crossref

Dual Low-b-value-driven U-shaped fusion GAN for synthesizing high-b-value prostate DWI

Rui Feng, Qun Huang, Aiping Chen, Chuanbing Wang, Leilei Zhou, Jingjing Xu, Xiaodong Wang, Da Cao, Xiuhan Li, Wei Wang

Physical and Engineering Sciences in Medicine · 2026

DOI: 10.1007/s13246-026-01713-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical and Engineering Sciences in Medicine, 2026. Verfasst von Rui Feng und 9 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Province Engineering Research Center of Smart Wearable and Rehabilitation Devices, School of Biomedical Engineering and Informatics, Nanjing …. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Generative Adversarial Networks, Prostate, Image Processing, Computer-Assisted. Die Arbeit nennt 38 Literaturangaben. Gefördert von: The Key R&D of Lianyungang City (Social Development) Project, The Natural Science Foundation of the Jiangsu Higher Education Institutions of China, the National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-b-value (b = 2000 s/mm²) diffusion-weighted imaging (DWI) is vital for prostate disease detection and characterization due to superior tumor-to-background contrast, but its direct acquisition is time-consuming, technically demanding, and prone to noise and artifacts, limiting routine clinical use. This study aims to synthesize high-b-value prostate DWI from low-b-value data via a novel deep learning method. A dual low-b-value-driven U-shaped Fusion Generative Adversarial Network (UsFGAN) was proposed, integrating three core components: (1) U-Net-based dedicated subnetworks (with skip connections) for feature extraction from two low-b-values (b = 50/1000 sec/mm²); (2) Swin-Transformer with residual blocks (STRB) to capture local/long-range pixel dependencies; (3) hierarchical fusion network with multiple feature fusion blocks (MFFB) for adaptive multi-scale feature combination. Validation was done on a multi-center dataset of 280 subjects (6440 DWI slices). The proposed method outperformed state-of-the-art models (CycleGAN, Pix2Pix, DiscoGAN): peak signal-to-noise ratio = 36.14 dB, structural similarity index = 0.91, LPIPS = 0.09, FID = 8.87. Synthesized high-b-value DWI achieved 86.3% accuracy in prostate lesion detection. Radiologist qualitative evaluation confirmed synthesized images were comparable to real high-b-value scans in noise suppression, artifact reduction, and diagnostic acceptability. UsFGAN effectively leverages dual low-b-value complementary information to synthesize high-quality high-b-value prostate DWI. It exhibits superior performance and clinical diagnostic value, promising to reduce scan time and improve prostate disease assessment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diffusion Magnetic Resonance ImagingGenerative Adversarial NetworksProstateImage Processing, Computer-AssistedMaleHumansProstatic NeoplasmsGenerative Artificial Intelligence

Stichwörter der Autor:innen

Diffusion-weighted imagingDual low-b-value-drivenGenerative adversarial networkImage synthesisProstate lesion detection

Autor:innen und Institutionen

  • Jiangsu Province Engineering Research Center of Smart Wearable and Rehabilitation Devices, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, 211166, China.
  • Department of Radiology, Shanghai Fifth People's Hospital, Fudan University, Shanghai, 200240, China.
  • The Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China.
  • Department of Radiology, Nanjing First Hospital, Nanjing Medical University, No.68, Changle Road, Nanjing, 210006, China.
  • Department of Radiology, Zhongda Hospital Southeast University, Nanjing, 210009, China.
  • Department of Medical Information Engineering, Kangda College of Nanjing Medical University, Lianyungang, 222000, China.

Förderung

  • The Key R&D of Lianyungang City (Social Development) Project
  • The Natural Science Foundation of the Jiangsu Higher Education Institutions of China
  • the National Key Research and Development Program of China
  • Clinical Major Project of Changzhou Medical Center of Nanjing Medical University

Zitieren

APA

Feng, R., Huang, Q., Chen, A., Wang, C., Zhou, L., Xu, J., Wang, X., Cao, D., Li, X., & Wang, W. (2026). Dual Low-b-value-driven U-shaped fusion GAN for synthesizing high-b-value prostate DWI. Physical and Engineering Sciences in Medicine. https://doi.org/10.1007/s13246-026-01713-7

Vancouver

Feng R, Huang Q, Chen A, Wang C, Zhou L, Xu J, et al. Dual Low-b-value-driven U-shaped fusion GAN for synthesizing high-b-value prostate DWI. Physical and Engineering Sciences in Medicine. 2026. doi:10.1007/s13246-026-01713-7

BibTeX
@article{Feng2026,
  author = {Feng, Rui and Huang, Qun and Chen, Aiping and Wang, Chuanbing and Zhou, Leilei and Xu, Jingjing and Wang, Xiaodong and Cao, Da and Li, Xiuhan and Wang, Wei},
  title = {Dual Low-b-value-driven U-shaped fusion GAN for synthesizing high-b-value prostate DWI},
  journal = {Physical and Engineering Sciences in Medicine},
  year = {2026},
  doi = {10.1007/s13246-026-01713-7}
}
Kostenlos starten →