Physics-informed neural networks for denoising high b-value diffusion-weighted images.
Authors
Affiliations (7)
Affiliations (7)
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen, 361102, Fujian, China.
- Department of Communication Engineering, Xiamen University, Xiamen, 361102, Fujian, China.
- Department of Radiology, Yuyao People's Hospital, Yuyao, 315400, Zhejiang, China.
- Intelligent Instrument and Equipment, Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen, 361102, Fujian, China.
- China Mobile (Suzhou) Software Technology Company Limited, Suzhou, 215163, Jiangsu, China.
- Department of Radiology, Yuyao People's Hospital, Yuyao, 315400, Zhejiang, China. Electronic address: [email protected].
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen, 361102, Fujian, China. Electronic address: [email protected].
Abstract
Diffusion-weighted imaging (DWI) is widely applied in tumor diagnosis by measuring the diffusion of water molecules. To increase the sensitivity to tumor identification, faithful high b-value DWI images are expected by setting a stronger strength of gradient field in magnetic resonance imaging (MRI). However, high b-value DWI images are heavily affected by reduced signal-to-noise ratio due to the exponential decay of signal intensity. Thus, removing noise becomes important for high b-value DWI images. Here, we propose a Physics-Informed neural Network for high b-value DWI images Denoising (PIND) by leveraging information from physics-informed loss and prior information from low b-value DWI images with high signal-to-noise ratio. Experiments are conducted on a prostate DWI dataset that has 125 subjects. Compared with the original noisy images, PIND improves the peak signal-to-noise ratio from 31.25 dB to 36.28 dB, and structural similarity index measure from 0.77 to 0.92. Our schemes can save 83% data acquisition time since fewer averages of high b-value DWI images need to be acquired, while maintaining 98% accuracy of the apparent diffusion coefficient value, suggesting its potential effectiveness in preserving essential diffusion characteristics. Reader study by 4 radiologists (3, 6, 13, and 18 years of experience) indicates PIND's promising performance on overall quality, signal-to-noise ratio, artifact suppression, and lesion conspicuity, showing potential for improving clinical DWI applications.