1
|
Zhang Y, Wan Z, Wang D, Meng J, Ma F, Guo Y, Liu J, Li G, Liu Y. Multi-scale feature aggregation and fusion network with self-supervised multi-level perceptual loss for textures preserving low-dose CT denoising. Phys Med Biol 2024. [PMID: 38593821 DOI: 10.1088/1361-6560/ad3c91] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/11/2024]
Abstract
OBJECTIVE The textures and detailed structures in computed tomography (CT) images are highly desirable for clinical diagnosis. This study aims to expand the current body of work on textures and details preserving convolutional neural networks for low-dose CT (LDCT) image denoising task. APPROACH This study proposed a novel Multi-scale Feature Aggregation and Fusion network (MFAF-net) for LDCT image denoising. Specifically, we proposed a Multi-scale Residual Feature Aggregation Module (MRFAM) to characterize multi-scale structural information in CT images, which captures regional-specific inter-scale variations using learned weights. We further proposed a Cross-level Feature Fusion Module (CFFM) to integrate cross-level features, which adaptively weights the contributions of features from encoder to decoder by using a Spatial Pyramid Attention (SPA) mechanism. Moreover, we proposed a Self-supervised Multi-level Perceptual Loss Module (SMPLM) to generate multi-level auxiliary perceptual supervision for recovery of salient textures and structures of tissues and lesions in CT images, which takes advantage of abundant semantic information at various levels. We introduced parameters for the perceptual loss to adaptively weight the contributions of auxiliary features of different levels and we also introduced an automatic parameter tuning strategy for these parameters. MAIN RESULTS Extensive experimental studies were performed to validate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method can achieve better performance on both fine textures preservation and noise suppression for CT image denoising task compared with other competitive CNN based methods. SIGNIFICANCE The proposed MFAF-net takes advantage of multi-scale receptive fields, cross-level features integration and self-supervised multi-level perceptual loss, enabling more effective recovering of fine textures and detailed structures of tissues and lesions in CT images.
Collapse
Affiliation(s)
- Yuanke Zhang
- School of Computer Science, Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Zhaocui Wan
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Dong Wang
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Jing Meng
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Fei Ma
- School of Computer Science, Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Yanfei Guo
- School of Computer Science, Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Jianlei Liu
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Guangshun Li
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA
| | - Yang Liu
- School of biomedical engineering, Fourth Military Medical University, 169#, Changlexi Road, Xi'an, 710032, CHINA
| |
Collapse
|