Multi-modal feature-fusion for CT metal artifact reduction using edge-enhanced generative adversarial networks. (April 2022)

• Record Type: Journal Article
• Authors: Huang, Zhiwei; Zhang, Guo; Lin, Jinzhao; Pang, Yu; Wang, Huiqian; Bai, Tong; Zhong, Lisha
• Is Part Of: Computer methods and programs in biomedicine. Volume 217(2022)
• Publication Date: 2022-04
• Subjects: Feature fusion -- Generative adversarial network -- Metal artifact reduction -- Second artifact -- Edge enhancement; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106700
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Multi-modal feature-fusion edge-enhance generative adversarial networks (MFE-GAN) method for CT image metal artifact reduction. Incorporating multi-modal fusion feature into the proposed MFE-GAN to preserve symptom invariance. Introducing edge-enhance sub-network to maintain clear texture and detailed edges while effectively suppressing the noises. Conducting comprehensive experiments objectively and subjectively, including corrected CT images evaluation and diagnostic quality assessment. Abstract: Computed Tomography (CT) imaging is one of the most widely-used and cost-effective technology for organ screening and diseases diagnosis. Because of existence of metallic implants in some patients, the CT images acquired from these patients are often corrupted by undesirable metal artifacts, which causes severe problem of metal artifact. Although there have been proposed many methods to reduce metal artifact, reduction is still challenging and inadequate, and results are suffering from symptom variance, second artifact and poor subjective evaluation. To address these problems, we propose a novel metal artifact reduction method based on generative adversarial networks to simultaneously reduce metal artifacts and enhance texture structure of corrected CT images. Specifically, we firstly incorporate interactive information (text) and imaging CT (image) into a comprehensive feature to yield multi-modal feature-fusion representation, which overcomes the representative ability limitation of single-modal data. The incorporation of interaction information constrains the feature generation to ensure symptom consistency between corrected and target CT. Then, we design an edge-enhance sub-network to avoid second artifact and suppress noise. Besides, we invite three professional physicians to evaluate corrected CT image subjectively. In this paper, We achieved average increment of 11.3% PSNR and 12.1% SSIM on DeepLesion dataset. The subjective evaluations by physicians show that ours outperforms over 6.3%, 7.1%, 5.50% and 6.9% in term of sharpness, resolution, invariance and acceptability, respectively. Our proposed method can achieve high-quality metal artifact reduction results. Graphical abstract: Image, graphical abstract