Abstract
Due to the existence of metallic implants in certain patients, the Computed Tomography (CT) images from these patients are often corrupted by undesirable metal artifacts, which causes severe problem of metal artifact. Although many methods have been proposed to reduce metal artifact, reduction is still challenging and inadequate. Some reduced results are suffering from symptom variance, second artifact, and poor subjective evaluation. To address these, we propose a novel method based on generative adversarial nets (GANs) to reduce metal artifacts. Specifically, we firstly encode interactive information (text) and imaging CT (image) to yield multi-modal feature-fusion representation, which overcomes representative ability limitation of single-modal CT images. The incorporation of interaction information constrains feature generation, which ensures symptom consistency between corrected and target CT. Then, we design an enhancement network to avoid second artifact and enhance edge as well as suppress noise. Besides, three radiology physicians are invited to evaluate the corrected CT image. Experiments show that our method gains significant improvement over other methods. Objectively, ours achieves an average increment of 7.44% PSNR and 6.12% SSIM on two medical image datasets. Subjectively, ours outperforms others in comparison in term of sharpness, resolution, invariance, and acceptability.
- [1] . 1987. Reduction of CT artifacts caused by metallic implants. Radiology 164, 2 (1987), 576–577.Google Scholar
Cross Ref
- [2] . 2017. Wasserstein GAN. In International Conference on Machine Learning. 214–223.Google Scholar
- [3] . 2005. A radial adaptive filter for metal artifact reduction. In SPIE Medical Imaging. 2075–2082.Google Scholar
- [4] . 2012. Multiple-gradient descent algorithm (MGDA) for multiobjective optimization. Comptes Rendus Mathematique 350, 5 (2012), 313–318.Google Scholar
Cross Ref
- [5] . 2017. Deep learning methods to guide CT image reconstruction and reduce metal artifacts. In SPIE Medical Imaging. 21–27.Google Scholar
- [6] . 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems. 2672–2680.Google Scholar
Digital Library
- [7] . 2017. GANs trained by a two time-scale update rule converge to a Nash equilibrium. In Advances in Neural Information Processing Systems. 2672–2680.Google Scholar
- [8] . 2017. Train longer, generalize better: Closing the generalization gap in large batch training of neural networks. In Advances in Neural Information Processing Systems. 1731–1741.Google Scholar
- [9] . 2019. Edge-enhanced GAN for remote sensing image superresolution. IEEE Transactions on Geoscience and Remote Sensing 57, 8 (2019), 5579–5812.Google Scholar
Cross Ref
- [10] . 2001. Generalized multi-dimensional adaptive filtering for conventional and spiral single-slice, multi-slice, and cone-beam CT. Medical Physics 28, 4 (2001), 475–490.Google Scholar
Cross Ref
- [11] . 2017. Progressive growing of GANs for improved quality, stability, and variation. In International Conference on Learning Representations. 1–26.Google Scholar
- [12] . 2017. Photo-realistic single image super-resolution using a generative adversarial network. In IEEE Conference on Computer Vision and Pattern Recognition. 4681–4690.Google Scholar
Cross Ref
- [13] . 2009. Suppression of metal artifacts in CT using a reconstruction procedure that combines MAP and projection completion. IEEE Transactions on Medical Imaging 28, 2 (2009), 250–260.Google Scholar
Cross Ref
- [14] . 2007. A closed-form solution to natural image matting. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 2 (2007), 228–242.Google Scholar
Digital Library
- [15] . 2020. ADN: Artifact disentanglement network for unsupervised metal artifact reduction. IEEE Transactions on Medical Imaging 39, 3 (2020), 634–643.Google Scholar
Cross Ref
- [16] . 2019. DuDoNet: Dual domain network for CT metal artifact reduction. In IEEE Conference on Computer Vision and Pattern Recognition. 10512–10521.Google Scholar
Cross Ref
- [17] . 2010. Normalized metal artifact reduction (NMAR) in computed tomography. Medical Physics 37, 10 (2010), 5482–5493.Google Scholar
Cross Ref
- [18] . 2016. Metal artifact reduction for polychromatic X-ray CT based on a beam-hardening corrector. IEEE Transactions on Medical Imaging 35, 2 (2016), 480–487.Google Scholar
Cross Ref
- [19] . 2009. A novel forward projection-based metal artifact reduction method for flat-detector computed tomography. Physics in Medicine and Biology 54, 21 (2009), 6575–6591.Google Scholar
Cross Ref
- [20] . 2017. Improved techniques for training GANs. In Advances in Neural Information Processing Systems. 2234–2242.Google Scholar
- [21] . 2005. An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Transactions on Image Processing 14, 12 (2005), 2117–2128.Google Scholar
Digital Library
- [22] . 2018. How good is my GAN? In IEEE Conference on Computer Vision and Pattern Recognition. 3654–3668.Google Scholar
Digital Library
- [23] . 2018. Conditional generative adversarial networks for metal artifact reduction in CT images of the ear. In International Conference on Medical Image Computing and Computer-Assisted Intervention. 3–11.Google Scholar
Digital Library
- [24] . 2007. Laplacian operator-based edge detectors. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 5 (2007), 886–890.Google Scholar
Digital Library
- [25] . 2003. Multiscale structural similarity for image quality assessment. In IEEE Asilomar Conference on Signals, Systems and Computers. 1398–1402.Google Scholar
Cross Ref
- [26] . 2018. Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT. Information Fusion 42, 1 (2018), 102–110.Google Scholar
Cross Ref
- [27] . 2020. BPGAN: Bidirectional CT-to-MRI prediction using multi-generative multi-adversarial nets with spectral normalization and localization. Neural Networks 128, 12 (2020), 82–96.Google Scholar
Cross Ref
- [28] . 2018. Deep residual learning enabled metal artifact reduction in CT. In SPIE Medical Imaging. 950–955.Google Scholar
- [29] . 2018. A reweighted joint spatial-radon domain CT image reconstruction model for metal artifact reduction. Siam Journal on Imaging Sciences 11, 1 (2018), 707–733.Google Scholar
Cross Ref
- [30] . 2011. FSIM: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing 20, 8 (2011), 2378–2386.Google Scholar
Digital Library
- [31] . 2018. Convolutional neural network based metal artifact reduction in X-ray computed tomography. IEEE Transactions on Medical Imaging 37, 10 (2018), 1370–1381.Google Scholar
Cross Ref
Index Terms
MFGAN: Multi-modal Feature-fusion for CT Metal Artifact Reduction Using GANs
Recommendations
Multi-modal feature-fusion for CT metal artifact reduction using edge-enhanced generative adversarial networks
Highlights- Multi-modal feature-fusion edge-enhance generative adversarial networks (MFE-GAN) method for CT image metal artifact reduction.
AbstractComputed 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 ...
Graphical abstractDisplay Omitted
Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018AbstractWe propose an approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) in computed tomography (CT) ear images of cochlear implants (CIs) recipients. Our training set contains paired pre-...
ADSegNet: Anatomy-Aware Artifact Disentanglement and Segmentation Network for Unpaired Segmentation, Artifact Reduction, and Modality Translation
Information Processing in Medical ImagingAbstractSpinal surgery planning necessitates automatic segmentation of vertebrae in cone-beam computed tomography (CBCT), an intraoperative imaging modality that is widely used in intervention. However, CBCT images are of low-quality and artifact-laden ...






Comments