Metal artifact reduction on cervical CT images by deep residual learning

被引:78
作者
Huang, Xia [1 ,2 ]
Wang, Jian [1 ,2 ]
Tang, Fan [1 ,2 ]
Zhong, Tao [1 ,2 ]
Zhang, Yu [1 ,2 ]
机构
[1] Southern Med Univ, Sch Biomed Engn, Guangzhou 510515, Guangdong, Peoples R China
[2] Southern Med Univ, Guangdong Prov Key Lab Med Image Proc, Guangzhou 510515, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Metal artifact reduction; Residual learning; Convolutional neural network; Cervical CT; COMPUTED-TOMOGRAPHY; NETWORK;
D O I
10.1186/s12938-018-0609-y
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Background: Cervical cancer is the fifth most common cancer among women, which is the third leading cause of cancer death in women worldwide. Brachytherapy is the most effective treatment for cervical cancer. For brachytherapy, computed tomography (CT) imaging is necessary since it conveys tissue density information which can be used for dose planning. However, the metal artifacts caused by brachytherapy applicators remain a challenge for the automatic processing of image data for image-guided procedures or accurate dose calculations. Therefore, developing an effective metal artifact reduction (MAR) algorithm in cervical CT images is of high demand. Methods: A novel residual learning method based on convolutional neural network (RL-ARCNN) is proposed to reduce metal artifacts in cervical CT images. For MAR, a dataset is generated by simulating various metal artifacts in the first step, which will be applied to train the CNN. This dataset includes artifact-insert, artifact-free, and artifact-residual images. Numerous image patches are extracted from the dataset for training on deep residual learning artifact reduction based on CNN (RL-ARCNN). Afterwards, the trained model can be used for MAR on cervical CT images. Results: The proposed method provides a good MAR result with a PSNR of 38.09 on the test set of simulated artifact images. The PSNR of residual learning (38.09) is higher than that of ordinary learning (37.79) which shows that CNN-based residual images achieve favorable artifact reduction. Moreover, for a 512 x 512 image, the average removal artifact time is less than 1s. ConclusionsThe RL-ARCNN indicates that residual learning of CNN remarkably reduces metal artifacts and improves critical structure visualization and confidence of radiation oncologists in target delineation. Metal artifacts are eliminated efficiently free of sinogram data and complicated post-processing procedure.
引用
收藏
页数:15
相关论文
共 46 条
  • [1] Metal Artifact Reduction in Computed Tomography After Deep Brain Stimulation Electrode Placement Using Iterative Reconstructions
    Aissa, Joel
    Boos, Johannes
    Schleich, Christoph
    Sedlmair, Martin
    Krzymyk, Karl
    Kroepil, Patric
    Antoch, Gerald
    Thomas, Christoph
    [J]. INVESTIGATIVE RADIOLOGY, 2017, 52 (01) : 18 - 22
  • [2] [Anonymous], P SPIE
  • [3] [Anonymous], 2015, ARXIV PREPRINT ARXIV
  • [4] [Anonymous], 2012, INT C ART INT STAT
  • [5] [Anonymous], EUR C COMP METH APPL
  • [6] [Anonymous], 2017, ARXIV170800607
  • [7] [Anonymous], 2013, 2013 IEEE NUCL SCI S, DOI DOI 10.1109/NSSMIC.2013.6829361
  • [8] [Anonymous], SOC PHOTO OPTICAL IN
  • [9] [Anonymous], 2014, ARXIV14124564
  • [10] [Anonymous], 14 INT M FULL 3 DIM