Spatio-temporal context based recurrent visual attention model for lymph node detection

被引:2
作者
Peng, Haixin [1 ]
Peng, Yinjun [1 ,2 ]
机构
[1] Shandong Univ Sci & Technol, Coll Comp Sci & Engn, Qingdao 266590, Peoples R China
[2] Shandong Univ Sci & Technol, Shandong Prov Key Lab Wisdom Min Informat Technol, Qingdao, Peoples R China
基金
中国国家自然科学基金;
关键词
biomedical image classification; false-positive reduction; mixture density networks; recurrent visual attention; CONVOLUTIONAL NEURAL-NETWORKS; AUTOMATIC DETECTION; SEGMENTATION; CNN;
D O I
10.1002/ima.22430
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
False-positive reduction is one of the most crucial components in an automated lymph nodes (LNs) detection task in volumetric computed tomography (CT) scans, which is a highly sought goal for cancer diagnosis and early treatment. In this article, treating the three-dimensional (3D) LN detection task as object detection on sequence problem, we propose a novel spatio-temporal context-based recurrent visual attention model (STRAM) for the LNs false positive reduction. We firstly extract the deep spatial features maps for two-dimensional LN patches from pre-trained Inception-V3 model. A new Gaussian kernel-based spatial attention method is then presented to extract the most discriminating spatial features for the corresponding center slices. Additionally, to combine the temporal information between 3D CT slices, we devise a novel "Siamese" mixture density networks which can learn to adaptively focus on the most relevant parts of the CT slices. Considering the lesion areas always locate around the centroid of the 3D CT scans, a hard constraint is imposed on the predicted attention locations with batch normalization technique and the Siamese architecture. The proposed model is a fully differentiable unit that can be optimized end-to-end by using stochastic gradient descent. The effectiveness of our method is verified on LN dataset: 388 mediastinal LNs labeled by radiologists in 90 patient CT scans, and 595 abdominal LNs in 86 patient CT scans. Our method demonstrates sensitivities of about 87%/82% at 3 FP/vol. and 93%/89% at 6 FP/vol. for mediastinum and abdomen, respectively, which compares favorably to previous methods.
引用
收藏
页码:1220 / 1242
页数:23
相关论文
共 55 条
  • [1] Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition
    Ablavatski, Artsiom
    Lu, Shijian
    Cai, Jianfei
    [J]. 2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, : 971 - 978
  • [2] [Anonymous], 2017, ARXIV170106452
  • [3] Ba J., 2014, Multiple object recognition with visual attention
  • [4] Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, DOI 10.48550/ARXIV.1409.0473]
  • [5] Automatic Detection and Segmentation of Lymph Nodes From CT Data
    Barbu, Adrian
    Suehling, Michael
    Xu, Xun
    Liu, David
    Zhou, S. Kevin
    Comaniciu, Dorin
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2012, 31 (02) : 240 - 250
  • [6] Bazzani L., 2016, P INT C LEARN REPR
  • [7] Bishop Christopher M, 1994, MIXTURE DENSITY NETW
  • [8] Deep Convolutional Encoder Networks for Multiple Sclerosis Lesion Segmentation
    Brosch, Tom
    Yoo, Youngjin
    Tang, Lisa Y. W.
    Li, David K. B.
    Traboulsee, Anthony
    Tam, Roger
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 : 3 - 11
  • [9] The devil is in the details: an evaluation of recent feature encoding methods
    Chatfield, Ken
    Lempitsky, Victor
    Vedaldi, Andrea
    Zisserman, Andrew
    [J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,
  • [10] Chen H, 2015, I S BIOMED IMAGING, P764, DOI 10.1109/ISBI.2015.7163984