Advertisement

MuTGAN: Simultaneous Segmentation and Quantification of Myocardial Infarction Without Contrast Agents via Joint Adversarial Learning

  • Chenchu Xu
  • Lei Xu
  • Gary Brahm
  • Heye Zhang
  • Shuo Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

Simultaneous segmentation and full quantification (estimation of all diagnostic indices) of the myocardial infarction (MI) area are crucial for early diagnosis and surgical planning. Current clinical methods still suffer from high-risk, non-reproducibility and time-consumption issues. In this study, the multitask generative adversarial networks (MuTGAN) is proposed as a contrast-free, stable and automatic clinical tool to segment and quantify MIs simultaneously. MuTGAN consists of generator and discriminator modules and is implemented by three seamless connected networks: spatio-temporal feature extraction network comprehensively learns the morphology and kinematic abnormalities of the left ventricle through a novel three-dimensional successive convolution; joint feature learning network learns the complementarity between segmentation and quantification through innovative inter- and intra-skip connection; task relatedness network learns the intrinsic pattern between tasks to increase the accuracy of estimations through creatively utilized adversarial learning. MuTGAN minimizes a generalized divergence to directly optimize the distribution of estimations by using the competition process, which achieves pixel segmentation and full quantification of MIs. Our proposed method yielded a pixel classification accuracy of 96.46%, and the mean absolute error of the MI centroid was 0.977 mm, from 140 clinical subjects. These results indicate the potential of our proposed method in aiding standardized MI assessments.

Supplementary material

473975_1_En_59_MOESM1_ESM.pdf (46 kb)
Supplementary material 1 (pdf 46 KB)

References

  1. 1.
    Bijnens, B., Claus, P., Weidemann, F.: Investigating cardiac function using motion and deformation analysis in the setting of coronary artery disease. Circulation 116(21), 2453–2464 (2007)CrossRefGoogle Scholar
  2. 2.
    Ordovas, K.G., Higgins, C.B.: Delayed contrast enhancement on MR images of myocardium: past, present, future. Radiology 261(2), 358–374 (2011)CrossRefGoogle Scholar
  3. 3.
    Fox, C.S., Muntner, P.: Use of evidence-based therapies in short-term outcomes of ST-Segment elevation myocardial infarction and Non-ST-Segment elevation myocardial infarction in patients with chronic kidney disease. Circulation 121(3), 357–365 (2010)CrossRefGoogle Scholar
  4. 4.
    Lipton, M.J., Bogaert, J., Boxt, L.M., Reba, R.C.: Imaging of ischemic heart disease. Eur. Radiol. 12(5), 1061 (2001)CrossRefGoogle Scholar
  5. 5.
    Wollmann, T., Ivanova, J., Gunkel, M.: Multi-channel deep transfer learning for nuclei segmentation in glioblastoma cell tissue images. Bildverarbeitung für die Medizin 2018, 316–321 (2018)Google Scholar
  6. 6.
    Xu, C., et al.: Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 240–249. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_28CrossRefGoogle Scholar
  7. 7.
    Popescu, I.A., Irving, B., Borlotti, A., Dall’Armellina, E., Grau, V.: Myocardial scar quantification using SLIC supervoxels - parcellation based on tissue characteristic strains. In: Mansi, T., McLeod, K., Pop, M., Rhode, K., Sermesant, M., Young, A. (eds.) STACOM 2016. LNCS, vol. 10124, pp. 182–190. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-52718-5_20CrossRefGoogle Scholar
  8. 8.
    Xue, W., Lum, A., Mercado, A., Landis, M., Warrington, J., Li, S.: Full quantification of left ventricle via deep multitask learning network respecting intra- and inter-task relatedness. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 276–284. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_32CrossRefGoogle Scholar
  9. 9.
    Ogawa, R., Kido, T.: Diagnostic capability of feature-tracking cardiovascular magnetic resonance to detect infarcted segments: a comparison with tagged magnetic resonance and wall thickening analysis. Eur. Radiol. 72(10), 828–834 (2017)Google Scholar
  10. 10.
    Xingjian, S.H.I., Chen, Z.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NIPS, pp. 802–810 (2015)Google Scholar
  11. 11.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)Google Scholar
  12. 12.
    Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)CrossRefGoogle Scholar
  13. 13.
    Bleton, H., Margeta, J., Lombaert, H., Delingette, H., Ayache, N.: Myocardial infarct localization using neighbourhood approximation forests. In: Camara, O., Mansi, T., Pop, M., Rhode, K., Sermesant, M., Young, A. (eds.) STACOM 2015. LNCS, vol. 9534, pp. 108–116. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-28712-6_12CrossRefGoogle Scholar
  14. 14.
    Karim, R., Housden, R.J., Balasubramaniam, M.: Evaluation of current algorithms for segmentation of scar tissue from late gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge. JCMR 15(1), 105 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Western universityLondonCanada
  2. 2.Beijing AnZhen HospitalBeijingChina
  3. 3.Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina

Personalised recommendations