Abstract
We tested different loss functions and hyper-parameters using a 2D U-Net architecture (resnet34 backbone) with five-fold cross-validation on the training data. Pathology specific sequence data (e.g. LGE for scar and T2 for edema) was used as a sole input for training and in combination with all sequences. We wanted to address the question whether for limited training data it is beneficial to incorporate prior knowledge by predicting classes with their appropriate sequence or if a neural network is able to infer these relationships from a multi-sequence dataset. In addition, we aimed to create a model zoo, combining predictions from models with high performance on individual classes. Images were cropped to the central 256 × 256 region as this contained the region of interest in all cases. To improve robustness and learn more general features extensive data augmentation was used, including both MR artifacts (motion, noise) and standard image transformations (zoom, rotation, brightness, contrast). Variations of training data, loss functions and hyper-parameters led to 21 models trained. The multi-sequence model was trained using all image sequences input via color channels producing pixel-level segmentation for all six classes (background, left ventricle, right ventricle, myocardium, edema, and scar). Cross-entropy as a loss function performed best (metric: dice) for non-pathologic tissue, while pathology weighted focal-loss (0.35 for both scar and edema) had best mean performance on scar and edema.
These results indicate that the employed neural networks are capable of learning multi-sequence segmentation end-to-end. Combining different outputs from a model zoo further improved segmentation performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bai, W., et al.: Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J. Cardiovas. Magn. Resonan. 20, 65 (2018)
Baumgartner, C.F., Koch, L.M., Pollefeys, M., Konukoglu, E.: An exploration of 2D and 3D deep learning techniques for cardiac MR image segmentation. In: Pop, M., et al. (eds.) STACOM 2017. LNCS, vol. 10663, pp. 111–119. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75541-0_12
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, William M., Frangi, Alejandro F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ankenbrand, M.J., Lohr, D., Schlötelburg, W., Reiter, T., Wech, T., Schreiber, L.M.: A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians - Transfer Learning Application to 7T. medRxiv 2020.2006.2015.20131656 (2020)
Zabihollahy, F., White, J.A., Ukwatta, E.: Convolutional neural network-based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images. Med. Phys. 46, 1740–1751 (2019)
Li, L., Weng, X., Schnabel, J.A., Zhuang, X.J.A.: Joint left atrial segmentation and scar quantification based on a DNN with spatial encoding and shape attention. abs/2006.13011 (2020)
Li, L., et al.: Atrial scar quantification via multi-scale CNN in the graph-cuts framework. Med. Image Anal. 60, 101595 (2020)
Zhuang, X.: Multivariate mixture model for cardiac segmentation from multi-sequence MRI. In: Ourselin, S., Joskowicz, L., Sabuncu, Mert R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 581–588. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_67
Zhuang, X.: Multivariate mixture model for myocardial segmentation combining multi-source images. IEEE Trans. Pattern Anal. Mach. Intell. 41(12), 2933–2946 (2019)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8024–8035 (2019)
Howard, J., Gugger, S.: fastai: a layered api for deep learning. Information 11, 108 (2020)
Pérez-García, F., Sparks, R., Ourselin, S.: TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. arXiv:2003.04696 [cs, eess, stat] (2020)
Brett, M., et al.: freec84: nibabel. Zenodo (2020). https://doi.org/10.5281/zenodo.591597
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graph 39, 355–368 (1987)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. arXiv:1708.02002 [cs] (2017)
Acknowledgements
This work was supported by the German Ministry of Education and Research (grant number, 01EO1504). The funding body took no role in the design of the study, collection, analysis, and interpretation of data and in writing the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ankenbrand, M.J., Lohr, D., Schreiber, L.M. (2020). Exploring Ensemble Applications for Multi-sequence Myocardial Pathology Segmentation. In: Zhuang, X., Li, L. (eds) Myocardial Pathology Segmentation Combining Multi-Sequence Cardiac Magnetic Resonance Images. MyoPS 2020. Lecture Notes in Computer Science(), vol 12554. Springer, Cham. https://doi.org/10.1007/978-3-030-65651-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-65651-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65650-8
Online ISBN: 978-3-030-65651-5
eBook Packages: Computer ScienceComputer Science (R0)