Direct Detection of Pixel-Level Myocardial Infarction Areas via a Deep-Learning Algorithm
- 9.1k Downloads
Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management. In this study, we propose an end-to-end deep-learning algorithm framework (OF-RNN) to accurately detect the MI area at the pixel level. Our OF-RNN consists of three different function layers: the heart localization layers, which can accurately and automatically crop the region-of-interest (ROI) sequences, including the left ventricle, using the whole cardiac magnetic resonance image sequences; the motion statistical layers, which are used to build a time-series architecture to capture two types of motion features (at the pixel-level) by integrating the local motion features generated by long short-term memory-recurrent neural networks and the global motion features generated by deep optical flows from the whole ROI sequence, which can effectively characterize myocardial physiologic function; and the fully connected discriminate layers, which use stacked auto-encoders to further learn these features, and they use a softmax classifier to build the correspondences from the motion features to the tissue identities (infarction or not) for each pixel. Through the seamless connection of each layer, our OF-RNN can obtain the area, position, and shape of the MI for each patient. Our proposed framework yielded an overall classification accuracy of 94.35% at the pixel level, from 114 clinical subjects. These results indicate the potential of our proposed method in aiding standardized MI assessments.
This work was supported in part by the Shenzhen Research and Innovation Funding (JCYJ20151030151431727, SGLH20150213143207911), the National Key Research and Development Program of China (2016YFC1300302, 2016YFC1301700), the CAS Presidents International Fellowship for Visiting Scientists (2017VTA0011), the National Natural Science Foundation of China (No. 61673020), the Provincial Natural Science Research Program of Higher Education Institutions of Anhui province (KJ2016A016) and the Anhui Provincial Natural Science Foundation (1708085QF143).
- 5.Afshin, M., Ben Ayed, I., Punithakumar, K., Law, M.W.K., Islam, A., Goela, A., Ross, I., Peters, T., Li, S.: Assessment of regional myocardial function via statistical features in MR images. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6893, pp. 107–114. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23626-6_14 CrossRefGoogle Scholar
- 6.Zhen, X., Islam, A., Bhaduri, M., Chan, I., Li, S.: Direct and simultaneous four-chamber volume estimation by multi-output regression. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 669–676. Springer, Cham (2015). doi: 10.1007/978-3-319-24553-9_82 CrossRefGoogle Scholar
- 7.Wong, K.C.L., Tee, M., Chen, M., Bluemke, D.A., Summers, R.M., Yao, J.: Computer-aided infarction identification from cardiac CT images: a biomechanical approach with SVM. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 144–151. Springer, Cham (2015). doi: 10.1007/978-3-319-24571-3_18 CrossRefGoogle Scholar
- 9.Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar