Multi-Indices Quantification for Left Ventricle via DenseNet and GRU-Based Encoder-Decoder with Attention

More and more research on left ventricle quantification skips segmentation due to its requirement of large amounts of pixel-by-pixel labels. In this study, a framework is developed to directly quantify left ventricle multiple indices without the process of segmentation. At first, DenseNet is utilized to extract spatial features for each cardiac frame. Then, in order to take advantage of the time sequence information, the temporal feature for consecutive frames is encoded using gated recurrent unit (GRU). After that, the attention mechanism is integrated into the decoder to effectively establish the mappings between the input sequence and corresponding output sequence. Simultaneously, a regression layer with the same decoder output is used to predict multi-indices of the left ventricle. Different weights are set for different types of indices based on experience, and l2-norm is used to avoid model overfitting. Compared with the state-of-the-art (SOTA), our method can not only produce more competitive results but also be more flexible. This is because the prediction results in our study can be obtained for each frame online while the SOTA only can output results after all frames are analyzed.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Terry M. Peters,et al.  Global Assessment of Cardiac Function Using Image Statistics in MRI , 2012, MICCAI.

[3]  Xiantong Zhen,et al.  Direct Estimation of Cardiac Bi-ventricular Volumes with Regression Forests , 2014, MICCAI.

[4]  Jonas Degrave.  Using Deep Learning to Estimate Systolic and Diastolic volumes from MRI-images , 2016 .

[5]  Joseph F. Murray,et al.  Supervised Learning of Image Restoration with Convolutional Networks , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[7]  A. Gupta,et al.  Cardiac MR image segmentation using deformable models , 1993, Proceedings of Computers in Cardiology Conference.

[8]  Ilkay Altintas,et al.  Left Ventricle Segmentation and Volume Estimation on Cardiac MRI using Deep Learning , 2018, ArXiv.

[9]  Bertil Schmidt,et al.  $ν$-net: Deep Learning for Generalized Biventricular Cardiac Mass and Function Parameters , 2017, ArXiv.

[10]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[11]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[12]  Xiantong Zhen,et al.  Direct and Simultaneous Four-Chamber Volume Estimation by Multi-Output Regression , 2015, MICCAI.

[13]  H. Sebastian Seung,et al.  Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction , 2015, NIPS.