Left Ventricular Parameter Regression from Deep Feature Maps of a Jointly Trained Segmentation CNN

Quantification of left ventricular (LV) parameters from cardiac MRI is important to assess cardiac condition and help in the diagnosis of certain pathologies. We present a CNN-based approach for automatic quantification of 11 LV indices: LV and myocardial area, 3 LV dimensions and 6 regional wall thicknesses (RWT). We use an encoder-decoder segmentation architecture and hypothesize that deep feature maps contain important shape information suitable to start an additional network branch for LV index regression. The CNN is simultaneously trained on regression and segmentation losses. We validated our approach on the LVQuan19 training dataset and found that our proposed CNN significantly outperforms a standard encoder regression CNN. The mean absolute error and Pearson correlation coefficient obtained for the different indices are respectively 190 mm\(^2\) (96\(\%\)), 214 mm\(^2\) (0.90\(\%\)), 2.99 mm (95\(\%\)) and 1.82 mm (71\(\%\)) for LV area, myocardial area, LV dimensions and RWT on a three-fold cross validation and 186 mm\(^2\) (97\(\%\)), 222 mm\(^2\) (0.88\(\%\)), 3.03 mm (0.95\(\%\)) and 1.67 mm (73\(\%\)) on a five-fold cross validation.

[1]  Chao Lu,et al.  Left Ventricle Full Quantification via Hierarchical Quantification Network , 2018, STACOM@MICCAI.

[2]  Jing Xiao,et al.  Automated Full Quantification of Left Ventricle with Deep Neural Networks , 2018, STACOM@MICCAI.

[3]  Graham A. Wright,et al.  Cardiac MRI Left Ventricle Segmentation and Quantification: A Framework Combining U-Net and Continuous Max-Flow , 2018, STACOM@MICCAI.

[4]  Hao Xu,et al.  Calculation of Anatomical and Functional Metrics Using Deep Learning in Cardiac MRI: Comparison Between Direct and Segmentation-Based Estimation , 2018, STACOM@MICCAI.

[5]  Jun Zhang,et al.  Multi-task neural networks for joint hippocampus segmentation and clinical score regression , 2018, Multimedia Tools and Applications.

[6]  Enzo Ferrante,et al.  Left ventricle quantification through spatio-temporal CNNs , 2018, STACOM@MICCAI.

[7]  Qian Tao,et al.  ESU-P-Net: Cascading Network for Full Quantification of Left Ventricle from Cine MRI , 2018, STACOM@MICCAI.

[8]  Zhiqiang Hu,et al.  Left Ventricle Full Quantification Using Deep Layer Aggregation Based Multitask Relationship Learning , 2018, STACOM@MICCAI.

[9]  Yeonggul Jang,et al.  Full Quantification of Left Ventricle Using Deep Multitask Network with Combination of 2D and 3D Convolution on 2D + t Cine MRI , 2018, STACOM@MICCAI.

[10]  Wufeng Xue,et al.  Full left ventricle quantification via deep multitask relationships learning , 2018, Medical Image Anal..

[11]  M. Cerqueira,et al.  Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. , 2002, Circulation.

[12]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[13]  Zhiming Luo,et al.  Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[14]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[16]  Eric Kerfoot,et al.  Left-Ventricle Quantification Using Residual U-Net , 2018, STACOM@MICCAI.

[17]  Xiang Li,et al.  Multi-Estimator Full Left Ventricle Quantification through Ensemble Learning , 2018, STACOM@MICCAI.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.