Full left ventricle quantification via deep multitask relationships learning

• Published in: Medical image analysis Vol. 43; pp. 54 - 65
• Main Authors: Xue, Wufeng, Brahm, Gary, Pandey, Sachin, Leung, Stephanie, Li, Shuo
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01-01-2018; Elsevier BV
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Algorithms; Bayes Theorem; Bayesian analysis; Bayesian framework; Cardiovascular disease; Classifiers; Convolution; Coronary artery disease; Covariance matrix; Diastole; Heart diseases; Heart Ventricles - anatomy & histology; Humans; Learning; Left ventricle quantification; Machine learning; Mathematical models; Medical diagnosis; Middle Aged; Models, Theoretical; Multitask learning; Multitask relationship; Myocardium; Neural networks; Neural Networks (Computer); Recurrent neural networks; Regional analysis; Representations; Studies; Systole; Ventricle; Ventricular Function - physiology; Multitask learning; 99-00; Multitask relationship; 00-01; Left ventricle quantification; Bayesian framework
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2017.09.005

•An effective end-to-end integrated framework for full quantification of cardiac LV.•A brand-new multitask relationship learning method for deep neural networks.•Proof of the convexity and proposing of an efficient algorithm for the framework.
[Display omitted]
Cardiac left ventricle (LV) quantification is among the most clinically important tasks for identification and diagnosis of cardiac disease. However, it is still a task of great challenge due to the high variability of cardiac structure across subjects and the complexity of temporal dynamics of cardiac sequences. Full quantification, i.e., to simultaneously quantify all LV indices including two areas (cavity and myocardium), six regional wall thicknesses (RWT), three LV dimensions, and one phase (Diastole or Systole), is even more challenging since the ambiguous correlations existing among these indices may impinge upon the convergence and generalization of the learning procedure. In this paper, we propose a deep multitask relationship learning network (DMTRL) for full LV quantification. The proposed DMTRL first obtains expressive and robust cardiac representations with a deep convolution neural network (CNN); then models the temporal dynamics of cardiac sequences effectively with two parallel recurrent neural network (RNN) modules. After that, it estimates the three types of LV indices under a Bayesian framework that is capable of learning multitask relationships automatically, and estimates the cardiac phase with a softmax classifier. The CNN representation, RNN temporal modeling, Bayesian multitask relationship learning, and softmax classifier establish an effective and integrated network which can be learned in an end-to-end manner. The obtained task covariance matrix captures the correlations existing among these indices, therefore leads to accurate estimation of LV indices and cardiac phase.
Experiments on MR sequences of 145 subjects show that DMTRL achieves high accurate prediction, with average mean absolute error of 180 mm2, 1.39 mm, 2.51 mm for areas, RWT, dimensions and error rate of 8.2% for the phase classification. This endows our method a great potential in comprehensive clinical assessment of global, regional and dynamic cardiac function.