Learning hidden elasticity with deep neural networks

Significance Elastography has been applied to medical imaging to detect cancerous tissues for decades. The conventional elastography based on the assumption of stress uniformity is prone to inaccuracies. Accurately reconstructing elasticity distributions of heterogeneous objects requires solving an inverse problem in elasticity, which is difficult due to its ill-posed nature. By implementing machine learning techniques, we have developed ElastNet, an elastography method for extracting the hidden elasticity of objects based on measured strain distributions. We show that by combining the theory of elasticity with a deep-learning approach, ElastNet can provide rapid and accurate predictions. We validate ElastNet by applying it to various elastography problems with complex elasticity distributions. Elastography is an imaging technique to reconstruct elasticity distributions of heterogeneous objects. Since cancerous tissues are stiffer than healthy ones, for decades, elastography has been applied to medical imaging for noninvasive cancer diagnosis. Although the conventional strain-based elastography has been deployed on ultrasound diagnostic-imaging devices, the results are prone to inaccuracies. Model-based elastography, which reconstructs elasticity distributions by solving an inverse problem in elasticity, may provide more accurate results but is often unreliable in practice due to the ill-posed nature of the inverse problem. We introduce ElastNet, a de novo elastography method combining the theory of elasticity with a deep-learning approach. With prior knowledge from the laws of physics, ElastNet can escape the performance ceiling imposed by labeled data. ElastNet uses backpropagation to learn the hidden elasticity of objects, resulting in rapid and accurate predictions. We show that ElastNet is robust when dealing with noisy or missing measurements. Moreover, it can learn probable elasticity distributions for areas even without measurements and generate elasticity images of arbitrary resolution. When both strain and elasticity distributions are given, the hidden physics in elasticity—the conditions for equilibrium—can be learned by ElastNet.