Page 8 - Artificial Intelligence for Computational Modeling of the Heart

Contents vii

3.1 Introduction. . ................................................ 97
3.2 Parsing of cardiac and vascular structures. ..................... 98

3.2.1 From shallow to deep marginal space learning ............ 98
3.2.2 Intelligent agent-driven image parsing . . ................. 105
3.2.3 Deep image-to-image segmentation ..................... 112
3.3 Structure tracking ........................................... 113
3.4 Summary ................................................... 115
Chapter 4 Data-driven reduction of cardiac models . . . . . . ........... 117
Lucian Mihai Itu, Felix Meister, Puneet Sharma, Tiziano Passerini

4.1 Deep-learning model for real-time, non-invasive fractional flow
reserve . .................................................... 118
4.1.1 Introduction ........................................... 118

4.1.2 Methods............................................... 120
4.1.3 Results ................................................ 128
4.1.4 Discussion............................................. 130
4.2 Meta-modeling of atrial electrophysiology..................... 136
4.2.1 Methods............................................... 139
4.2.2 Experiments and results ................................ 144
4.2.3 Discussion............................................. 153

4.3 Deep learning acceleration of biomechanics ................... 154
4.3.1 Motivation. ............................................ 154
4.3.2 Methods............................................... 154
4.3.3 Evaluation ............................................. 156
4.4 Summary ................................................... 160
Chapter 5 Machine learning methods for robust parameter estimation. 161
Dominik Neumann, Tommaso Mansi

5.1 Introduction. . ............................................... 161
5.2 A regression approach to model parameter estimation ......... 163
5.2.1 Data-driven estimation of myocardial electrical diffusivity . 163
5.2.2 Experiments and results ................................ 165
5.3 Reinforcement learning method for model parameter estimation168
5.3.1 Parameter estimation as a Markov decision process ...... 170