Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification
This addresses the challenge of patient-independent feature learning for coronary plaque classification in medical imaging, but it is incremental as it builds on existing adversarial methods.
The paper tackled the problem of poor generalization in deep learning for medical plaque classification due to small, heterogeneous datasets with patient- and acquisition-specific variations, and showed that an adversarial training strategy improved performance on a small medical dataset.
Deep learning methods have shown impressive results for a variety of medical problems over the last few years. However, datasets tend to be small due to time-consuming annotation. As datasets with different patients are often very heterogeneous generalization to new patients can be difficult. This is complicated further if large differences in image acquisition can occur, which is common during intravascular optical coherence tomography for coronary plaque imaging. We address this problem with an adversarial training strategy where we force a part of a deep neural network to learn features that are independent of patient- or acquisitionspecific characteristics. We compare our regularization method to typical data augmentation strategies and show that our approach improves performance for a small medical dataset.