Incremental learning of fetal heart anatomies using interpretable saliency maps
While medical image analysis has seen extensive use of deep neural networks, learning over multiple tasks is a challenge for connectionist networks due to tendencies of degradation in performance over old tasks while adapting to novel tasks. It is pertinent that adaptations to new data distributions...
| मुख्य लेखकों: | , |
|---|---|
| स्वरूप: | Conference item |
| भाषा: | English |
| प्रकाशित: |
Springer
2020
|
| सारांश: | While medical image analysis has seen extensive use of deep neural networks, learning over multiple tasks is a challenge for connectionist networks due to tendencies of degradation in performance over old tasks while adapting to novel tasks. It is pertinent that adaptations to new data distributions over time are tractable with automated analysis methods as medical imaging data acquisition is typically not a static problem. So, one needs to ensure that a continual learning paradigm be ensured in machine learning methods deployed for medical imaging. To explore interpretable lifelong learning for deep neural networks in medical imaging, we introduce a perspective of understanding forgetting in neural networks used in ultrasound image analysis through the notions of attention and saliency. Concretely, we propose quantification of forgetting as a decline in the quality of class specific saliency maps after each subsequent task schedule. We also introduce a knowledge transfer from past tasks to present by a saliency guided retention of past exemplars which improve the ability to retain past knowledge while optimizing parameters for current tasks. Experiments on a clinical fetal echocardiography dataset demonstrate a state-of-the-art performance for our protocols. |
|---|