Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation
This work addresses the problem of efficient and accurate hippocampus segmentation for medical imaging applications, representing an incremental improvement in SNN training methods.
The paper tackles the challenge of training spiking neural networks (SNNs) for low-power applications by proposing a hybrid SNN training scheme that uses ANN-SNN conversion as initialization and spike-based backpropagation for fine-tuning, applied to hippocampus segmentation from MRI images, resulting in improved segmentation accuracy and training efficiency compared to existing methods.
Over the past decade, artificial neural networks (ANNs) have made tremendous advances, in part due to the increased availability of annotated data. However, ANNs typically require significant power and memory consumptions to reach their full potential. Spiking neural networks (SNNs) have recently emerged as a low-power alternative to ANNs due to their sparsity nature. SNN, however, are not as easy to train as ANNs. In this work, we propose a hybrid SNN training scheme and apply it to segment human hippocampi from magnetic resonance images. Our approach takes ANN-SNN conversion as an initialization step and relies on spike-based backpropagation to fine-tune the network. Compared with the conversion and direct training solutions, our method has advantages in both segmentation accuracy and training efficiency. Experiments demonstrate the effectiveness of our model in achieving the design goals.