Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing
This work addresses medical imaging challenges like data efficiency and power consumption, but it is incremental as it builds on existing lines of research.
The paper tackles medical image analysis by introducing a capsule network for robust representation learning, domain adaptation for state-of-the-art accuracy, and a neuromorphic spiking neural network for low-power inference, with results including outperforming baselines and achieving new SOTA on a brain cancer MRI classification benchmark.
We explore three representative lines of research and demonstrate the utility of our methods on a classification benchmark of brain cancer MRI data. First, we present a capsule network that explicitly learns a representation robust to rotation and affine transformation. This model requires less training data and outperforms both the original convolutional baseline and a previous capsule network implementation. Second, we leverage the latest domain adaptation techniques to achieve a new state-of-the-art accuracy. Our experiments show that non-medical images can be used to improve model performance. Finally, we design a spiking neural network trained on the Intel Loihi neuromorphic chip (Fig. 1 shows an inference snapshot). This model consumes much lower power while achieving reasonable accuracy given model reduction. We posit that more research in this direction combining hardware and learning advancements will power future medical imaging (on-device AI, few-shot prediction, adaptive scanning).