Quantum-classical convolutional neural networks in radiological image classification
This work addresses the challenge of limited training data in medical imaging by exploring quantum-classical hybrids, but it is incremental as it shows similar performance to existing methods without clear superiority.
The authors tackled the problem of applying quantum machine learning to medical image classification by proposing hybrid quantum-classical convolutional neural networks (QCCNNs) with various quantum circuit designs and encoding techniques, achieving performance similar to classical counterparts on 2D and 3D radiological data.
Quantum machine learning is receiving significant attention currently, but its usefulness in comparison to classical machine learning techniques for practical applications remains unclear. However, there are indications that certain quantum machine learning algorithms might result in improved training capabilities with respect to their classical counterparts -- which might be particularly beneficial in situations with little training data available. Such situations naturally arise in medical classification tasks. Within this paper, different hybrid quantum-classical convolutional neural networks (QCCNN) with varying quantum circuit designs and encoding techniques are proposed. They are applied to two- and three-dimensional medical imaging data, e.g. featuring different, potentially malign, lesions in computed tomography scans. The performance of these QCCNNs is already similar to the one of their classical counterparts -- therefore encouraging further studies towards the direction of applying these algorithms within medical imaging tasks.