Quantum Image Classification for Sustainable Medical Image Diagnosis
Abstract
Quantum Machine Learning (QML), which offers several computing paradigms and pattern recognition capabilities, is becoming a viable method for medical diagnostics. This study investigates the use of a particular hybrid QML algorithm to identify photos linked to medicine by utilizing the concepts of quantum computing. The study intends to assess diagnostic performance in comparison to a purely classical baseline by combining a classical neural network with a quantum-enhanced feature extraction technique (quanvolution). To categorize photos of autistic versus non-autistic persons, we use a hybrid model that combines a basic Keras backend with a simulated 4-qubit quantum circuit. We evaluate its loss and validation accuracy against a classical model that is identical and was trained on unprocessed image data. The results of this particular case study show that the hybrid model performs better in the selected setup, indicating the possibility of using QML feature extraction for this task. However, they also point out drawbacks and areas that require further research.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.