Hybrid Classical-Quantum Neural Network Using Room-Temperature Photonic Computing Achieves High Accuracy in Oral Cancer Detection from Smartphone Images

Summary

This research paper presents a hybrid classical-quantum classifier for oral cancer detection using smartphone images, leveraging continuous-variable (CV) photonic quantum computing that operates at room temperature (unlike qubit-based systems requiring cryogenics). The pipeline combines MobileNetV1 feature extraction, PCA dimensionality reduction to 16 dimensions, and a parameterized CV-QNN with displacement, interferometric, and Kerr gates. The authors propose a simplified Φ∘D∘U₁ CV-QNN architecture that reduces trainable parameters by 40-45% compared to standard approaches, and identify strategies that mitigate barren plateaus by raising loss-gradient variance by ~58 orders of magnitude. The best model (four-qumode simplified CV-QNN with only 18 parameters) achieves the highest validation AUC, exceeds a 55-parameter classical baseline using 67% fewer parameters, and reaches 100% calibrated test accuracy. The work supports CV photonic quantum ML for parameter-efficient, room-temperature medical image classification for edge quantum AI.

Source

bskyHybrid Classical-Quantum Neural Network Using Room-Temperature Photonic Computing Achieves High Accuracy in Oral Cancer Detection from Smartphone Imagesarxiv.org