Parameter-Efficient Continuous-Variable Photonic Quantum Neural Networks for Edge Quantum AI: Demonstration in Oral Cancer Detection

2026-06-26

AI Summary

This work addresses the lack of efficient oral cancer screening tools for resource-constrained edge devices by proposing a lightweight hybrid classical–continuous-variable photonic quantum neural network (CV-QNN). The approach integrates MobileNetV1 for feature extraction, principal component analysis, and a four-mode parametrized CV-QNN composed of displacement, interferometer, and Kerr gates, adopting a simplified Φ∘D∘U₁ architecture. This design reduces trainable parameters by 40–45% and mitigates barren plateaus through dimensionality reduction and encoding constraints, achieving up to 58 orders of magnitude improvement in gradient variance. With only 18 trainable parameters, the model attains state-of-the-art validation AUC on a room-temperature photonic platform—67% fewer parameters than a 55-parameter classical baseline—and achieves 100% calibrated test accuracy across all random seeds.

Abstract

Early detection of oral cancer markedly improves clinical outcomes, yet specialized diagnostic tools remain scarce in low-resource settings. Smartphone-based screening is a scalable alternative but needs lightweight models that run within edge-hardware constraints. Hybrid classical-quantum architectures are emerging candidates for parameter-efficient learning, yet most rely on qubit hardware that needs cryogenic operation, unsuitable for edge deployment. Continuous-variable (CV) photonic quantum computing, which operates at room temperature, offers a complementary route. We investigate a hybrid classical-CV quantum classifier for oral cancer detection from smartphone images. The pipeline combines a MobileNetV1 feature extractor, principal component analysis to 16 dimensions, and a parameterized CV-QNN of displacement, interferometric, and Kerr gates on a photonic backend. We propose a simplified $Φ\circ D \circ U_1$ CV-QNN architecture that cuts trainable parameters 40-45% relative to the standard CV-QNN layer of Killoran et al. (2019a), and identify dimensionality-reduction and encoding-restriction strategies that mitigate barren plateaus, raising loss-gradient variance by roughly 58 orders of magnitude. Whether the simplified layer beats the full layer is width-dependent: the full layer holds a small but significant edge at two qumodes, whereas the simplified layer is significantly better at four qumodes using 44% fewer parameters. The strongest model, a four-qumode simplified CV-QNN with only 18 parameters, attains the highest validation AUC of all models, exceeds a 55-parameter classical baseline using 67% fewer parameters, and reaches 100% calibrated test accuracy across all seeds. These results support CV photonic quantum machine learning for parameter-efficient, room-temperature medical image classification and motivate progress toward edge quantum AI.

Problem

• oral cancer detection
• edge quantum AI
• parameter-efficient learning
• continuous-variable photonic quantum computing
• lightweight models

Innovation

• continuous-variable quantum computing
• parameter-efficient quantum neural networks
• edge quantum AI
• barren plateau mitigation
• photonic quantum machine learning