Purpose: The impact of hybrid quantum-classical neural network (NN) architectures with multiple backbones and quantum transformation as a data augmentation (DA) technique on image classification tasks was investigated using the CIFAR-10 and MedMNIST (DermaMNIST) datasets. These datasets were chosen for their relevance in general-purpose and medical-specific small-scale image classification, respectively. Methods: A series of quanvolutional transformations, utilizing random quantum circuits based on single-qubit rotation quantum gates (Y-axis, X-axis, and combined XY-axis transformations), were applied to create multiple quantum channels (QC) for input augmentation. By integrating these QCs with baseline convolutional NN architectures (LCNet050) and scalable hybrid NN architectures with multiple (n) backbones and separate QC (n) inputs (HNN-QCn), the scalability and performance enhancements offered by quantum-inspired data augmentation were evaluated. The proposed cross-validation workflow ensured reproducibility and systematic performance evaluation of hybrid models by mean and standard deviation values of metrics (such as accuracy and area under the curve (AUC) for the receiver operating characteristic). Results: The results demonstrated consistent performance improvements by AUC and accuracy in HNN-QCn models with the number n (where n∈{4,5,9,10,17,18}) of backbones and QC inputs across both datasets. The different improvement rates were observed for the smaller increase in AUC and the larger increase in accuracy as input complexity (number of backbones and QCs inputs) increases. It is assumed that the prediction probability distribution is becoming sharpened with the addition of backbones and QC inputs, leading to larger improvements in accuracy. At the same time, AUC reflects these changes more slowly unless the model’s ranking ability improves substantially. Conclusion: The findings highlight the scalability, robustness, and adaptability of HNN-QCn architectures, with superior performance by AUC (micro and macro) and accuracy across diverse datasets and potential for applications in high-stakes domains like medical imaging. These results underscore the utility of quantum transformations as a form of DA, paving the way for further exploration into the scalability and efficiency of hybrid architectures in complex datasets and real-world scenarios.
Purpose: The impact of hybrid quantum-classical neural network (NN) architectures with multiple backbones and quantum transformation as a data augmentation (DA) technique on image classification tasks was investigated using the CIFAR-10 and MedMNIST (DermaMNIST) datasets. These datasets were chosen for their relevance in general-purpose and medical-specific small-scale image classification, respectively. Methods: A series of quanvolutional transformations, utilizing random quantum circuits based on single-qubit rotation quantum gates (Y-axis, X-axis, and combined XY-axis transformations), were applied to create multiple quantum channels (QC) for input augmentation. By integrating these QCs with baseline convolutional NN architectures (LCNet050) and scalable hybrid NN architectures with multiple (n) backbones and separate QC (n) inputs (HNN-QCn), the scalability and performance enhancements offered by quantum-inspired data augmentation were evaluated. The proposed cross-validation workflow ensured reproducibility and systematic performance evaluation of hybrid models by mean and standard deviation values of metrics (such as accuracy and area under the curve (AUC) for the receiver operating characteristic). Results: The results demonstrated consistent performance improvements by AUC and accuracy in HNN-QCn models with the number n (where n∈{4,5,9,10,17,18}) of backbones and QC inputs across both datasets. The different improvement rates were observed for the smaller increase in AUC and the larger increase in accuracy as input complexity (number of backbones and QCs inputs) increases. It is assumed that the prediction probability distribution is becoming sharpened with the addition of backbones and QC inputs, leading to larger improvements in accuracy. At the same time, AUC reflects these changes more slowly unless the model’s ranking ability improves substantially. Conclusion: The findings highlight the scalability, robustness, and adaptability of HNN-QCn architectures, with superior performance by AUC (micro and macro) and accuracy across diverse datasets and potential for applications in high-stakes domains like medical imaging. These results underscore the utility of quantum transformations as a form of DA, paving the way for further exploration into the scalability and efficiency of hybrid architectures in complex datasets and real-world scenarios.
Purpose: While hybrid quantum–classical neural networks (HNNs) are a promising avenue for quantum advantage, the critical influence of the classical backbone architecture on their performance remains poorly understood. This study investigates the role of lightweight convolutional neural network architectures, focusing on LCNet, in determining the stability, generalization, and effectiveness of hybrid models augmented with quantum layers for medical applications. The objective is to clarify the architectural compatibility between quantum and classical components and provide guidelines for backbone selection in hybrid designs. Methods: We constructed HNNs by integrating a four-qubit quantum circuit (with trainable rotations) into scaled versions of LCNet (050, 075, 100, 150, 200). These models were rigorously evaluated on CIFAR-10 and MedMNIST using stratified 5-fold cross-validation, assessing accuracy, AUC, and robustness metrics. Performance was assessed with accuracy, macro- and micro-averaged area under the ROC curve (AUC), per-class accuracy, and out-of-fold (OoF) predictions to ensure unbiased generalization. In addition, training dynamics, confusion matrices, and performance stability across folds were analyzed to capture both predictive accuracy and robustness. Results: The experiments revealed a strong dependence of hybrid network performance on both backbone architecture and model scale. Across all tests, LCNet-based hybrids achieved the most consistent benefits, particularly at compact and medium configurations. From LCNet050 to LCNet100, hybrid models maintained high macro-AUC values exceeding 0.95 and delivered higher mean accuracies with lower variance across folds, confirming enhanced stability and generalization through quantum integration. On the DermaMNIST dataset, these hybrids achieved accuracy gains of up to seven percentage points and improved AUC by more than three points, demonstrating their robustness in imbalanced medical settings. However, as backbone complexity increased (LCNet150 and LCNet200), the classical architectures regained superiority, indicating that the advantages of quantum layers diminish with scale. The mostconsistent gains were observed at smaller and medium LCNet scales, where hybridization improved accuracy and stability across folds. This divergence indicates that hybrid networks do not necessarily follow the “bigger is better” paradigm of classical deep learning. Per-class analysis further showed that hybrids improved recognition in challenging categories, narrowing the gap between easy and difficult classes. Conclusions: The study demonstrates that the performance and stability of hybrid quantum–classical neural networks are fundamentally determined by the characteristics of their classical backbones. Across extensive experiments on CIFAR-10 and DermaMNIST, LCNet-based hybrids consistently outperformed or matched their classical counterparts at smaller and medium scales, achieving higher accuracy and AUC along with notably reduced variability across folds. These improvements highlight the role of quantum layers as implicit regularizers that enhance learning stability and generalization—particularly in data-limited or imbalanced medical settings. However, the observed benefits diminished with increasing backbone complexity, as larger classical models regained superiority in both accuracy and convergence reliability. This indicates that hybrid architectures do not follow the conventional “larger-is-better” paradigm of classical deep learning. Overall, the results establish that architectural compatibility and model scale are decisive factors for effective quantum–classical integration. Lightweight backbones such as LCNet offer a robust foundation for realizing the advantages of hybridization in practical, resource-constrained medical applications, paving the way for future studies on scalable, hardware-efficient, and clinically reliable hybrid neural networks.
Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.
This study explores the impact of classical backbone architecture on the performance of hybrid quantum-classical neural networks in image classification tasks. Hybrid models combine the representational power of classical deep learning with the potential advantages of quantum computation. Specifically, this research employs a quanvolutional neural network architecture in which a quantum convolutional layer, based on a four-qubit Ry circuit, preprocesses input images before classical processing. Despite the growing interest in hybrid models, few studies have systematically investigated how variations in classical architecture design affect the overall performance of hybrid quantum-classical neural networks. To address this gap, we compare two lightweight convolutional backbones – MobileNetV3Small050 and LCNet050 – integrated with an identical quantum preprocessing layer. Both models are evaluated on the CIFAR-10 dataset using 5-fold stratified cross-validation. Performance is assessed using multiple metrics, including accuracy, macro- and micro-averaged area under the curve, and class-wise confusion matrices. The results indicate that the LCNet-based hybrid model consistently outperforms its MobileNet counterpart, achieving higher overall accuracy and area under the curve scores, along with improved class balance and robustness in distinguishing less-represented classes. These findings underscore the critical role of classical backbone selection in hybrid quantum-classical architectures. While the quantum layer remains fixed, the synergy between quantum preprocessing and classical feature extraction significantly affects model performance. This study contributes to a growing body of work on quantum-enhanced learning systems by demonstrating the importance of classical design choices. Future research may extend these insights to alternative datasets, deeper or transformer-based backbones, and more expressive quantum circuits.
Accurate classification of microscopic blood cells is still a critical task in medical image analysis, where subtle variations and limited data can challenge conventional deep learning models. As such, we investigate in this work the potential of Hybrid Quantum-Classical Neural Networks (HQNNs) to enhance feature representation and improve classification performance in this domain. We propose a modular architecture combining a pre-trained ResNet-50 backbone with a low-dimensional latent bottleneck and a variational quantum circuit, enabling a direct comparison between quantum-enhanced and purely classical transformation mechanisms. To isolate the contribution of the quantum component, we evaluate three architectures: a HQNN model, a Classical Matched Model with an additional nonlinear transformation layer of comparable capacity, and a baseline model without an intermediate transformation stage. Experiments conducted on two publicly available blood cell datasets, namely the Blood Cell Images dataset and the PBC dataset, demonstrate that HQNNs consistently achieve superior or more balanced performance across evaluation metrics. In the Blood Cell Images Dataset, the proposed approach improves macro F1-score by up to 3.7% compared to classical baselines, while improving the F1-score from 98.54% to 98.69% in the more challenging 8-class scenario with near-saturated performance. Additional evaluation on IBM quantum hardware shows that the model remains robust under noise, with only a modest performance degradation relative to simulated results. These results indicate that quantum feature transformations can enhance discriminative representations, particularly in challenging classification scenarios, and highlight the practical potential of HQNN models for medical imaging tasks.
In the last decade, quantum computing (QC) has shown its great potential in advancing research in many fields. Here we introduce a new quantum-classical neural network, by combining quantum computing and classical computing in a hybrid neural network (HNN) that can be trained to perform image classification. The HNN on the basis of the classic convolutional neural network (CNN) with quantum circuit is considered for image classification problem. The various configurations of HNN were investigated where QC with different number of qubits were used and compared. The HNN configurations were trained, validated, and tested on the more complex CIFAR10 and CIFAR100 datasets in addition to our previous attempts on the simpler MNIST, notMNIST, MNIST Fashion datasets. Performance of HNN was compared for multiclass classification on these datasets for different number of classes (from 2 to 10) using QCs with correspondent number of qubits (from 2 to 4). The metrics measured (accuracy and loss) during these experiments support our assumption about feasibility of HNN application for multiclass classification problems.
Table1_Performance.csv This file contains the classification performance of the Classical CNN and the proposed SH-QC-CNN across three benchmark datasets: ImageNet-1K, CIFAR-100, and Medical X-ray. It reports Top-1 accuracy for both models and the percentage improvement achieved by the hybrid architecture. The data supports the claim that quantum-enhanced feature processing consistently improves recognition accuracy across diverse domains. Fig7_Parameter_Counts.csv This dataset reports the number of trainable parameters (in millions) for Classical CNNs and SH-QC-CNN on three datasets. It demonstrates the substantial reduction in model size achieved by replacing dense classical layers with Parameterized Quantum Circuits (PQCs), highlighting the parameter efficiency of the proposed hybrid architecture. Fig8_Training_Time.csv This file provides the total training time (in hours) for Classical CNNs and SH-QC-CNN across ImageNet-1K, CIFAR-100, and Medical X-ray datasets. The data shows that SH-QC-CNN reduces training time by approximately 34% on average, validating the computational efficiency of quantum-enhanced feature compression. Fig9_PQC_Depth_vs_Accuracy.csv This dataset captures the relationship between PQC depth (number of quantum layers) and classification accuracy. It illustrates that performance improves with depth up to three layers, after which accuracy degrades due to NISQ-era limitations such as noise and barren plateaus. The data justifies the selection of a three-layer PQC as the optimal configuration. Fig11_Noise_Robustness.csv This file contains clean and noisy accuracy values for both Classical CNN and SH-QC-CNN under Gaussian noise perturbation. It quantifies the accuracy drop and demonstrates that SH-QC-CNN is significantly more robust to input noise, confirming the stabilizing effect of quantum feature embeddings. Fig12_Qubit_Scaling.csv This dataset shows the relationship between classical feature dimensionality and the number of qubits required for quantum encoding. It evidences a logarithmic scaling behavior, indicating that high-dimensional feature spaces can be efficiently represented using a small number of qubits, making the architecture feasible for NISQ-era hardware.