Automated analysis of dermoscopic images can support benign-versus-malignant skin lesion classification, but the practical usefulness of hybrid quantum-classical models remains unclear under current hardware constraints. This paper presents an experimental comparison between a classical MobileNetV2-based baseline and a hybrid pipeline that combines convolutional feature extraction with a variational quantum circuit for binary classification on the publicly available HAM10000 dataset. In the hybrid approach, image features extracted by the classical backbone are projected to a low-dimensional latent space and encoded into a trainable quantum circuit. Both models are evaluated on disjoint train, validation, and test splits, with model selection for the quantum pipeline performed on the validation set. The classical baseline clearly outperformed the hybrid model. The selected hybrid configuration reached a balanced accuracy of 0.582 and an area under the receiver operating characteristic curve (AUC) of 0.610 on the held-out test set. We also validated inference on IBM Quantum backends, confirming compatibility with execution on real quantum hardware. Taken together, these results suggest that the hybrid pipeline is better viewed as a feasibility study under current noisy intermediate-scale quantum (NISQ) limitations rather than as a replacement for strong classical image classifiers.
Automated analysis of dermoscopic images can support benign-versus-malignant skin lesion classification, but the practical usefulness of hybrid quantum-classical models remains unclear under current hardware constraints. This paper presents an experimental comparison between a classical MobileNetV2-based baseline and a hybrid pipeline that combines convolutional feature extraction with a variational quantum circuit for binary classification on the publicly available HAM10000 dataset. In the hybrid approach, image features extracted by the classical backbone are projected to a low-dimensional latent space and encoded into a trainable quantum circuit. Both models are evaluated on disjoint train, validation, and test splits, with model selection for the quantum pipeline performed on the validation set. The classical baseline clearly outperformed the hybrid model. The selected hybrid configuration reached a balanced accuracy of 0.582 and an area under the receiver operating characteristic curve (AUC) of 0.610 on the held-out test set. We also validated inference on IBM Quantum backends, confirming compatibility with execution on real quantum hardware. Taken together, these results suggest that the hybrid pipeline is better viewed as a feasibility study under current noisy intermediate-scale quantum (NISQ) limitations rather than as a replacement for strong classical image classifiers.
Skin cancer is among the most widespread and life-threatening conditions in the world with the need to detect lesions promptly and consistently in order to treat the disease in a timely manner. Nonetheless, automated lesion classification of the skin is a complex challenge due to inter-class similarity, which is high, illumination variation, and imbalance in the data in various classes of lesions. To address these obstacles, this paper presents a lightweight but powerful 6-qubit Hybrid Quantum-Classical Convolutional Neural Network (HQNN) that is optimized to 6-bit (low-precision) medical imaging applications. The proposed framework will use a ResNet-18 backbone to learn deep dermatological features based on dermoscopic images and a Particle Swarm Optimization (PSO) algorithm with a Random Forest (RF) ranking of features will reduce the 512-dimensional embedding space into six highly discriminative descriptors, which can be encoded in quantum. These are then converted into quantum states with ZZFeatureMap and RealAmplitudes ansatz which comprise a 6-qubit variational circuit the output of which is fused with a classical CNN classifier to achieve final lesion prediction. This strategy of optimization of quantum-aware features is a balance between the representation of high dimensions and limitations of qubits, which ensures a computational tractability on near-term noisy intermediate-scale quantum (NISQ) devices. Existing experimental results on the ISIC 2019 skin-lesion dataset show state-of-the-art performance achieving 98.2% accuracy, 98.5% precision, 97.7% recall, 98.0% F1-score, and a macro ROC-AUC of 0.985. The findings affirm that quantized deep learning with low-qubit quantum encoding has better diagnostic performance, noise resistance, and scalability with minimal hardware costs, making Q-SkinNet a realistic advancement towards experimental quantum-assisted dermatological diagnostics.
This paper presents a systematic ablation and evaluation integrity study of hybrid quantum-classical neural networks for seven-class skin lesion classification on the HAM10000 dermoscopy dataset. We study the effect of the evaluation protocol on a hybrid quantum-classical pipeline by comparing two partitioning schemes on the same model and data. The first is a leakage-prone scheme that partitions the pool of augmented images, and the second is a verified scheme that partitions original lesion identities. Under the leakage-prone scheme, augmented variants of the same physical lesion appear on both sides of the split. An audit found that 1,095 of 4,810 lesions (22.8%) crossed the split boundary, artificially inflating all previously reported metrics. We rebuild the pipeline with a verified lesion-level partition consisting of 4,152 training, 522 validation, and 517 original test images. The training set is augmented to 10,503 images while ensuring zero image-level and lesion-level overlap. We then re-run every experiment across five random seeds with per-class Wilson confidence intervals and paired significance tests on a fixed held-out test set that is never used for tuning. Under the corrected protocol, the strongest configuration features a ResNet50 backbone with concatenation fusion, focal loss, and test-time augmentation. This setup reaches 78.41% ±0.74 test accuracy and a macro F1 of 0.804 against a verified baseline of 76.17% ±1.91 . However, under the leakage-prone protocol, this exact same pipeline yields 94.57%. A parameter-matched classical control, in which a 36-parameter multilayer perceptron replaces the variational quantum circuit (VQC), is statistically indistinguishable from the hybrid model (78.14% versus 78.41%, p = 0.81). Additionally, a controlled fusion comparison shows that concatenation is not significantly better than weighted fusion. We therefore report no detectable advantage from the quantum branch at this scale as a controlled negative result rather than a failure, and we characterize VQC trainability under noiseless and depolarizing simulation. Finally, a split-audit survey of recent quantum-hybrid HAM10000 studies indicates that reported accuracies above 90% are associated with undisclosed or leakage-prone evaluation protocols. The contribution of this work is methodological: a reproducible leakage audit, a verified correction protocol, an honest multi-seed baseline, a parameter-matched classical control, and evidence that evaluation protocols rather than architectures drive the headline differences reported in this literature.
Skin cancer is the most common and fatal illness globally, and therefore, proper early detection is essential for successful treatment and enhanced patient outcomes. Classic deep learning models, especially Convolutional Neural Networks (CNNs), have greatly succeeded in medical image classification. However, classic CNNs also suffer from severe limitations such as computational inefficiency, overfitting on small datasets, and redundant feature extraction, which restrict their utility in clinical settings. To overcome these drawbacks, we introduce QAttn-CNN as a quantum–classical deep learning model combining a Quantum Attention Mechanism (QAttn) to improve feature selection and classification accuracy. Our method utilizes Quantum Convolutional Layers (QConv) and Quantum Image Representation (QIR) with Novel Enhanced Quantum Representation (NEQR) encoding to draw upon quantum parallelism and improve computational efficiency and complexity from O(N 2 ) to O(log N). The model is tested on three benchmark datasets: MNIST (70,000 grey-scale handwritten digit images), CIFAR-10 (60,000 RGB object images), and the Kaggle Skin Cancer: Malignant versus Benign dataset (3297 dermoscopic images: 1800 benign and 1497 malignant cases, from the International Skin Imaging Collaboration (ISIC) Archive). The dataset images were processed by converting them to grayscale, resizing them bilinearly to 150 × 150 pixels, and normalizing to [0–1] for quantum encoding. QAttn-CNN is contrasted with standard CNNs, QAttn-ViT (Quantum Attention Vision Transformer), and QAttn-ResNet18. Results indicate that QAttn-CNN attains state-of-the-art accuracy of 91% on the Skin Cancer dataset with a precision of 89%, a recall of 89%, and an F1-score of 91%, surpassing Baseline CNN (89% accuracy), QAttn-ViT (87%), and QAttn-ResNet18 (83%). On CIFAR-10, QAttn-CNN exhibits 10% accuracy enhancement over Baseline CNN with accuracy of 82% and 90% precision. On MNIST, QAttn-CNN performs at the peak of 99% accuracy, comparable to classical benchmarks but with greatly diminished computational overhead due to quantum parallelism. This study demonstrates the revolutionary potential of quantum-assisted deep learning in healthcare applications, especially for real-world binary medical image classification problems that identify malignant vs. benign skin lesions.
Skin lesion classification from dermoscopic images remains difficult because diagnostically important lesions may share similar colours, textures, and structural patterns. Fine local details and broader lesion characteristics must therefore be considered together to achieve reliable multi-class classification. This study presents a noise-aware and statistically evaluated dual-branch hybrid quantum-classical framework that combines EfficientNet-B3 features, handcrafted dermatological descriptors, and parameterized quantum circuits. A 6-qubit branch processes micro-level textural information, while a 4-qubit branch represents broader structural characteristics. The resulting quantum features are combined with deep visual representations and handcrafted descriptors based on texture, colour, and lesion complexity. The framework was evaluated using stratified five-fold cross-validation and repeated experiments with different random initialization seeds. On HAM10000, it achieved a mean accuracy of 95.18% ±0.75 %, a mean balanced accuracy of 92.92% ±0.89 %, and a mean macro-F1 score of 0.904±0.009 . A separate training and evaluation experiment on ISIC-2019 produced an accuracy of 93.86% and a macro-F1 score of 0.913, indicating consistent performance across two independently evaluated dermoscopic datasets. The effect of non-ideal quantum operation was also examined by introducing depolarizing noise during evaluation. The model retained accuracies of 94.13% at p=0.01 and 93.21% at p=0.05 . These findings show that combining deep features, dermatological descriptors, and dual-scale quantum representations can improve the discrimination of visually similar lesion categories, including melanoma. The proposed framework provides a statistically reliable and noise-resilient approach for computer-aided dermoscopic image classification, although further external and clinical validation is required before practical clinical use.
This study investigates the potential of Hybrid Quantum Machine Learning (HQML) to improve the classification of skin lesions, a critical task for early detection of skin cancer. We utilized latent feature representations extracted by a Mobile CLIP model from a skin lesion dataset. These features were classified using three leading classical machine learning (ML) models-Logistic Regression (LR), Gradient Boosting (GB), and Support Vector Machine (SVM)-and compared against two quantum models: the Quantum Kernel Support Vector Machine (QSVM) and a Variational Quantum Classifier (VQC). All models were trained on features reduced to4dimensions via PCA. The results indicate that while classical models achieved high overall accuracy (GB: 0.9452, LR: 0.9424, SVM: 0.9292), they struggled significantly with the minority class (malignant lesions). The SVM achieved the highest recall for the minority class (0.36), outperforming LR (0.32) and GB (0.17). The QSVM achieved 100 % accuracy on the initial synthetic test data, while the VQC achieved an accuracy of 0.8933. These results highlight the potential of quantum feature spaces to enhance separability, establishing a baseline for further exploration of HQML in robust clinical decision support.
Skin cancer identification and categorization are still open issues in medical image analysis due to ambiguous boundaries, variance in shapes, and strong similarities to non-malignant lesions, which must be acknowledged by any framework supporting the clinical decision making. The proposed Quantum-Enhanced Deep Learning Framework (QDLF) is a new approach that combines Quantum feature encoding and Classical deep learning networks for skin lesion classification. Hereby, the QDLF is compared with the traditional models such as ResNet50, DenseNet, and VGG-16 showing a better performance on the HAM10000 dataset containing 10,015 dermoscopic images with seven lesion categories. Therefore, higher accuracy was achieved in the proposed framework at an accuracy level of 96.2% with F1-score 95.1% and ROCAUC value of 0.983 as compared to classical approaches. The QDLF uses quantum feature mappings with Variational Quantum Circuits (VQCs) that enables the model to learn abstract non-linear patterns and it incorporates global contextual features from pre-trained CNNs. The use of a mixture of CNN and FNN in this study not only improves the classification efficiency but also cuts down the time taken to train and the number of parameters involved, getting to a convergence point in 36 minutes with 18.5 million of parameters. To further enhance the interpretability of the model, Grad-CAM visualization is employed to identify clinically significant areas of the lesions as well as t-SNE plots showing good distinction in the quantum features space. The findings affirm the effectiveness of QDLF as a method for addressing class imbalance issues, with precision and recall for key classes such as melanoma at 92.7% and 94.1% respectively. Quantum-classical hybrid frameworks presented in this work reveal the uniqueness of the approach to medical image analysis in terms of scalability and applicability to real-life cases. Further studies will focus on implementation on quantum platforms and generalization of this approach to other image processing tasks in medicine.