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% $\pm ~0.74$ test accuracy and a macro F1 of 0.804 against a verified baseline of 76.17% $\pm ~1.91$ . 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.
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.
Abstract Accurate skin lesion classification in real-world deployment remains difficult when models are trained on a single dataset and must generalize across heterogeneous devices and patient cohorts. Quantum computing can enrich representation learning via variational transformations in high-dimensional Hilbert spaces, yet clinically reliable and domain-robust hybrid quantum dermoscopy remains insufficiently explored. A shift-consistent and explanation-stable distributed hybrid quantum network (SCES-QNet) was developed to examine whether source-only cross-domain generalization, calibration, and attribution consistency could be improved within a unified dermoscopic classification framework. Distributed quantum branches were combined with prediction-consistency and attribution-equivariance regularization under strict source-only training. HAM10000 was used for model development, whereas ISIC 2019 and PAD-UFES-20 were reserved for external evaluation after class-taxonomy harmonization. Discrimination, calibration, and explanation-stability measures were assessed over five independently initialized runs. On HAM10000, near-ceiling performance was achieved (Macro-F1 = 98.4%, Balanced Accuracy = 98.6%, macro-AUROC = 0.998). Under source-only transfer, strong retention was maintained on ISIC 2019 and PAD-UFES-20 (Macro-F1 = 96.2% / 94.8%; macro-AUROC = 0.993 / 0.989). Calibration degradation remained controlled (ECE: 0.007 → 0.014 → 0.017), and explanation stability remained high across domains (ESS ≥ 0.872). Under the evaluated protocol, SCES-QNet was associated with strong discrimination, controlled calibration drift, and comparatively stable explanations across the selected datasets. The findings provide preliminary evidence for stability-aware hybrid quantum learning in dermoscopic classification; however, broader multi-center evaluation, verified cross-archive duplicate auditing, and execution on physical NISQ hardware remain necessary before clinical or hardware-level conclusions can be drawn.
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.
Background/Objectives: Hybrid quantum–classical neural networks are reported to classify brain tumors on magnetic resonance imaging (MRI) accurately, but these reports rarely control for data leakage or test whether the quantum circuit contributes. We examined both issues. Methods: We audited version 2 of the Kaggle Brain Tumor MRI Dataset (7200 images) with mirror- and rotation-invariant duplicate detection and by matching every image to its source collections, which recovered patient identities for 4846 tumor images. A variational quantum circuit (VQC) was compared with size-matched, deeper and Fourier-surrogate classical controls using frozen features, end-to-end fine-tuning and training from scratch, all under patient-grouped five-fold cross-validation. Results: Of the 1600 test images, 1269 (79%) had a copy in the training partition, and 915 of the 917 figshare-derived test images shared a patient with it. On frozen features, a six-qubit VQC head was 6.0 percentage points (pp) less accurate than its classical control (95% confidence interval −6.8 to −5.2) and less accurate than a classical surrogate of its own function class. With fine-tuning, it stayed within about 1 pp of its control but was 0.7 pp less accurate (−1.2 to −0.1) after convergence-based training; a hybrid network trained from scratch was 8.3 pp less accurate than its control. Patient-grouped evaluation lowered accuracy by 3–8 pp relative to our earlier duplicate-grouped evaluation, and 76 glioma test images from another source remained poorly recognized. Conclusions: The quantum layer added cost but no accuracy, and leakage and provenance mattered more than the classifier head.
Abstract Quantum machine learning (QML) has recently been explored as a means of augmenting classical convolutional neural networks (CNNs) for medical image analysis, yet most existing hybrid architectures insert a single quantum component either at the input or the output of an otherwise classical pipeline, and few works empirically isolate which placement is actually responsible for performance change. This paper proposes QCQ-CNN, a Quantum-Classical-Quantum hybrid framework for brain tumor magnetic resonance imaging (MRI) classification in which a quantum convolutional (“quanvolutional”) layer performs early-stage feature extraction, a classical CNN backbone performs hierarchical representation learning, and a variational quantum circuit (VQC) performs final classification, so that quantum processing brackets the classical backbone at both ends. Using a real, held-out four-class brain tumor MRI dataset (glioma, meningioma, pituitary tumor, and no tumor), we implement and train four architectural variants under matched conditions — (A) a fully classical CNN baseline, (B) a quantum-convolution-plus-classical-CNN variant, (C) a classical-CNN-plus-quantum-head variant, and (D) the full proposed QCQ-CNN — and report actual experimental accuracy, precision, recall, and F1-score on a common test set, together with training curves, confusion matrices, and qualitative visualizations of the learned quantum feature maps. Our small-scale experiments show that quantum convolutional preprocessing alone improves macro-F1 over the classical baseline (0.204 to 0.382), while replacing the classical classification head with a variational quantum circuit degrades performance in both the quantum-head-only and the full QCQ-CNN configurations. We discuss this finding in the context of variational quantum circuit trainability at low qubit counts and limited data, and argue that our staged ablation methodology — rather than a single best-accuracy claim — constitutes the paper's principal novelty: a reusable protocol for empirically localizing where, in a CNN pipeline, quantum layers help versus hurt. We conclude with concrete design recommendations and directions for scaling QCQ-style frameworks. Keywords: Quantum Machine Learning, Hybrid Quantum-Classical Neural Networks, Quanvolutional Neural Network, Variational Quantum Circuit, Convolutional Neural Network, Brain Tumor Classification, Medical Image Processing
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.
Quantum machine learning (QML) presents a promising avenue for addressing complex classification challenges, yet its application in medical imaging remains largely unexplored. This work introduces a hybrid quantum classical framework designed to classify skin diseases—Chickenpox, Measles, Monkeypox, and Normal—using a 4 qubit quantum system. The framework integrates a Quantum Convolutional Neural Network (QCNN) for feature extraction and a Variational Quantum Classifier (VQC) for classification, processing a dataset of 770 images with significant class imbalance. To address this imbalance, we employ a class weighted loss function with weightswyi= [3.0, 3.5, 0.6, 0.4], ensuring balanced representation across all classes. The model is optimized using Simultaneous Perturbation Stochastic Approximation (SPSA) over 150 iterations, achieving a test accuracy of 70.13% on a subset of 154 images, which represents 20% of the dataset. This marks a substantial improvement over both a random baseline of 25% and a prior run that achieved 37.66% accuracy, which was skewed toward the majority class. Principal Component Analysis (PCA) reduces image features to a 4 dimensional representation, enabling compatibility with the quantum system. The QCNN extracts these features, while the VQC performs classification based on measurements from 1024 shots on the QASM simulator. To ensure practical reusability, the trained model—including quantum circuits, optimized parameters, and PCA transformations—is saved for future deployment. Validation on a separate set of 24 samples (6 per class) yields 70.83% accuracy (17 out of 24 correct predictions), demonstrating the model’s generalization capabilities. While the performance falls short of classical benchmarks, this study establishes the feasibility of QML with minimal qubits, paving the way for quantum driven diagnostics in resource constrained environments.