Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE Access

Noise-Aware and Statistically Validated Dual-Branch Quantum Feature Learning for Robust Skin Lesion Classification

Alok Kumar Srivastava, Shadab Hussain, Shiru Sharma, Nidhi Sharma

Published Jan 1, 2026• 0 citations
Publisher

Abstract

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% $\pm ~0.75$ %, a mean balanced accuracy of 92.92% $\pm ~0.89$ %, and a mean macro-F1 score of $0.904~\pm ~0.009$ . 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.

DOI
10.1109/access.2026.3714913

Related papers

Quantum classical convolutional neural network using ResNet-18 and feature optimization for multiclass skin lesion classification

G. Suryanarayana, Mohd Dilshad Ansari, L. N. C. Prakash K. +3 more

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.

Discover Artificial Intelligence•May 20, 2026•0 citations

Shift-consistent and explanation-stable distributed hybrid quantum learning for domain-generalized skin lesion classification

Ramesh Sekaran, Arunkumar Gopu, Senthil Kumar A +1 more

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.

Scientific Reports•Aug 19, 2026•0 citations

Quantum-Enhanced Deep Learning Framework (QDLF): A Hybrid Approach for Advanced Skin Cancer Detection and Image Classification

S. Sai Kumar, Dr. Kannan Shanmugam, V Jyothi, T Venkata Deepthi, P. Srinivasa Rao, R. Suguna Devi

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.

Frontiers in Health Informatics•Dec 4, 2024•0 citations

Evaluation Integrity in Hybrid Quantum-Classical Skin Lesion Classification: A Data-Leakage Audit and Lesion-Level Correction on HAM10000

Muhammad Herman Jamaludin, Chang Soo Kim

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.

IEEE Access•Jan 1, 2026•0 citations

Quantum dual-branch neural networks with transfer learning for early detection of skin cancer

Yuyang Sun

BACKGROUND: Accurate classification of skin cancer is critical for early detection and timely treatment, significantly improving patient survival rates. While quantum neural networks combined with transfer learning show promise in medical image analysis, quantum noise remains a major challenge, compromising the stability and reliability of these systems. This study aims to address this limitation by developing a robust quantum-based framework for skin cancer classification. METHODS: We propose a Quantum Dual-Branch Neural Network (QDBNN) that employs two independently trained network branches without shared weights. Dual-modal features are fused at the fully connected layer, and a Variational Quantum Classifier (VQC) is utilized for final classification. The model is evaluated on two datasets: the multiclass HAM10000 and the binary Malignant vs. Benign dataset. RESULTS: QDBNN achieved state-of-the-art accuracies of 93.6% on HAM10000 and 93.5% on the Malignant vs. Benign dataset, outperforming classical and quantum transfer learning baselines. The dual-branch architecture and weighted feature fusion demonstrated enhanced robustness against quantum noise while improving generalization. CONCLUSION: QDBNN effectively mitigates quantum noise interference and leverages quantum-classical hybrid advantages for skin cancer classification. Its success highlights the potential of quantum-inspired architectures in medical imaging, offering a pathway toward clinically deployable tools for early diagnosis. Future work will focus on hardware optimization and scalability to larger datasets.

American Journal of Translational Research•Jan 1, 2025•5 citations

Quantum Kernel-Driven Hybrid Neural Network for Brain Tumor Classification

Alok Kumar Srivastava, Shadab Hussain, Shiru Sharma +2 more

Multiclass brain tumor classification from magnetic resonance imaging (MRI) remains challenging due to subtle inter-class visual similarities, particularly for anatomically small and heterogeneous tumor types such as pituitary lesions. To address these challenges, this paper presents a hybrid classical-quantum learning framework that integrates a deep convolutional feature extractor from the ResNet family with a variational quantum neural network (QNN) head for enhanced feature representation. In the present work, classical deep features extracted by the ResNet model are encoded into a six-qubit quantum circuit, enabling richer feature interactions within a high-dimensional Hilbert space. In addition, an anatomically guided Kernel-based Center Cropping (KCC) strategy is introduced as a deterministic spatial prior to emphasize anatomically relevant central brain structures, particularly benefiting challenging pituitary tumor cases. The proposed Kernel-based Center Cropping–Hybrid Quantum Neural Network (KCC-HQNN) framework is trained and evaluated on a publicly available composite four-class brain MRI dataset curated from Kaggle sources, comprising glioma, meningioma, pituitary tumor, and no-tumor categories. Experimental results across multiple ResNet variants demonstrate that the hybrid quantum–classical models consistently outperform their purely classical counterparts, achieving classification accuracy of up to 99%, while macro-averaged precision, recall, and F1 scores consistently fall in the range of approximately 0.95–0.99 across different ResNet variants. Reliability and reproducibility are further validated through stratified five-fold cross-validation and repeated experiments using multiple random initialization seeds, yielding a mean classification accuracy of 99.00 ± 0.08%, macro F1-score of 0.986 ± 0.11, and weighted F1-score of 0.989 ± 0.12, while cross-dataset evaluation on independent IEEE DataPort MRI datasets demonstrates robust generalization under dataset shift. All experiments are conducted on publicly available retrospective datasets using a quantum simulator. These results indicate that combining quantum feature processing with anatomically informed spatial processing improves multiclass discrimination of brain tumors.

IEEE Access•Jan 1, 2026•1 citation
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\pm ~0.75± 0.75 %, a mean balanced accuracy of 92.92% ± 0.89\pm ~0.89± 0.89 %, and a mean macro-F1 score of 0.904 ± 0.0090.904~\pm ~0.0090.904 ± 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=0.01p=0.01p=0.01 and 93.21% at p=0.05p=0.05p=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.
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.
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 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.
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\pm ~0.74± 0.74 test accuracy and a macro F1 of 0.804 against a verified baseline of 76.17% ± 1.91\pm ~1.91± 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.
BACKGROUND: Accurate classification of skin cancer is critical for early detection and timely treatment, significantly improving patient survival rates. While quantum neural networks combined with transfer learning show promise in medical image analysis, quantum noise remains a major challenge, compromising the stability and reliability of these systems. This study aims to address this limitation by developing a robust quantum-based framework for skin cancer classification. METHODS: We propose a Quantum Dual-Branch Neural Network (QDBNN) that employs two independently trained network branches without shared weights. Dual-modal features are fused at the fully connected layer, and a Variational Quantum Classifier (VQC) is utilized for final classification. The model is evaluated on two datasets: the multiclass HAM10000 and the binary Malignant vs. Benign dataset. RESULTS: QDBNN achieved state-of-the-art accuracies of 93.6% on HAM10000 and 93.5% on the Malignant vs. Benign dataset, outperforming classical and quantum transfer learning baselines. The dual-branch architecture and weighted feature fusion demonstrated enhanced robustness against quantum noise while improving generalization. CONCLUSION: QDBNN effectively mitigates quantum noise interference and leverages quantum-classical hybrid advantages for skin cancer classification. Its success highlights the potential of quantum-inspired architectures in medical imaging, offering a pathway toward clinically deployable tools for early diagnosis. Future work will focus on hardware optimization and scalability to larger datasets.
Multiclass brain tumor classification from magnetic resonance imaging (MRI) remains challenging due to subtle inter-class visual similarities, particularly for anatomically small and heterogeneous tumor types such as pituitary lesions. To address these challenges, this paper presents a hybrid classical-quantum learning framework that integrates a deep convolutional feature extractor from the ResNet family with a variational quantum neural network (QNN) head for enhanced feature representation. In the present work, classical deep features extracted by the ResNet model are encoded into a six-qubit quantum circuit, enabling richer feature interactions within a high-dimensional Hilbert space. In addition, an anatomically guided Kernel-based Center Cropping (KCC) strategy is introduced as a deterministic spatial prior to emphasize anatomically relevant central brain structures, particularly benefiting challenging pituitary tumor cases. The proposed Kernel-based Center Cropping–Hybrid Quantum Neural Network (KCC-HQNN) framework is trained and evaluated on a publicly available composite four-class brain MRI dataset curated from Kaggle sources, comprising glioma, meningioma, pituitary tumor, and no-tumor categories. Experimental results across multiple ResNet variants demonstrate that the hybrid quantum–classical models consistently outperform their purely classical counterparts, achieving classification accuracy of up to 99%, while macro-averaged precision, recall, and F1 scores consistently fall in the range of approximately 0.95–0.99 across different ResNet variants. Reliability and reproducibility are further validated through stratified five-fold cross-validation and repeated experiments using multiple random initialization seeds, yielding a mean classification accuracy of 99.00 ± 0.08%, macro F1-score of 0.986 ± 0.11, and weighted F1-score of 0.989 ± 0.12, while cross-dataset evaluation on independent IEEE DataPort MRI datasets demonstrates robust generalization under dataset shift. All experiments are conducted on publicly available retrospective datasets using a quantum simulator. These results indicate that combining quantum feature processing with anatomically informed spatial processing improves multiclass discrimination of brain tumors.