Marwan AIT HADDOU

Mr. Marwan AIT HADDOU

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 June 2025 in medRxiv
Verified
Preprint
Open access
PDF file
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Bennai
Mohamed Bennai
This study investigates the efficacy of a hybrid quantum-classical model, denoted as HQCM-EBTC, for the automated classification of brain tumors, comparing its performance against a classical counterpart. A comprehensive dataset comprising 7,576 magnetic resonance imaging (MRI) images, encompassing normal brain structures, meningioma, glioma, and pituitary tumors, was employed. The HQCM-EBTC model integrates a quantum processing layer with 5 qubits per circuit, a circuit depth of 2, and 5 parallel circuits, trained via the AdamW optimizer with a composite loss function that combines cross-entropy and attention consistency losses. The results demonstrate that HQCM-EBTC significantly outperforms the classical model, achieving an overall classification accuracy of 96.48% compared to 86.72%. The quantumenhanced model exhibits superior precision, recall, and F1-scores across all tumor classes, particularly in glioma classification. t-SNE visualizations reveal enhanced feature separability within the quantum processing layer, leading to more distinct decision boundaries. Confusion matrix analysis further substantiates a reduction in misclassification rates with HQCM-EBTC. Moreover, attention map analysis, quantified using the Jaccard Index, indicates that HQCM-EBTC produces more localized and accurate tumor region activations, especially at higher confidence thresholds. These findings underscore the potential of quantum-enhanced models to improve brain tumor classification accuracy and localization, offering promising advancements for clinical diagnostic applications. The demonstrated ability of HQCM-EBTC to achieve higher accuracy and more precise tumor localization suggests a significant step forward in applying quantum computing to medical imaging analysis.

4 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Bennai
Mohamed Bennai
This study investigates the efficacy of a hybrid quantum-classical model, denoted as HQCM-EBTC, for the automated classification of brain tumors, comparing its performance against a classical counterpart. A comprehensive dataset comprising 7,576 magnetic resonance imaging (MRI) images, encompassing normal brain structures, meningioma, glioma, and pituitary tumors, was employed. The HQCM-EBTC model integrates a quantum processing layer, characterized by 5 qubits per circuit, a circuit depth of 2, and 5 parallel circuits, trained via the AdamW optimizer with a composite loss function that combines cross-entropy and attention consistency losses. The results demonstrate that HQCM-EBTC significantly outperforms the classical model, achieving an overall classification accuracy of 96.48\% compared to 86.72\%. The quantum-enhanced model exhibits superior precision, recall, and F1-scores across all tumor classes, particularly in the classification of glioma. t-SNE visualizations reveal enhanced feature separability within the quantum processing layer, leading to more distinct decision boundaries. Confusion matrix analysis further substantiates a reduction in misclassification rates with HQCM-EBTC. Moreover, attention map analysis, quantified using the Jaccard Index, indicates that HQCM-EBTC produces more localized and accurate tumor region activations, especially at higher confidence thresholds. These findings underscore the potential of quantum-enhanced models to improve brain tumor classification accuracy and localization, offering promising advancements for clinical diagnostic applications. The demonstrated ability of HQCM-EBTC to achieve higher accuracy and more precise tumor localization suggests a significant step forward in the application of quantum computing to medical imaging analysis.
1

27 June 2025 in Authorea
Verified
Preprint
Open access
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Bennai
Mohamed Bennai

27 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Bennai
Mohamed Bennai
We propose HQCM-EBTC, a hybrid quantum-classical model for automated brain tumor classification using MRI images. Trained on a dataset of 7,576 scans covering normal, meningioma, glioma, and pituitary classes, HQCM-EBTC integrates a 5-qubit, depth-2 quantum layer with 5 parallel circuits, optimized via AdamW and a composite loss blending cross-entropy and attention consistency. HQCM-EBTC achieves 96.48% accuracy, substantially outperforming the classical baseline (86.72%). It delivers higher precision and F1-scores, especially for glioma detection. t-SNE projections reveal enhanced feature separability in quantum space, and confusion matrices show lower misclassification. Attention map analysis (Jaccard Index) confirms more accurate and focused tumor localization at high-confidence thresholds. These results highlight the promise of quantum-enhanced models in medical imaging, advancing both diagnostic accuracy and interpretability for clinical brain tumor assessment.

9 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
In this study, we demonstrate the use of physics-informed neural networks (PINNs) for computing the quasinormal modes (QNMs) of black holes in de Rham-Gabadadze-Tolley (dRGT) massive gravity. These modes describe the oscillation frequencies of perturbed black holes and are important in understanding the behavior of these objects. We show that by carefully selecting the hyperparameters of the PINN, including the network architecture and the training data, it is possible to achieve good agreement between the computed QNMs and the approximate analytical formula in the near-extremal limit for the smallest mode number. Our results demonstrate the effectiveness of PINNs for solving inverse problems in the context of QNMs and highlight the potential of these algorithms for providing valuable insights into the behavior of black holes.
1

4 May 2026 in Progress of Theoretical and Experimental Physics
Verified
Journal Article
Open access
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Belfkir
Mohamed Belfkir
SHSalah Eddine El Harrauss
Salah Eddine El Harrauss
In this paper, we propose a hybrid quantum machine learning framework to improve the sensitivity of double Higgs boson searches in the $HH \rightarrow b\bar{b}\gamma \gamma$ final state at $\sqrt{s} = 13.6~\text{TeV}$. The proposed model combines parameterized quantum circuits with a classical neural network meta-model, enabling event-level features to be embedded in a quantum feature space while maintaining the optimization stability of classical learning. In our benchmark setup, the hybrid model outperforms the pure quantum implementation and improves over the XGBoost baseline while performing similarly to the graph neural network baseline, achieving an expected 95% CL upper limit on the nonresonant double Higgs boson production cross section of $1.9\times \sigma _{\text{SM}}$ and $2.1\times \sigma _{\text{SM}}$ under background normalization uncertainties of 10% and 50%, respectively. In addition, expected constraints on the Higgs boson self-coupling $\kappa _{\lambda }$ and quartic vector-boson–Higgs coupling $\kappa _{2V}$ are improved relative to the pure quantum model and competitive with the classical baselines considered in this work.