Marwan Ait Haddou

Marwan Ait Haddou, 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.

Marwan Ait Haddou, Mohamed Bennai

We present a novel meta learning framework called Sculpture that explicitly conditions the Fubini Study metric tensor of parameterized quantum circuits to mitigate barren plateaus in variational quantum algorithms. Our theoretical analysis identifies the logarithmic condition number of the Fubini Study metric as a critical geometric quantity governing trainability, optimization dynamics, and generalization. Sculpture uses a classical meta model trained to generate data dependent quantum circuit initializations that minimize the logarithmic condition number, thereby promoting an isotropic and well conditioned parameter space. Empirical results show that meta training reduces the logarithmic condition number from approximately 1.47 to 0.64 by significantly increasing the minimum eigenvalue and slightly decreasing the maximum eigenvalue of the metric, effectively alleviating barren plateaus. This improved conditioning generalizes well to unseen data, consistently producing well conditioned quantum circuit initializations. In a downstream hybrid quantum classical classification task on the Kaggle diabetes dataset, increasing the meta scaling coefficient accelerates convergence, reduces training loss and gradient norms, and crucially improves generalization, with test accuracy increasing from about 0.68 to over 0.78. These findings demonstrate that sculpting the quantum landscape via meta learning serves as a principled geometric regularizer, substantially enhancing trainability, optimization, and generalization of parameterized quantum circuits and enabling more robust and efficient variational quantum algorithms.