Mounir Mekkour
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mounir Mekkour has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Fatima-Ezzahraa Ben-Bouazza
BRET Lab, Mohammed VI University of Health Sciences, Casablanca 82403, Morocco
3 shared publications - Youssef Akdim
Laboratory of Modeling, Applied Mathematics, and Intelligent Systems (L2MASI), Department of Mathematics, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah
3 shared publications - Zakaria Said
University Sidi Mohamed Ben Abdellah
3 shared publications - Badr El Haji
Abdelmalek Essaadi University
2 shared publications - Jaouad Bennouna
Laboratory L2MASI, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, Fez, Morocco
2 shared publications - Mohammed El Fatry
Sidi Mohamed Ben Abdellah University
2 shared publications
Latest Publications
- Open Access
- 21 September 2026
- Published by MDPI AG in BioMedInformatics
- Vol. 6 (5) , 79
A Guarded Hybrid Pipeline for Rigid FLAIR–T1 MRI Registration: Learned Initialisation of Iterative Mutual-Information Refinement
Background: Rigid alignment of multimodal MRI is a prerequisite for neurological post-processing, yet classical iterative optimisers are accurate only when allowed to converge, at tens of seconds per volume, while learning-based predictors are fast but far less precise. This study asks whether a learned predictor can serve as the initialisation of an iterative optimiser so that both speed and accuracy are obtained. Methods: A supervised dual-path convolutional network with a cross-modal attention block (AttentionReg) was trained on BraTS 2020 under a subject-level split and a synthetic rigid-transformation protocol. Its prediction initialises a brain-masked Mattes Mutual-Information optimiser, forming a guarded hybrid pipeline in which a refinement is accepted only when it improves the metric. Eight methods were compared under one protocol on a common subset of 990 held-out pairs from 99 subjects, using a landmark-based Target Registration Error expressed in physical millimetres. Results: The proposed hybrid attained a median TRE of 0.81 mm over the evaluated pairs (IQR 0.57–1.12; P95 1.67 mm; 0.3% above 3 mm) at 0.79 s per volume, against 0.57 mm at 25.3 s for the fully converged iterative reference. The subject-level paired difference was 0.23 mm (95% CI 0.19–0.28), statistically significant yet equivalent within a 0.50 mm margin, obtained with a 32-fold reduction in computation time. Used alone, the network reached 3.10 mm; iterative refinement improved it by a mean subject-level paired reduction of 2.49 mm (95% CI 2.32–2.67). An ablation showed the attention block does not change median accuracy relative to a matched network without it. Conclusions: A learned initialiser converts an accurate but slow iterative method into an accurate and fast one, providing a proof of concept for real-time rigid multimodal MRI registration.
- 21 September 2026
- Published by MDPI AG in BioMedInformatics
- Vol. 6 (5) , 79
Open AccessA Guarded Hybrid Pipeline for Rigid FLAIR–T1 MRI Registration: Learned Initialisation of Iterative Mutual-Information Refinement
Background: Rigid alignment of multimodal MRI is a prerequisite for neurological post-processing, yet classical iterative optimisers are accurate only when allowed to converge, at tens of seconds per volume, while learning-based predictors are fast but far less precise. This study asks whether a learned predictor can serve as the initialisation of an iterative optimiser so that both speed and accuracy are obtained. Methods: A supervised dual-path convolutional network with a cross-modal attention block (AttentionReg) was trained on BraTS 2020 under a subject-level split and a synthetic rigid-transformation protocol. Its prediction initialises a brain-masked Mattes Mutual-Information optimiser, forming a guarded hybrid pipeline in which a refinement is accepted only when it improves the metric. Eight methods were compared under one protocol on a common subset of 990 held-out pairs from 99 subjects, using a landmark-based Target Registration Error expressed in physical millimetres. Results: The proposed hybrid attained a median TRE of 0.81 mm over the evaluated pairs (IQR 0.57–1.12; P95 1.67 mm; 0.3% above 3 mm) at 0.79 s per volume, against 0.57 mm at 25.3 s for the fully converged iterative reference. The subject-level paired difference was 0.23 mm (95% CI 0.19–0.28), statistically significant yet equivalent within a 0.50 mm margin, obtained with a 32-fold reduction in computation time. Used alone, the network reached 3.10 mm; iterative refinement improved it by a mean subject-level paired reduction of 2.49 mm (95% CI 2.32–2.67). An ablation showed the attention block does not change median accuracy relative to a matched network without it. Conclusions: A learned initialiser converts an accurate but slow iterative method into an accurate and fast one, providing a proof of concept for real-time rigid multimodal MRI registration.
- 2 August 2026
- Published by Springer Nature
- p. 525-536
Deep Learning for Breast Tumor Classification in Ultrasound Imaging: Enhancing Diagnosis with Explainability
- 2 August 2026
- Published by Springer Nature
- p. 525-536
Deep Learning for Breast Tumor Classification in Ultrasound Imaging: Enhancing Diagnosis with Explainability
- 9 June 2026
- Published by Institute of Mathematics, Czech Academy of Sciences
- p. 1-23
Renormalized solutions for some nonlinear degenerated parabolic problems
Institute of Mathematics of the Czech Academy of Sciences
- 9 June 2026
- Published by Institute of Mathematics, Czech Academy of Sciences
- p. 1-23
Renormalized solutions for some nonlinear degenerated parabolic problems
Institute of Mathematics of the Czech Academy of Sciences
- 29 May 2026
- Published by Springer Nature
- p. 147-158
Analysis of Elliptic Systems with Singular Diffusion Coefficients
- 29 May 2026
- Published by Springer Nature
- p. 147-158
Analysis of Elliptic Systems with Singular Diffusion Coefficients
- 3 March 2026
- Published by Springer Nature in Journal of Elliptic and Parabolic Equations
- Vol. 12 (1) , 991-1004
Existence results for the second-order discrete boundary value problem involving the p-Laplacian with a parameter
- 3 March 2026
- Published by Springer Nature in Journal of Elliptic and Parabolic Equations
- Vol. 12 (1) , 991-1004
Existence results for the second-order discrete boundary value problem involving the p-Laplacian with a parameter
- 20 July 2025
- Published by Springer Nature
- p. 93-107
SurvivalNets: Brain Tumor Patients Survival Rates Prediction Through MRI Segmentation Models
- 20 July 2025
- Published by Springer Nature
- p. 93-107
SurvivalNets: Brain Tumor Patients Survival Rates Prediction Through MRI Segmentation Models
- Open Access
- 11 January 2024
- Published by Universidad Nacional de Colombia in Revista Colombiana de Matemáticas
- Vol. 57 (1) , 123-154
On the some equations inequalities in Musielak-Orlicz spaces with measure data
Our aim in this present work is to prove the existence of a solution for the nonlinear unilateral parabolic problems associated to the equation ∂u - div a(x, t, u, ∇u) - div Φ(x, t, u) = μ in QT = Ω × (0, T), ∂t where the lower order term Φ satisfies a generalized natural growth condition and the datum μ belongs to L1(Q) + E (Q). El objetivo de este trabajo es probar la existencia de soluciones para problemas parabólicos unilaterales asociados a la ecuación ∂u - div a(x, t, u, ∇u) - div Φ(x, t, u) = μ in QT = Ω × (0, T), ∂t donde el término Φ satisface una condición natural generalizada de crecimiento y la condición μ pertenece al espacio L1(Q) + E (Q).
- 11 January 2024
- Published by Universidad Nacional de Colombia in Revista Colombiana de Matemáticas
- Vol. 57 (1) , 123-154
Open AccessOn the some equations inequalities in Musielak-Orlicz spaces with measure data
Our aim in this present work is to prove the existence of a solution for the nonlinear unilateral parabolic problems associated to the equation ∂u - div a(x, t, u, ∇u) - div Φ(x, t, u) = μ in QT = Ω × (0, T), ∂t where the lower order term Φ satisfies a generalized natural growth condition and the datum μ belongs to L1(Q) + E (Q). El objetivo de este trabajo es probar la existencia de soluciones para problemas parabólicos unilaterales asociados a la ecuación ∂u - div a(x, t, u, ∇u) - div Φ(x, t, u) = μ in QT = Ω × (0, T), ∂t donde el término Φ satisface una condición natural generalizada de crecimiento y la condición μ pertenece al espacio L1(Q) + E (Q).
- 25 June 2022
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Zurnal matematiceskoj fiziki, analiza, geometrii
- Vol. 18 (3) , 332-349
On Some Nonlinear Elliptic Problems with Large Monotonocity in Musielak–Orlicz–Sobolev Spaces
У цiй роботi ми вивчаємо iснування ентропiйного розв’язку деякої нелiнiйної елiптичної проблеми типу Лерея–Лiонса, пов’язану з рiвнянням −div a(x,u,∇u) = f(x)−div F(u) в Ω з умовою великої монотонностi у визначеннi просторiв Мусйелака–Орлича–Соболєва, де права частина належить L1 (Ω) i F = (F 1 ,...,F N ) задовольняє умову F ∈ (C0 (ℝ))N . Mathematical Subject Classification 2010: 35J62, 35J25
- 25 June 2022
- Published by National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka) (Publications) in Zurnal matematiceskoj fiziki, analiza, geometrii
- Vol. 18 (3) , 332-349
On Some Nonlinear Elliptic Problems with Large Monotonocity in Musielak–Orlicz–Sobolev Spaces
У цiй роботi ми вивчаємо iснування ентропiйного розв’язку деякої нелiнiйної елiптичної проблеми типу Лерея–Лiонса, пов’язану з рiвнянням −div a(x,u,∇u) = f(x)−div F(u) в Ω з умовою великої монотонностi у визначеннi просторiв Мусйелака–Орлича–Соболєва, де права частина належить L1 (Ω) i F = (F 1 ,...,F N ) задовольняє умову F ∈ (C0 (ℝ))N . Mathematical Subject Classification 2010: 35J62, 35J25
- 20 February 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2074 (1) , 020001
Doubly nonlinear parabolic inequality in weighted Sobolev spaces with irregular data
We study the strongly nonlinear degenerate parabolic problems with obstacle of the type: we prove the existence of entropy solutions in the framework of weighted Sobolev space with the homogeneous Dirichlet boundary conditions and the initial conditions in the time t = 0.- 20 February 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2074 (1) , 020001
Doubly nonlinear parabolic inequality in weighted Sobolev spaces with irregular data
We study the strongly nonlinear degenerate parabolic problems with obstacle of the type: we prove the existence of entropy solutions in the framework of weighted Sobolev space with the homogeneous Dirichlet boundary conditions and the initial conditions in the time t = 0.- 7 July 2016
- Published by Taylor & Francis in Applicable Analysis
- Vol. 96 (12) , 2102-2117
Nonlinear parabolic inequalities with lower order terms
We prove an existence result of entropy solutions for the nonlinear parabolic problems with obstacle in and a.e. in where b(x, u) is a strictly increasing -function of u, the term is a Leray–Lions type operator and the function is a nonlinear lower order term and satisfies only growth condition. The data f belongs to . The proof is based on the penalization methods.
- 7 July 2016
- Published by Taylor & Francis in Applicable Analysis
- Vol. 96 (12) , 2102-2117
Nonlinear parabolic inequalities with lower order terms
We prove an existence result of entropy solutions for the nonlinear parabolic problems with obstacle in and a.e. in where b(x, u) is a strictly increasing -function of u, the term is a Leray–Lions type operator and the function is a nonlinear lower order term and satisfies only growth condition. The data f belongs to . The proof is based on the penalization methods.