Nasir, Inzamam Mashood
- research article[2026][S1][T007][33]
;Abdelbaki, Wiem ;Alshaya, Hend; ;Tehsin, Sara ;Said, SalwaBouchelligua, WidedBiomedicines., 2026, p. 1-33Background: Diagnosing CNS tumors through MRI is limited by significant variability in scanner hardware, acquisition protocols, and intensity characteristics at clinical centers, resulting in substantial domain shifts that lead to diminished reliability for automated models. Methods: We present a Domain-Adaptive MRI Learning Model (DA-MLM) consisting of an adversarially aligned hybrid 3D CNN-transformer encoder with contrastive regularization and covariance-based feature harmonization. Varying sequence MRI inputs (T1, T1ce, T2, and FLAIR) were inputted to multi-scale convolutional layers followed by global self-attention to effectively capture localized tumor structure and long-range spatial context, with domain adaptation that harmonizes feature distribution across datasets. Results: On the BraTS 2020 dataset, we found DA-MLM achieved 94.8% accuracy, 93.6% macro-F1, and 96.2% AUC, improving upon previously established benchmarks by 2-4%. DA-MLM also attained Dice score segmentation of 93.1% (WT), 91.4% (TC), and 89.5% (ET), improving upon 2-3.5% for CNN and transformer methods. On the REMBRANDT dataset, DA-MLM achieved 92.3% accuracy with segmentation improvements of 3-7% over existing U-Net and expert annotations. Robustness testing indicated 40-60% less degradation under noise, contrast shift, and motion artifacts, and synthetic shifts in scanner location showed negligible performance impairment (<0.06). Cross-domain evaluation also demonstrated 5-11% less degradation than existing methods. Conclusions: In summary, DA-MLM demonstrates improved accuracy, segmentation fidelity, and robustness to perturbations, as well as strong cross-domain generalization indicating the suitability for deployment in multicenter MRI applications where variation in imaging performance is unavoidable.
5 19Scopus© Citations 3 Transformer-based foundation learning for robust and data-efficient skin disease imagingItem type:Publication, research article[2026][S1][T007][31]; ;Alshaya, Hend ;Tehsin, SaraBouchelligua, WidedDiagnostics, 2026, vol. vol. 16, no. iss. 3, p. 1-31Background/Objectives: Accurate and reliable automated dermoscopic lesion classification remains challenging. This is due to pronounced dataset bias, limited expert-annotated data, and poor cross-dataset generalization of conventional supervised deep learning models. In clinical dermatology, these limitations restrict the deployment of data-driven diagnostic systems across diverse acquisition settings and patient populations. Methods: Motivated by these challenges, this study proposes a transformer-based, dermatology-specific foundation model. The model learns transferable visual representations from large collections of unlabeled dermoscopic images via self-supervised pretraining. It integrates large-scale dermatology-oriented self-supervised learning with a hierarchical vision transformer backbone. This enables effective capture of both fine-grained lesion textures and global morphological patterns. The evaluation is conducted across three publicly available dermoscopic datasets: ISIC 2018, HAM10000, and PH2. The study assesses in-dataset, cross-dataset, limited-label, ablation, and computational-efficiency settings. Results: The proposed approach achieves in-dataset classification accuracies of 94.87%, 97.32%, and 98.17% on ISIC 2018, HAM10000, and PH2, respectively. It outperforms strong transformer and hybrid baselines. Cross-dataset transfer experiments show consistent performance gains of 3.5-5.8% over supervised counterparts. This indicates improved robustness to domain shift. Furthermore, when fine-tuned with only 10% of the labeled training data, the model achieves performance comparable to fully supervised baselines. Conclusions: This highlights strong data efficiency. These results demonstrate that dermatology-specific foundation learning offers a principled and practical solution for robust dermoscopic lesion classification under realistic clinical constraints.
Scopus© Citations 6 2 Deep sequence learning with multi-task supervision for scalable population health monitoringItem type:Publication, research article[2026][S1a][N009][21] ;Ashraf, Imran; ;Awais, Muhammad ;Bouchelligua, Wided ;Mansour, Sahar ;Alyounis, EssaNawaz, MajedFrontiers in public health, 2026, vol. 14, p. 1-21Models designed for artificial intelligence-driven population health monitoring must be able to integrate multiple types of information over time, be heterogeneous in the data they consider, and be deployed at scale. This research proposes an integrated multitask framework for predicting population disease incidence and mortality risk, based on deep learning and using both longitudinal biobank and National Health Survey data in a scalable manner. The framework will learn shared temporal representations from clinical lab-generated/demographically defined survey variables by applying a strict prospective evaluation approach across the framework. On UK Biobank, the proposed model achieves an AUROC of 0.842 and a C-index of 0.791, outperforming strong baselines such as Proformer having AUROC 0.829 and UKB-MDRMF having AUROC 0.821. On NHANES, the model achieves an AUROC of 0.861 and a C-index of 0.808, exceeding those of commonly used boosted tree and survival-based approaches. Temporal robustness analysis shows controlled performance degradation across extended horizons, with UK Biobank AUROC decreasing from 0.872 at 1 year to 0.819 at 10 years and NHANES AUROC decreasing from 0.886 at 1 year to 0.836 at 5 years. Subgroup evaluation demonstrates stable performance across age, sex, and clinical risk strata, while scalability analysis confirms near-linear training growth and stable inference latency below three milliseconds per individual at biobank scale.