Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mostafa El Habib Daho has a total of 126 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CornOrb: A Multimodal Dataset of Orbscan Corneal Topography and Clinical Annotations for Keratoconus Detection

    by Mohammed El Amine Lazouni, Leila Ryma Lazouni, Zineb Aziza Elaouaber, Mohammed Ammar, Soufyane Zehar, Mohammed Youcef Bouayad Agha, Ahmed Lazouni, Amel Feroui, Ali H. Al-Timemy, Siamak Yousefi, et al.

    Keratoconus assessment relies on corneal topography to characterize curvature, elevation, and thickness. Public datasets remain limited, particularly for Orbscan 3 and underrepresented geographic populations. CornOrb is a multimodal dataset of Bausch & Lomb Orbscan 3 examinations retrospectively collected at an ophthalmology center in Algeria. It contains 1454 examination records from 744 patients: 889 clinically normal and 565 keratoconus records. For each eye, four anonymized PNG maps are provided: axial curvature, anterior elevation, posterior elevation, and pachymetry. Native pixel-wise quantitative curvature, elevation, and pachymetry matrices are not available in the current release. A structured CSV file provides age, sex, astigmatism, maximum keratometry, central and thinnest pachymetry, and anterior and posterior asphericity. Diagnostic labels correspond to the final adjudicated binary clinical diagnosis at the examination level and were established from clinical records together with Orbscan 3 findings. Only clinically definite normal and keratoconus cases were retained, whereas borderline, suspected, forme-fruste, subclinical, or otherwise diagnostically uncertain cases were excluded from the binary dataset. No independent quantitative diagnostic or staging index was used as a corroborating criterion, and inter-rater reliability could not be retrospectively quantified. Accordingly, performance on CornOrb should be interpreted within this adjudicated binary task and should not be extrapolated to early-stage, subclinical, or borderline keratoconus detection. CornOrb is intended to support reproducible research on keratoconus detection and analysis, including image-based classification, multimodal learning combining topographic maps and tabular variables, and reproducible comparative evaluation of machine-learning methods within the CornOrb cohort. To the best of our knowledge, CornOrb is the first publicly accessible African Orbscan 3 dataset dedicated to keratoconus analysis.

  • Open Access

    Beyond Accuracy: Assessing the Trustworthiness of Deep Learning Models for Coronary CT Angiography

    by Kenza Bougrid, Mohammed Ammar, Amel Laidi, Mahmood Alzubaidi, Marco Agus, Mowafa Househ, Mostafa El Habib Daho

    The use of high-performing deep learning models in clinical settings raises concerns about trust, especially because these models often lack interpretability. In this study, we fine-tuned four different architectures: DenseNet121, InceptionV3, InceptionResNetV2, and ViT-B/16. for the detection of atherosclerosis on coronary CT angiography (CCTA) and jointly evaluated their predictive performance and explainability. Using k-fold cross-validation and held-out test data, DenseNet121 and ViT-B/16 achieved higher accuracy, precision, and recall than the Inception models; ViT-B/16 reached a test accuracy of 96.17%, followed by DenseNet121 with 95.80%, and both significantly outperformed the Inception architectures in statistical comparisons. We applied multiple XAI techniques, including LIME, SHAP, and Integrated Gradients, to characterize how each model arrived at its predictions. DenseNet121 provided localized, vessel-specific saliency focused on clinically relevant coronary segments, whereas ViT-B/16 displayed more holistic, patch-level attention that captured broader vascular context while maintaining strong predictive performance. This combined performance–interpretability analysis advances trustworthy AI for coronary artery disease detection on CCTA by linking automated predictions to clinically meaningful image patterns and supporting future development of explainable decision-support tools in cardiology.

  • Open Access

    Stain-Standardized Deep Learning Framework for Robust Leukocyte Segmentation Across Heterogeneous Cytological Datasets

    by Leila Ryma Lazouni, Mourtada Benazzouz, Fethallah Hadjila, Mohammed El Amine Lazouni, Mostafa El Habib Daho

    Accurate leukocyte segmentation remains challenging in automated hematological analysis due to staining variability, heterogeneous imaging conditions, and morphological diversity across cytological datasets, severely limiting deep learning model generalization. This work proposes a dual-module framework designed to achieve stain-invariant and robust leukocyte segmentation. The first module performs explicit stain standardization by combining a VGG-based encoder, a transformer bottleneck, and a convolutional decoder to harmonize diverse inputs toward a Wright–Giemsa reference appearance. The second module introduces a multi-encoder segmentation architecture integrating complementary spatial, leukocyte-specific, and nucleus-focused representations extracted from multiple color spaces. The framework is evaluated on six public and clinical datasets covering multiple staining protocols, magnifications, and imaging scenarios. Experimental results demonstrate consistent high performance, with Dice coefficients exceeding 96% on most datasets and systematic improvements over state-of-the-art methods. Extensive ablation studies confirm the synergistic contributions of stain-standardization and multi-encoder fusion to model robustness and cross-dataset generalization. This framework overcomes stain variability and domain shift, offering a practical tool for automated leukocyte analysis in clinical settings.

  • Open Access

    JustRAIGS: Justified Referral in AI Glaucoma Screening Challenge

    by Yeganeh Madadi, Hina Raja, Koenraad A. Vermeer, Hans G. Lemij, Xiaoqin Huang, Eunjin Kim, Seunghoon Lee, Gitaek Kwon, Hyunwoo Kim, Jaeyoung Kim, et al.

    A major contributor to permanent vision loss is glaucoma. Early diagnosis is crucial for preventing vision loss due to glaucoma, making glaucoma screening essential. A more affordable method of glaucoma screening can be achieved by applying artificial intelligence to evaluate color fundus photographs (CFPs). We present the Justified Referral in AI Glaucoma Screening (JustRAIGS) challenge to further develop these AI algorithms for glaucoma screening and to assess their efficacy. To support this challenge, we have generated a distinctive big dataset containing more than 110,000 meticulously labeled CFPs obtained from approximately 60,000 patients and 500 distinct screening centers in the USA. Our objective is to assess the practicality of creating advanced and dependable AI systems that can take a CFP as input and produce the probability of referable glaucoma, as well as outputs for glaucoma justification by integrating both binary and multi-label classification tasks. This paper presents the evaluation of solutions provided by nine teams, recognizing the team with the highest level of performance. The highest achieved score of sensitivity at a specificity level of 95% was 85%, and the highest achieved score of Hamming losses average was 0.13. Additionally, we test the top three participants' algorithms on an external dataset to validate the performance and generalization of these models. The outcomes of this research can offer valuable insights into the development of intelligent systems for detecting glaucoma. Ultimately, findings can aid in the early detection and treatment of glaucoma patients, hence decreasing preventable vision impairment and blindness caused by glaucoma.


  • Open Access

    Automated multimodal severity assessment of diabetic retinopathy using ultra-widefield color fundus photography and clinical tabular data

    by Alireza Rezaei, Sarah Matta, Rachid Zeghlache, Pierre-Henri Conze, Capucine Lepicard, Pierre Deman, Laurent Borderie, Deborah Cosette, Sophie Bonnin, Aude Couturier, et al.


  • Open Access

    Artificial Intelligence–Derived Biomechanical Index for Early Corneal Ectasia Detection: Advancing Beyond Tomography

    by Hazem Abdelmotaal, Suphi Taneri, Ramin Salouti, M. Hossein Nowroozzadeh, Ali H. Al-Timemy, Alexandru Lavric, Mostafa El Habib Daho, Hidenori Takahashi, Rossen Mihaylov Hazarbassanov, Siamak Yousefi


  • Open Access

    Explainable AI for early malaria detection using stacked-LSTM and attention mechanisms

    by Adil Gaouar, Souaad Hamza Cherif, Abdellatif Rahmoun, Mostafa El Habib Daho


  • Open Access

    High-capacity DWT-SVD watermarking for MRI images embedding MITR medical information

    by Aicha Benyoucef, Aya Goudjil, M'HAmed Hamadouche, Mohammed Chaker Boutalbi, Mohammed Ammar, Mostafa El Habib Daho


  • Deep Learning-Based Detection of Referable Diabetic Retinopathy and Macular Edema Using Ultra-widefield Fundus Imaging

    by Philippe Zhang, Pierre-Henri Conze, Mathieu Lamard, Béatrice Cochener, Gwenolé Quellec, Mostafa El Habib Daho


  • Open Access

    L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction

    by Rachid Zeghlache, Pierre-Henri Conze, Mostafa El Habib Daho, Yihao Li, Alireza Rezaei, Hugo Le Boité, Ramin Tadayoni, Pascal Massin, Béatrice Cochener, Ikram Brahim, et al.