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


Loay Hassan has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cross-Modal Correlation Fusion for End-to-End ECG–PPG Stress Classification

    by Abdelrhman Y. Soliman, Loay Hassan, Domenec Puig, Hatem A. Rashwan

    Automated stress detection is critical for clinical monitoring; however, developing robust models that address the non-stationary nature and inter-subject variability. This paper presents a multimodal deep learning framework that lever-ages the synergy between Electrocardiogram (ECG) and Photoplethysmography (PPG) signals for reliable stress identification. The proposed architecture utilizes dual parallel encoders to autonomously extract high-level morphological features from both cardiovascular streams. To bridge these heterogeneous modalities, we introduce a cross-modal correlation fusion layer that explicitly models the electro-mechanical alignment between cardiac electrical triggers and peripheral blood volume pulses. We rigorously evaluated the framework on the publicly available WESAD dataset using a subject-independent 5-fold cross-validation protocol. Our method achieved a mean Accuracy of 90.34%, an AUC-ROC of 97.29%, and a Stress Recall of 94.07%. These results demonstrate that the framework offers a scalable, high-performance solution for real-time monitoring systems that facilitates proactive interventions in healthcare and automotive environments without requiring manual feature engineering.

  • Open Access

    Classifying Breast Tumors in Digital Tomosynthesis by Combining Image Quality-Aware Features and Tumor Texture Descriptors

    by Loay Hassan, Mohamed Abdel-Nasser, Adel Saleh, Domenec Puig

    Digital breast tomosynthesis (DBT) is a 3D breast cancer screening technique that can overcome the limitations of standard 2D digital mammography. However, DBT images often suffer from artifacts stemming from acquisition conditions, a limited angular range, and low radiation doses. These artifacts have the potential to degrade the performance of automated breast tumor classification tools. Notably, most existing automated breast tumor classification methods do not consider the effect of DBT image quality when designing the classification models. In contrast, this paper introduces a novel deep learning-based framework for classifying breast tumors in DBT images. This framework combines global image quality-aware features with tumor texture descriptors. The proposed approach employs a two-branch model: in the top branch, a deep convolutional neural network (CNN) model is trained to extract robust features from the region of interest that includes the tumor. In the bottom branch, a deep learning model named TomoQA is trained to extract global image quality-aware features from input DBT images. The quality-aware features and the tumor descriptors are then combined and fed into a fully-connected layer to classify breast tumors as benign or malignant. The unique advantage of this model is the combination of DBT image quality-aware features with tumor texture descriptors, which helps accurately classify breast tumors as benign or malignant. Experimental results on a publicly available DBT image dataset demonstrate that the proposed framework achieves superior breast tumor classification results, outperforming all existing deep learning-based methods.


  • Open Access

    Detecting Breast Tumors in Tomosynthesis Images Utilizing Deep Learning-Based Dynamic Ensemble Approach

    by Loay Hassan, Adel Saleh, Vivek Kumar Singh, Domenec Puig, Mohamed Abdel-Nasser

    Digital breast tomosynthesis (DBT) stands out as a highly robust screening technique capable of enhancing the rate at which breast cancer is detected. It also addresses certain limitations that are inherent to mammography. Nonetheless, the process of manually examining numerous DBT slices per case is notably time-intensive. To address this, computer-aided detection (CAD) systems based on deep learning have emerged, aiming to automatically identify breast tumors within DBT images. However, the current CAD systems are hindered by a variety of challenges. These challenges encompass the diversity observed in breast density, as well as the varied shapes, sizes, and locations of breast lesions. To counteract these limitations, we propose a novel method for detecting breast tumors within DBT images. This method relies on a potent dynamic ensemble technique, along with robust individual breast tumor detectors (IBTDs). The proposed dynamic ensemble technique utilizes a deep neural network to select the optimal IBTD for detecting breast tumors, based on the characteristics of the input DBT image. The developed individual breast tumor detectors hinge on resilient deep-learning architectures and inventive data augmentation methods. This study introduces two data augmentation strategies, namely channel replication and channel concatenation. These data augmentation methods are employed to surmount the scarcity of available data and to replicate diverse scenarios encompassing variations in breast density, as well as the shapes, sizes, and locations of breast lesions. This enhances the detection capabilities of each IBTD. The effectiveness of the proposed method is evaluated against two state-of-the-art ensemble techniques, namely non-maximum suppression (NMS) and weighted boxes fusion (WBF), finding that the proposed ensemble method achieves the best results with an F1-score of 84.96% when tested on a publicly accessible DBT dataset. When evaluated across different modalities such as breast mammography, the proposed method consistently attains superior tumor detection outcomes.


  • Efficient Multi-Organ Multi-Center Cell Nuclei Segmentation Method Based on Deep Learnable Aggregation Network

    by Loay Hassan, Adel Saleh, Mohamed Abdel-Nasser, Osama A. Omer, Domenec Puig

    Automated cell nuclei delineation in whole-slide imaging (WSI) is a fundamental step for many tasks like cancer cell recognition, cancer grading, and cancer subtype classification. Although numerous computational methods have been proposed for segmenting nuclei in WSI images based on image processing and deep learning, existing approaches face major challenges such as color variation due to the use of different stains, the various structures of cell nuclei, and the overlapping and clumped cell nuclei. To circumvent these challenges in this article, we propose an efficient and accurate cell nuclei segmentation method based on deep learning, in which a set of accurate individual cell nuclei segmentation models are developed to predict rough segmentation masks, and then a learnable aggregation network (LANet) is used to predict the final nuclei masks. Besides, we develop cell nuclei segmentation software (with a graphical user interface—GUI) that includes the proposed method and other deep-learning-based cell nuclei segmentation methods. A challenging WSI dataset collected from different centers and organs is used to demonstrate the efficiency of our method. The experimental results reveal that our method obtains a competitive performance compared to the existing approaches in terms of the aggregated Jaccard index (AJI=89.25%) and F1-score (F1=73.02%). The developed nuclei segmentation software can be downloaded from https://github.com/loaysh2010/Cell-Nuclei-Segmentation-GUI-Application.


  • Promising Deep Semantic Nuclei Segmentation Models for Multi-Institutional Histopathology Images of Different Organs.

    by Loay Hassan, Adel Saleh, Mohamed Abdel Nasser, Osama A. Omer, Domenec Puig

    Nuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computational pathology. It is a fundamental task for different applications, such as cancer cell type classification, cancer grading, and cancer subtype classification. However, existing nuclei segmentation methods face many challenges, such as color variation in histopathological images, the overlapping and clumped nuclei, and the ambiguous boundary between different cell nuclei, that limit their performance. In this paper, we present promising deep semantic nuclei segmentation models for multi-institutional WSI images (i.e., collected from different scanners) of different organs. Specifically, we study the performance of pertinent deep learning-based models with nuclei segmentation in WSI images of different stains and various organs. We also propose a feasible deep learning nuclei segmentation model formed by combining robust deep learning architectures. A comprehensive comparative study with existing software and related methods in terms of different evaluation metrics and the number of parameters of each model, emphasizes the efficacy of the proposed nuclei segmentation models.


  • Open Access

    Efficient Stain-Aware Nuclei Segmentation Deep Learning Framework for Multi-Center Histopathological Images

    by Loay Hassan, Mohamed Abdel-Nasser, Adel Saleh, Osama A. Omer, Domenec Puig

    Existing nuclei segmentation methods have obtained limited results with multi-center and multi-organ whole-slide images (WSIs) due to the use of different stains, scanners, overlapping, clumped nuclei, and the ambiguous boundary between adjacent cell nuclei. In an attempt to address these problems, we propose an efficient stain-aware nuclei segmentation method based on deep learning for multi-center WSIs. Unlike all related works that exploit a single-stain template from the dataset to normalize WSIs, we propose an efficient algorithm to select a set of stain templates based on stain clustering. Individual deep learning models are trained based on each stain template, and then, an aggregation function based on the Choquet integral is employed to combine the segmentation masks of the individual models. With a challenging multi-center multi-organ WSIs dataset, the experimental results demonstrate that the proposed method outperforms the state-of-art nuclei segmentation methods with aggregated Jaccard index (AJI) and F1-scores of 73.23% and 89.32%, respectively, while achieving a lower number of parameters.


  • Partially Occluded Pedestrian Classification using Three Stage Cascaded Classifier

    by Saleh Aly, Loay Hassan, Alaa Sagheer

    Pedestrian detection is an important area in computer vision with key applications in intelligent vehicle and surveillance systems. One of the main challenges in pedestrian detection is occlusion. In this paper, we propose a novel pedestrian detection approach capable of handling partial occlusion. Three stage cascaded classifier is used in the proposed approach. Global classifier based on HOG features and linear-SVM is first employed to classify the whole scanning window. For ambiguous patterns, a set of part-based classifiers trained on features derived from non-occluded dataset are employed on the second stage. Several fusion methods including average, maximum, linear and non-linear SVM classifiers are examined to combine the obtained part scores. The linear/non-linear fusion coefficients are estimated by learning an additional third stage SVM classifier. The training data in the third stage classifier is augmented by generating a set of artificially occluded samples which simulate real occlusion conditions commonly occurred in pedestrians. Experimental results using Daimler and INRIA data sets show the effectiveness of the proposed approach.

  • Partially occluded pedestrian classification using part-based classifiers and Restricted Boltzmann Machine model

    by Saleh Aly, Loay Hassan, Alaa Sagheer, Hiroshi Murase

    One of the main challenges in pedestrian detection is occlusion. This paper presents a new method for pedestrian classification with partial occlusion handling. The proposed system involves a set of component-based classifiers trained on features derived from non-occluded dataset. The scores of all component classifiers are statistically modeled to estimate the final score of pedestrian. A generative stochastic neural network model namely Restricted Boltzmann Machine (RBM) is learned to estimate the posterior probability of pedestrian given its components scores. The training data used to train RBM model is artificially generated occluded data which simulate real occlusion conditions appeared in pedestrians. Experimental results on real-world dataset, with both partially occluded and non-occluded data shows the effectiveness of the proposed method.