Amir Hajjam El Hassani

Background/Objectives: Breast cancer continues to be one of the primary causes of death among women worldwide, emphasizing the necessity for accurate and efficient diagnostic approaches. This work focuses on developing an automated diagnostic framework based on convolutional neural networks (CNNs) capable of handling multiple imaging modalities. Methods: The proposed CNN model are trained and evaluated on several benchmark datasets, including mammography (DDSM, MIAS, INbreast), ultrasound, magnetic resonance imaging (MRI), and histopathology (BreaKHis). Standardized preprocessing procedures were applied across all datasets, and the outcomes were compared with leading state-of-the-art techniques. Results: The model attained strong classification performance with accuracy scores of 99.2% (DDSM), 98.97% (MIAS), 99.43% (INbreast), 98.00% (Ultrasound), 98.43% (MRI), and 86.42% (BreaKHis). These findings indicate superior results compared to many existing approaches, confirming the robustness of the method. Conclusions: This study introduces a reliable and scalable diagnostic system that can support radiologists in early breast cancer detection. Its high accuracy, efficiency, and adaptability across different imaging modalities make it a promising tool for integration into clinical practice.

Drug-induced and idiosyncratic cytopenias, including anemia, neutropenia, and thrombocytopenia, present significant challenges in fields like immunohematology and internal medicine. These conditions are often unpredictable, multifactorial, and can arise from a complex interplay of drug reactions, immune abnormalities, and other poorly understood mechanisms. In many cases, the precise triggers and underlying factors remain unclear, making diagnosis and management difficult. However, advancements in artificial intelligence (AI) are offering new opportunities to address these challenges. With its ability to process vast amounts of clinical, genomic, and pharmacovigilance data, AI can identify patterns and risk factors that may be missed by traditional methods. Machine learning algorithms can refine predictive models, enabling earlier detection and more accurate risk assessments. Additionally, AI’s role in enhancing patient engagement—through tailored monitoring and personalized treatment strategies—ensures more effective follow-up and improved clinical outcomes for patients at risk of these potentially life-threatening conditions. Through these innovations, AI is paving the way for a more proactive and personalized approach to managing drug-induced cytopenias.

Technical documentation written using the S1000D norm in aeronautics and aerospace fields is based on ‘applicability’ tags that define the context in which a document or part of it is valid. Filtering data modules by applicability is challenging because tags can have the potential to accumulate infinitely, reaching a level of complexity that becomes challenging for human interpretation. On the other hand, many changes were made to the applicability tag's structure when upgraded from version 2.3 to version 4.1. This paper presents a general AND/OR tree-based model to filter documents based on their applicability. Transformations were made to both versions to get a unique one, thereby, evaluating the input values and selecting accessible content for each user. The model has shown accurate filtering for all tests made, on multiple datasets of different versions, having applicability of different complexity ranges.

The increasing elderly population is affecting the social-economical balance in developed countries. Falls in general and particularly nocturnal falls are a major key-role players in the healthcare cost. In this paper, we propose a novel real-time sensor node system, non-wearable, and mounted on the contour of the bed mattress to continuously monitor sleep activities and detect nocturnal falls. The proposed system consists of eight node sensors, each consisting of an Inertial Measurement Unit (IMU), a Microcontroller Unit (MCU), and a serial network interface. The sensor nodes communicate on a single bus with a remote monitoring station. The system utilizes bed vibrations from accelerometers generated by body movements to detect and categorize sleep activities as well as identify fall events. The system generates real-time results and provides information about sleeping postures. The efficacy and robustness of the system are assessed by measuring key performance metrics, including sensitivity, accuracy, precision, and f1-Score. Experiments were conducted on 25 volunteers showed results surpassing 90% for all four metrics namely, sensitivity, accuracy, precision, and F1 score.

Breast cancer is considered one of the most-common types of cancers among females in the world, with a high mortality rate. Medical imaging is still one of the most-reliable tools to detect breast cancer. Unfortunately, manual image detection takes much time. This paper proposes a new deep learning method based on Convolutional Neural Networks (CNNs). Convolutional Neural Networks are widely used for image classification. However, the determination process for accurate hyperparameters and architectures is still a challenging task. In this work, a highly accurate CNN model to detect breast cancer by mammography was developed. The proposed method is based on the Particle Swarm Optimization (PSO) algorithm in order to look for suitable hyperparameters and the architecture for the CNN model. The CNN model using PSO achieved success rates of 98.23% and 97.98% on the DDSM and MIAS datasets, respectively. The experimental results proved that the proposed CNN model gave the best accuracy values in comparison with other studies in the field. As a result, CNN models for mammography classification can now be created automatically. The proposed method can be considered as a powerful technique for breast cancer prediction.

Image segmentation is a crucial aspect of clinical decision making in medicine, and as such, it has greatly enhanced the sustainability of medical care. Consequently, biomedical image segmentation has become a prominent research area in the field of computer vision. With the advent of deep learning, many manual design-based methods have been proposed and have shown promising results in achieving state-of-the-art performance in biomedical image segmentation. However, these methods often require significant expert knowledge and have an enormous number of parameters, necessitating substantial computational resources. Thus, this paper proposes a new approach called GA-UNet, which employs genetic algorithms to automatically design a U-shape convolution neural network with good performance while minimizing the complexity of its architecture-based parameters, thereby addressing the above challenges. The proposed GA-UNet is evaluated on three datasets: lung image segmentation, cell nuclei segmentation in microscope images (DSB 2018), and liver image segmentation. Interestingly, our experimental results demonstrate that the proposed method achieves competitive performance with a smaller architecture and fewer parameters than the original U-Net model. It achieves an accuracy of 98.78% for lung image segmentation, 95.96% for cell nuclei segmentation in microscope images (DSB 2018), and 98.58% for liver image segmentation by using merely 0.24%, 0.48%, and 0.67% of the number of parameters in the original U-Net architecture for the lung image segmentation dataset, the DSB 2018 dataset, and the liver image segmentation dataset, respectively. This reduction in complexity makes our proposed approach, GA-UNet, a more viable option for deployment in resource-limited environments or real-world implementations that demand more efficient and faster inference times.

The widespread adoption of Machine Learning and Artificial Intelligence across different domains can be attributed to the digitization of data over several decades, resulting in vast amounts of data, types and structures. Thus, data processing and preparation turns out to be a crucial stage. However, applying these techniques to S1000D standard-based data poses a challenge due to its complexity and the need to preserve logical information. This paper describes SALERNO, an S1000d AppLicability dEpended pRocessiNg mOdel. This python-based model analyzes and converts the XML S1000D-based files, into an easier data format that can be used in machine learning techniques while preserving the different logic and relationships in files. The model parses the files in the given folder, filters them, and extracts the required information to be saved in appropriate data frames and Excel sheets. Its main idea is to group the extracted information by applicability. In addition, it extracts the full text by replacing internal and external references, while maintaining the relationships between files, as well as the necessary requirements. Resulting files can be then saved in databases and used in different models. Documents in both English and French languages were tested, and special characters were decoded. Updates on the technical manuals were taken into consideration as well. The model was tested on different versions of the S1000D, and the results demonstrated its ability to effectively handle the applicability, requirements, references, and relationships across all files and on different levels.

Feature selection plays a vital role in promoting classifier performance. However, current methods cannot effectively distinguish the complex interaction in the selected features. To further remove these hidden negative interactions, we propose a Genetic Algorithm (GA)-like Dynamic Probability (GADP) method with mutual information method (MI), which has a two-layer structure. The first layer applies MRMR to obtain a primary feature subset. Based on the former candidate features, the GADP, as the second layer, can mine more supportive features. Instead of the commonly used approaches that they frequently focus on improving the operators of GA to enhance the search ability and lowering the convergence time, we improve GA by boldly abandoning the operators and employing the dynamic probability that relies on the performance of each chromosome to determine feature selection in the new generation. The dynamic probability mechanism significantly reduces the parameter number in GA and makes it easy to use. As each gene's probability is independent, the chromosome variety in GADP is more notable than in traditional GA, which ensures GADP has a wider search space and can effectively and accurately select relevant features. To verify the superiority of our method, we evaluate it under multiple conditions on 15 datasets. The results demonstrate the outperformance of the proposed method. Generally, it has the best accuracy. Further, we also compare the proposed model to the state-of-the-art heuristic methods like Harris Hawk Optimization (HHO), Salp Swarm Algorithm (SSA), and White Shark Optimizer (WSO). Our model still owns advantages over them.